mirror of
https://github.com/davila7/claude-code-templates.git
synced 2026-09-19 01:30:23 +08:00
feat/concise-mode-setting
128 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Daniel Avila
|
1bcb3e5daa |
improve: modernize computer-vision-engineer agent (#821)
* improve: enhance computer-vision-engineer based on automated review - Fix deprecated TensorRT 10.x API (build_serialized_network, set_memory_pool_limit) - Add Foundation & Zero-Shot Vision Models section (SAM2/SAM3, Grounding DINO, CLIP, Florence-2, multimodal LLMs) with a model selection framework - Update default detector to YOLO11 with AGPL-3.0 licensing note and RT-DETRv2/RF-DETR alternatives - Modernize face recognition guidance to InsightFace/DeepFace, keep dlib face_recognition as a lightweight fallback only - Add multi-object tracking (ByteTrack via model.track) to video analysis - Replace unimplemented document-structure stub methods with a layoutparser-based approach and pointers to unstructured/VLM alternatives - Add a Compliance & Ethical Considerations section for biometric/PII data - Align frontmatter/structure with sibling data-ai agents: add model: sonnet, Glob/Grep tools, multi-example description, and an Integration with Other Agents section with explicit boundaries vs ai-engineer and ml-engineer Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: reset ByteTrack state between independent video streams Reusing a VideoAnalyzer instance for a new stream would otherwise carry stale track IDs from the previous session, since persist=True caches tracker state on the model's predictor. Addresses review feedback on PR #821. * fix: stop prior stream's threads before starting a new one start_real_time_analysis previously only reset tracker state but left any earlier capture/process threads running against the same frame_queue/result_queue/model, so a reused VideoAnalyzer instance could mix frames and tracker state across streams. Add stop_processing() to join the old threads and drain the queues before starting a new stream. Addresses further review feedback on PR #821. * fix: correct layoutparser color channel and text-region filter - Convert BGR (cv2.imread) to RGB before Detectron2LayoutModel.detect(), since PubLayNet was trained on RGB - Include PubLayNet's 'Title' and 'List' labels in text_regions, not just 'Text', so headings and list blocks aren't dropped Addresses cubic review feedback on PR #821. * fix: unblock capture thread on stop and fail loudly if it won't die cap.read() blocks until a frame arrives, so join(timeout=5.0) alone could return with the capture thread still alive and start_real_time_analysis would then reuse the shared model/queues underneath it. stop_processing now releases the VideoCapture to unblock read() immediately, and raises if a thread still hasn't exited after the join timeout instead of silently proceeding. Addresses further greptile review feedback on PR #821. * fix: re-check thread liveness on retry instead of the processing flag stop_processing() sets self.processing = False before it can guarantee the old threads have exited (e.g. one is still blocked in model.track() past the join timeout and it raises). A caller retrying start_real_time_analysis after that RuntimeError would see self.processing already False and skip straight to relaunch, letting the still-alive worker resume against the shared model/queues once it unblocks. Guard on actual thread.is_alive() instead so a retry keeps re-joining until the old threads are confirmed dead. Addresses further greptile review feedback on PR #821. * fix: call stop_processing unconditionally to always drain queues Gating stop_processing() on thread liveness skipped the queue drain whenever the previous call's stuck thread had exited by the time of a retry (the liveness check would then be False), leaking stale frames/results from the old stream into the new one. stop_processing is idempotent for dead/None threads, so call it unconditionally instead. Addresses cubic review feedback on PR #821. * fix: guard tracker reset against predictor without trackers attribute Ultralytics only registers .trackers on the predictor once model.track() has run at least once. If this model instance was previously used with model.predict()/model() (plain inference, no tracking), self.model.predictor exists but lacks a trackers attribute, so the direct attribute access raised AttributeError and aborted stream startup. Use getattr with a default instead of assuming the attribute exists. Addresses further greptile review feedback on PR #821. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
a5a9a4b260 |
improve: enhance data-analyst agent based on automated review (#817)
* improve: enhance data-analyst based on automated review - Add missing model field (sonnet) - Add clarifying-questions preamble before starting analysis - Fix stale Data Studio reference to Looker Studio - Ground vague concept lists with concrete tools & libraries - Add Responsible Analysis section for data privacy/governance - Remove stray duplicate blank line Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: address cubic review findings on data-analyst - Remove orphaned Communication Protocol / Analysis Context block (get_analysis_context) left dangling after the "Query context manager" step was replaced by the clarifying-questions preamble; the reference sibling data-scientist.md has no equivalent block either. - Drop the duplicated tool-name parenthetical on "Business intelligence" now that the same names live in the single "Tools & libraries" list. Co-Authored-By: Claude Code <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
a8b8011548 |
improve: enhance accessibility-tester agent based on automated review (#814)
* improve: enhance accessibility-tester agent based on automated review - Fix pa11y guidance to use --runner axe (default htmlcs runner is WCAG 2.0-era, misses 2.1/2.2 violations) - Note axe-core version requirement (>=4.5) for reliable WCAG 2.2 rule coverage - Annotate which WCAG 2.2 new criteria are actually automatable (only 2.5.8 via axe-core target-size) - Add a fully worked example finding to anchor severity/remediation phrasing - Add document/PDF accessibility checklist item (Section 508/EAA scope) - Add forced-colors / prefers-contrast manual checklist item Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: cover prefers-contrast alongside forced-colors in accessibility-tester Addresses review feedback on PR #814 — the manual checklist tested Windows High Contrast (forced-colors) but omitted the distinct prefers-contrast media feature, which interfaces can also use for alternate high-contrast styling. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QTTuf1dEt7QW83eyAPV7Lm * fix: require both forced-colors and prefers-contrast checks explicitly The previous wording used "or", allowing an audit to satisfy the checklist item by testing only one of the two distinct contrast display modes. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QTTuf1dEt7QW83eyAPV7Lm * fix: correct pa11y WCAG 2.2 coverage claim and axe-core version check scope pa11y's axe runner maps WCAG2AA to wcag2a/wcag21a/wcag2aa/wcag21aa tags only (confirmed against pa11y/pa11y#666 and lib/runners/axe.js) — it does not include wcag22aa, and pa11y has no --tags CLI flag. Also scope the axe-core version check to the tool actually being run, since @axe-core/cli --version only reports its own bundled axe-core, not pa11y's or @axe-core/playwright's independently-resolved versions. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QTTuf1dEt7QW83eyAPV7Lm * fix: give a concrete command for checking per-tool axe-core versions Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QTTuf1dEt7QW83eyAPV7Lm --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
2c2c1bbc00 |
improve: enhance model-evaluator agent based on automated review (#812)
* improve: enhance model-evaluator based on automated review - De-anchor hardcoded/aging model names (GPT-4o, Gemini 1.5, etc.) in frontmatter examples and Model Categories, replacing them with capability-tier language and a prominent instruction to verify current model IDs via WebSearch/WebFetch before recommending or testing - Add a "Required Initial Step: Requirements Gathering" section, matching the pattern used by sibling agents llm-architect and prompt-engineer - Add WebFetch to the tools list for pulling full pricing/leaderboard pages (LMSYS Arena, HELM) beyond WebSearch snippets - Add Inspect AI and OpenAI Evals to the Standard Frameworks & Tools table - Fix imprecise terminology: replace "GitHub Copilot" (a product, not a benchmarkable model) with actual code-specialized models, and clarify "Vision" models are a native capability rather than a separate SKU Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: align tier language in model-evaluator example The first description example's Context named balanced/flagship tiers but the assistant response evaluated budget/balanced tiers instead. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FHagP9k8UdbMyPJHjmYaTy --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
c1b2c31a2f |
improve: enhance prompt-engineer agent based on automated review (#809)
* improve: enhance prompt-engineer based on automated review - Add WebSearch to tools frontmatter, matching sibling ai-specialists agents - Add 4th description example covering Claude Code subagent/skill prompt optimization - Add guidance on avoiding aggressive imperative language (CRITICAL/YOU MUST/NEVER EVER) that causes overtriggering on current models - Route target-model answer to model-specific prompting guidance (verbosity, effort calibration, delegation, tool-triggering) - Add long-context document placement guidance (documents near top, instructions/query at end) - Expand agentic prompting into concrete sub-guidance (tool-triggering, overeagerness containment, destructive-action confirmation, tool-error handling, autonomy boundary) - Sharpen budget_tokens deprecation language (returns HTTP 400 on current models; effort/max_tokens is the replacement) - Reference Structured Outputs as a response-parsing option Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: qualify budget_tokens claim by model generation, regenerate catalog Addresses PR review feedback: - cubic-dev-ai/greptile: dashboard/catalog artifacts were stale after the prompt-engineer edits (old tool allowlist, 3-example description) — regenerated via scripts/generate_components_json.py. - cubic-dev-ai: the budget_tokens deprecation claim was overbroad — it now varies correctly by model generation instead of asserting a blanket HTTP 400 on all "current" models. Co-Authored-By: Claude Code <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
c403348e24 |
improve: task-decomposition-expert agent (tool scope, boundaries, PERT estimation) (#806)
* improve: enhance task-decomposition-expert based on automated review - Trim tools allowlist to Read, Glob, Grep, WebSearch (drop unused Write/Edit/Bash) - Add "Boundaries with Related Agents" section distinguishing from project-manager and scrum-master - Instruct grounding the WBS in the actual codebase via Read/Glob/Grep before finalizing - Add PERT (three-point) estimation guidance for Medium+ complexity tasks Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: address review feedback on task-decomposition-expert - Regenerate the dashboard content mirror so it matches the trimmed tool allowlist and new prompt sections (Greptile/cubic P2). - Reword the Boundaries section so it no longer claims project-manager and scrum-master appear in the Agent Handoff Plan table (cubic P3). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VZwwQ2MD4wsrwTJi5yM515 --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
93189924a0 |
improve: modernize salesforce-expert agent frontmatter and platform coverage (#802)
* improve: enhance salesforce-expert agent based on automated review - Add required model field (sonnet) to frontmatter - Replace invalid tools list (vscode, execute, sfdx-mcp/*, agent, todo) with valid Claude Code tool names - Replace generic description with routing-oriented description plus 3 <example>/<commentary> blocks - Add Agentforce & Agent Actions subsection (exposing Apex as Agentforce Actions, Topics/Instructions, guardrails) - Add Flow vs. Apex decision-guidance subsection - Add Lightning Web Security (LWS) and API-version-pinning guidance to operationalize the Release Aware Developer persona - Add Salesforce CLI Commands Reference section using the current unified sf CLI, noting sfdx is legacy - Normalize bullet indentation to a single "- " marker Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: remove TodoWrite from salesforce-expert tools allowlist TodoWrite isn't in StructuralValidator's accepted tool identifiers (Read, Write, Edit, Bash, Glob, Grep, WebSearch, WebFetch, *), which was flagging STRUCT_W006 on the PR. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
a6e030742d |
improve: enhance websocket-engineer agent with 2026 best practices (#801)
* improve: enhance websocket-engineer based on automated review - Add required model (sonnet) and color (cyan) frontmatter fields - Add discovery step to detect existing WebSocket stack before designing - Add protocol/library selection guidance (ws, uWebSockets.js, Socket.IO, SSE, WebTransport) - Add concrete security hardening section (Origin validation, wss://, rate limiting, backpressure, compression DoS) - Add edge/serverless hosting options (Durable Objects/PartyKit, Fly.io, Ably, Pusher) - Name concrete testing tools (k6, Artillery, autocannon/wrk, Toxiproxy) - Pin runtime/library baseline in persona (Node.js 22+/24+, ws/Socket.IO/uWebSockets.js) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * improve: broaden websocket-engineer discovery patterns Address Greptile review feedback on PR #801 — the discovery step only matched **/*.ws.* filenames and inferred deps from filenames; now it also matches common websocket/realtime filenames and reads package.json directly for dependency detection. Co-Authored-By: Claude Code <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
9a106cc6dd |
improve: enhance database-admin agent based on automated review (#799)
- Add required model field (sonnet) to frontmatter - Name specific database engines (PostgreSQL, MySQL, MongoDB, Redis) in description and Focus Areas - Add credential-safety instruction to Approach (env vars / secrets manager) - Add Glob, Grep to tools field for locating existing config files - Add differentiation/handoff note vs postgres-pro and database-optimizer - Name concrete per-engine monitoring commands and schema migration tooling Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
4fb73af42d |
improve: enhance search-specialist agent based on automated review (#797)
- Resolve name collision: rename cli-tool/components/agents/deep-research-team/search-specialist.md to multi-source-searcher.md (both filename and frontmatter name field), since it duplicated the canonical, higher-adoption ai-specialists/search-specialist.md and both installed to the same .claude/agents/search-specialist.md target path. Updated the cross-reference in research-analyst.md accordingly. - Tighten WebFetch guidance in ai-specialists/search-specialist.md to request verbatim extraction and note that WebFetch only returns raw text unmodified for Markdown sources under ~100K characters (otherwise a smaller model paraphrases it). - Add a "Handling Untrusted Content" section instructing the agent to treat fetched page content as untrusted data, not instructions, and flag rather than act on embedded directive-like text (prompt-injection hardening). - Clarify that allowed_domains/blocked_domains are mutually exclusive per WebSearch call. Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
9b0bada5a6 |
improve: enhance llms-maintainer agent (framework-aware discovery, more frameworks, safety) (#794)
* improve: enhance llms-maintainer based on automated review - Make content-discovery directories framework-aware (Astro/Nuxt/Next/SvelteKit) instead of a fixed generic list - Add detection and scan paths for Docusaurus, VitePress, and Jekyll - Raise maxTurns from 20 to 50 and add a batching/graceful-truncation strategy for large sites - Add "Use PROACTIVELY" to the description for reliable automatic delegation - Gate automatic git commits behind explicit user confirmation, consistent with the deletion-confirmation safety rule - Add optional llms-full.txt companion generation, opt-in only - Clarify that description/title length limits and the blockquote/H2 sections are house-style conventions, not llms.txt spec requirements Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: use detected output path when staging llms.txt, not hard-coded public/llms.txt Addresses Greptile review feedback on PR #794: the Step 8 git-add command was hard-coded to public/llms.txt, which misses the actual output path for SvelteKit/Hugo/Docusaurus (static/llms.txt), VitePress (<srcDir>/public/llms.txt), Jekyll (llms.txt at repo root), and the optional llms-full.txt companion. Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: resolve Next.js hybrid-router ambiguity and Jekyll _posts/ ignore-rule conflict Addresses cubic review feedback on PR #794: - The two separate Next.js detection bullets were not mutually exclusive; a hybrid app/+pages/ setup would have legacy pages/ routes silently omitted. Now scans both when both exist, preferring app/ for output. - Step 3's blanket "/_*" ignore rule would have silently skipped every Jekyll post, since _posts/ starts with an underscore. Added an explicit exception for _posts/ while still ignoring other Jekyll internals. Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: extend Jekyll ignore-rule exception to configured collection dirs Addresses cubic review feedback on PR #794: the underscore-path exception only covered _posts/, but Step 1 also tells the agent to scan Jekyll's configured collections (e.g. _projects/, _team/), which are similarly underscore-prefixed and were getting silently filtered by Step 3's ignore rule. Co-Authored-By: Claude Code <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
6b4a2716c6 |
improve: enhance sales-engineer agent (#791)
* improve: enhance sales-engineer based on automated review - Add required `model: sonnet` field to frontmatter - Replace vestigial "context manager" pattern with explicit "When Invoked" user-ask step - Remove fabricated metrics (demo/win-rate figures); use session-grounded placeholders instead - Add Human-in-the-Loop Pause Criteria for pricing, SLA, compliance, and POC sign-off - Add Source Boundaries for Research (public sources only, citations, no pretexting) - Add Anti-Fabrication section for compliance certifications, benchmarks, SLAs - Consolidate redundant bullet sections into a single Core Practices section - Modernize qualification methodology to MEDDIC/MEDDPICC with BANT as secondary reference - Add time-boxed POC guidance with upfront success criteria and decision gates - Add scope-boundary note to description (hand off pricing/contracts and compliance drafting) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * address review: avoid redundant discovery questions when context is already supplied Per Greptile review comment on PR #791. * address review: drop dangling "(below)" cross-reference in Anti-Fabrication section Per cubic review comment on PR #791. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
824146c009 |
improve: enhance hackathon-ai-strategist agent based on automated review (#790)
* improve: enhance hackathon-ai-strategist agent based on automated review - Expand tools to Glob, Grep, Write for codebase exploration and saving deliverables - Instruct WebSearch/WebFetch use for current model releases, sponsor API changes, and recent winning techniques - Add Boundaries with Related Agents / Integration with Other Agents sections - Merge duplicated Strategic Guidance / Optimizing for Constraints sections - Add AI-assisted rapid-prototyping tools (Lovable, Bolt.new, v0, Replit Agent) to strategic guidance - Add submission-format context gathering question and cross-reference in Phase 5 - Instruct confirming actual published judging rubric before defaulting to fixed weights - Add solo-hacker and virtual/remote-hackathon callouts Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: add fallback when submission-format details are unavailable Addresses review feedback on PR #790: the new context-gathering question about submission platform/format could stall the agent's advice when the event hasn't published those details yet. Fall back to a conservative default (~3 min cap, public repo) and flag it as an assumption to confirm later, instead of blocking. * fix: scale pitch outline to the actual submission cap Addresses cubic review feedback on PR #790: Phase 5 told the agent not to assume a 3-minute cap, but the only pitch outline provided was hard-coded to exactly 3 minutes with no scaling guidance. Reframe it as a 3-minute baseline with an explicit proportional-scaling rule. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
1ae011f168 |
improve: enhance api-architect agent with idempotency, OAuth 2.1, and RFC 9457 guidance (#789)
* improve: enhance api-architect agent based on automated review - Add idempotency-key guidance (Idempotency-Key header) for retry/backoff on non-idempotent methods - Update auth guidance from OAuth 2.0 to OAuth 2.1 (PKCE S256, Client Credentials, no Implicit/ROPC) - Resolve REST/GraphQL/gRPC scope inconsistency (gRPC recommendations hand off to api-designer) - Adopt RFC 9457 Problem Details as the REST error contract - Reference standard rate-limit headers (RateLimit, RateLimit-Policy, Retry-After) in resilience/security guidance - Add cursor/offset pagination guidance for GET-all - Add OpenTelemetry tracing guidance for the resilience layer - Add Deliverables, Bash Usage Constraint, and Integration with Other Agents sections (mirroring api-designer.md conventions) - Scope Bash tool access to output validation (redocly lint, graphql-inspector validate) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: address PR review findings in api-architect - Add PATCH to the REST methods intake list — the new idempotency default already referenced POST/PATCH but PATCH wasn't selectable - Fix rate-limit header mismatch: client-side backoff now parses the RateLimit header's reset parameter instead of a nonexistent RateLimit-Reset header, matching what the security checklist tells servers to emit Addresses review-bot findings on PR #789. * fix: correct RateLimit header parameter name to t draft-ietf-httpapi-ratelimit-headers-11 uses the t parameter (effective window in seconds) on the RateLimit header, not a "reset" parameter. Addresses greptile-apps follow-up finding on PR #789. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
9b2432237b |
improve: enhance ml-engineer agent with current tooling and scope clarity (#787)
* improve: enhance ml-engineer based on automated review - Modernize tooling ecosystem with named, current tools (KServe, vLLM/Triton, Feast/Tecton/Hopsworks, Evidently/WhyLabs/Arize) and note Seldon Core v2's BSL license - Ground bare "Data validation" bullets in named tools (Great Expectations, Pandera) - Add scope-clarifying sentence distinguishing this agent from machine-learning-engineer and mlops-engineer - Reframe hardcoded performance targets as illustrative/configurable SLAs - Name fairness/explainability tooling (Fairlearn, Aequitas, SHAP, LIME) and add model card/regulatory awareness note - Add ML-specific security bullets: artifact integrity, training data PII/leakage checks, adversarial robustness testing Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: move ml-engineer scope boundaries into frontmatter description Agent auto-selection reads the frontmatter description, not the body prompt text, so the scope-clarifying sentence added in the previous commit had no effect on delegation. Move it into the description field where it can actually reduce ambiguity with machine-learning- engineer, mlops-engineer, and ai-engineer. Addresses review feedback from greptile-apps[bot] on PR #787. * fix: route prompt-text optimization to prompt-engineer, not ai-engineer ai-engineer's own description explicitly hands off prompt-text-only optimization on an already-chosen model to prompt-engineer (ai-specialists category). ml-engineer's scope note was steering all "prompting work" to the generalist ai-engineer instead, which could reintroduce the routing ambiguity this review is meant to reduce. Addresses review feedback from cubic-dev-ai[bot] on PR #787. * fix: resolve contradiction between ml-engineer's example and its own delegation boundary Example 2 in the frontmatter description depicted ml-engineer handling pure inference-serving optimization (quantization, serving-strategy comparison, canary rollout) - exactly the work the new scope note says to delegate to machine-learning-engineer. Rewrote the example so ml-engineer owns the training-pipeline root cause (feature drift, retraining) and explicitly hands off the serving-side optimization, following the same hand-off pattern already used in ai-engineer.md's examples. Addresses review feedback from greptile-apps[bot] on PR #787. * clarify: distinguish model-level lifecycle work from platform infra in Example 3 Sharpens Example 3's commentary to explicitly frame deployment/ monitoring/retraining as model-level lifecycle ownership (a specific model's own rollout and retraining loop), distinct from the underlying platform/infrastructure automation (CI/CD, GPU orchestration, cross-model versioning) that mlops-engineer.md's own description already claims. Full disambiguation between the three sibling agents' descriptions would require editing mlops-engineer.md and machine-learning-engineer.md too, which is out of scope for this single-file review. Addresses review feedback from greptile-apps[bot] on PR #787. * fix: remove ambiguous "performance optimization" from opening invocation trigger The opening sentence of the frontmatter description is the first thing agent selection matches against, and it still claimed raw "performance optimization" as ml-engineer's trigger even though the same description delegates deep inference-serving optimization to machine-learning-engineer later on. Reworded the opening trigger to fold the redirect in directly, so a pure serving-latency-optimization request no longer matches ml-engineer's own invocation criteria. Addresses review feedback from greptile-apps[bot] on PR #787. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
f072c81dcc |
improve: enhance data-scientist agent (model alias, tooling, measurable checklist) (#783)
* improve: enhance data-scientist based on automated review - Replace pinned model claude-sonnet-4-5 with alias sonnet - Add WebSearch to tools (needed for literature review/methodology selection tasks already in the prompt) - Name concrete libraries: Fairlearn/AIF360 (bias/fairness), SHAP/LIME (interpretation), DoWhy/EconML/CausalML (causal inference), Optuna/Ray Tune/Hyperopt (hyperparameter tuning), DVC (versioning) - Tighten data science checklist to measurable/testable criteria instead of vague adverbial items - Upgrade pre-analysis clarifying questions into a structured, numbered gate that blocks proposing a model/methodology until key unknowns are resolved Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: repair double-escaped newlines in data-scientist description Pre-existing bug where the description field used \\n instead of \n, rendering as literal backslash-n text in the agent picker/dashboard. Also tightens grammar in the pre-analysis gate added in the prior commit. * fix: scope modeling requirements to modeling tasks in data-scientist gate Addresses Greptile review feedback: the clarification gate and checklist required a success-metric threshold and held-out-test/cross-validation steps even for pure exploratory profiling, visualization, and clustering work the agent explicitly supports. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
20be4bacde |
improve: fix droid agent to use Claude Code conventions instead of GitHub Copilot (#781)
* improve: enhance droid agent based on automated review - Fix frontmatter to use valid Claude Code subagent conventions (tools: Read, Grep, Glob, Bash, WebFetch, WebSearch instead of GitHub Copilot aliases; model: sonnet instead of pinned dated ID) - Remove GitHub Copilot Integration section (contradicted actual .claude/agents/ install path) and replace with a Claude Code usage section - Fix outdated --enabled-tools flag to current --restrict-tools/--additional-tools/--disabled-tools - Remove stale hardcoded model IDs from droid exec --model examples, point to docs.factory.ai/models instead - Add missing droid exec flags: --fork, -w/--worktree, --use-spec, -r/--reasoning-effort - Add <example>/<commentary> blocks to the description frontmatter matching sibling agent conventions - Clarify autonomy tier boundaries (medium = no push, high = push/deploy with safety checks) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: remove dangling model-ID hint from GitHub Actions example The parenthetical referenced a --model flag that was removed from the command in an earlier edit, leaving a confusing dangling hint. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01B3THSCtx7huxkRFmmUXne7 --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
6de26145ad |
improve: enhance llm-architect agent with 2026 tooling and techniques (#779)
* improve: enhance llm-architect based on automated review - Add Glob and Grep to tools list (parity with sibling agents) - Add SGLang to serving framework selection; remove stale vLLM version gates - Add Anthropic Contextual Retrieval technique and Voyage AI embedding option - Add GraphRAG/agentic retrieval escalation callout for multi-hop queries - Add Unsloth as fine-tuning library option for LoRA/QLoRA - Add ORPO and KTO preference-alignment methods to method-selection table - Add "verify current model IDs" disclaimer to multi-model routing section Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: clarify ORPO vs DPO/KTO selection criterion in llm-architect Both rows now key off dataset format (paired vs unpaired preferences) instead of mixing in GPU count, so ORPO no longer overlaps with the adjacent DPO/KTO rows. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Eckv6ssk3XuRXpbAzCxPgA * fix: split DPO and GRPO into separate rows with correct prerequisites GRPO is a reward/verifier-driven RL method, not a paired-preference method — the previous merge wrongly implied it needs paired preference data and a prior SFT checkpoint like DPO does. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Eckv6ssk3XuRXpbAzCxPgA --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
a7782213f0 |
improve: enhance ai-engineer (#775)
* improve: enhance ai-engineer based on automated review - Reposition scope as generalist for both classical ML and generative-AI/LLM engineering, with explicit handoffs to llm-architect, ml-engineer/machine-learning-engineer, and prompt-engineer - Add Generative AI / LLM Engineering section (LLM API providers, RAG basics, agentic patterns, fine-tuning, evaluation frameworks) - Add model: sonnet and WebSearch tool to frontmatter - Replace fictional context-manager protocol with a concrete Requirements Gathering step - Replace vague adjective checklists with measurable criteria and named tools/thresholds - Sharpen frontmatter description examples with concrete frameworks and a boundary-clarifying example - Disambiguate the "prompt-engineer" cross-reference (ai-specialists vs data-ai) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: remove stray content marker, make requirements gathering conditional Addresses Greptile review feedback on PR #775: an unmatched </content> marker leaked into the installed prompt, and the requirements-gathering step re-asked for details the user had already supplied. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QS1SncnafSWXMRXQa1yVBA --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
01bb22b727 |
improve: enhance ai-ethics-advisor agent (fix frontmatter, add current standards) (#772)
* improve: enhance ai-ethics-advisor based on automated review - Fix malformed YAML frontmatter: description examples were bare unindented text outside the description field, breaking YAML parsing / delegation matching. Merged into a single quoted description scalar per sibling convention. - Add missing model: sonnet field, consistent with other ai-specialists agents - Add NIST AI 600-1 (Generative AI Profile) subsection with the 12 GenAI risk categories - Add EU AI Act compliance-timeline caveat with current/pending deadlines - Cite OWASP Top 10 for LLM Applications (LLM01, LLM06) in Agentic AI Ethics - Add LLM/Generative System Explainability subsection (chain-of-thought faithfulness caveat, citation-grounded transparency) - Add Aequitas toolkit, 80% disparate-impact rule, and Bash least-privilege clarification Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * chore: sync generated content for ai-ethics-advisor Regenerate only the per-component content artifact for ai-ethics-advisor so the dashboard detail view reflects the updated frontmatter/body. Full catalog regeneration (docs/components.json, counts, search-index, download stats) is left to the scheduled update-json-data workflow, since a local run here pulled stale/wrong download counts that would have clobbered production data. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018wpuLQJaC6qskfDwUSioLF --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
599a084246 |
improve: enhance product-manager agent based on automated review (#768)
* improve: enhance product-manager based on automated review - Remove fabricated JSON "protocol" blocks and invented metrics (fake agent-to-agent JSON requests, +$4.2M/84% satisfaction canned numbers) that don't map to real Claude Code mechanics and risk priming fabricated outputs - Add model: sonnet to frontmatter (required field for agents) - Replace ~20 flat keyword-list sections with concrete worked frameworks: RICE scoring formula, OKR worksheet, discovery-to-launch checklist with exit criteria, one-page PRD template, and stakeholder communication cadence - Add explicit "How This Differs From Related Agents" section disambiguating from product-strategist (market/positioning strategy) and se-product-manager-advisor (GitHub issue creation), mirrored in description examples - Fix cross-reference from "customer-success" to the actual component name "customer-success-manager" - Add explicit Write/Edit output guidance (PRD/roadmap markdown documents) and anti-fabrication guidance for progress reporting Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: restore component download counts reset by catalog regeneration The prior commit regenerated the catalog without Supabase credentials, resetting download counts to 0 for ~1800 unrelated components. Restore each file's original download counts from main while keeping the product-manager description update. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012oa4wnU6RLfRH4gFWLFumC * fix: soften product-manager/product-strategist disambiguation product-strategist's own description explicitly covers feature prioritization and roadmap planning, so the prior wording (claiming it handles only market/positioning docs) contradicted the referenced agent. Acknowledge the overlap instead, per cubic review feedback. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_012oa4wnU6RLfRH4gFWLFumC --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
1b48fe8a5a |
improve: enhance sales-automator based on automated review (#767)
- Add Compliance & Anti-Spam Requirements section (CAN-SPAM/GDPR/CASL) - Add Accuracy & Anti-Fabrication guidance for case studies/social proof - Expand tools to Read, Write, Edit, Glob, Grep, WebFetch, WebSearch - Add Source Boundaries for Research section - Rewrite description with example blocks and explicit scope boundary - Add Integration with Other Agents section (handoffs) - Add model: sonnet and a "When Invoked" data-gathering first step Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
938c6656cf |
Rename risk-manager to trading-risk-manager, fix naming collision (#765)
* improve: rename risk-manager to trading-risk-manager, add model field - Resolve name collision with finance/risk-manager.md by renaming this trading/portfolio-focused agent to trading-risk-manager (frontmatter name + filename), sharpening the description to distinguish it from the enterprise ERM-focused finance/risk-manager - Add required model: sonnet field (was missing, failed component-reviewer checklist) - Add "When Invoked" context-gathering step and Human-in-the-Loop Pause Criteria (account size, risk tolerance, leverage/derivatives, full-Kelly requests) - Add financial-advice disclaimer as a required Output element - Add <example> blocks to description for reliable auto-invocation - Recommend fractional (half/quarter) Kelly over full Kelly, and add tail-risk hedging / leverage-liquidation risk / Sharpe-Sortino-Calmar focus areas - Add "Integration with Other Agents" section Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * chore: regenerate component catalog for trading-risk-manager rename Propagates the risk-manager -> trading-risk-manager rename (and the model/content updates) into the generated catalog artifacts so browse/search/install no longer reference the deleted business-marketing/risk-manager.md path. Also removes the now-orphaned component-content JSON for the deleted path. Addresses review feedback on PR #765. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
3642cfb99f |
improve: enhance backend-developer agent (runtime baselines, OWASP API security, discovery protocol) (#764)
* improve: enhance backend-developer based on automated review - Replace fictional context-manager JSON RPC messaging with concrete Glob/Grep/Read-based discovery steps (matches api-designer's pattern) - Update runtime baselines: Node.js 22+/24+, Python 3.12+ (3.13/3.14 fluency), Go 1.24+ - Reference OWASP API Security Top 10 (2023) explicitly, naming BOLA and Broken Object Property Level Authorization, plus secret management and short-lived token/MFA guidance - Cross-reference backend-architect for upfront design decisions and add it to Integration with other agents - Add model: sonnet and color: green to frontmatter - Add "Use PROACTIVELY" framing to the description Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: address PR review feedback on backend-developer agent Make manifest discovery Glob patterns recursive (**/package.json etc.) so nested services in monorepos are found, and reword the two "service boundary" checklist bullets so they consume/confirm backend-architect's design instead of contradicting the new architecture handoff note. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019vHEpW64LEdeoV7jhZGRPR * fix: remove remaining architecture-ownership claims from description examples The <example> blocks in the frontmatter description still had backend-developer "architect this service decomposition" and "design service boundaries", contradicting the handoff to backend-architect introduced earlier in this PR. Reworded both examples and the "full stack from architecture decisions" commentary line so the description is consistent with the body's ownership split. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019vHEpW64LEdeoV7jhZGRPR * fix: make remaining discovery glob patterns recursive openapi.yaml and docker-compose.yml were the only patterns in the Discovery Protocol Glob step without the **/ prefix, inconsistent with the monorepo-nested-service rationale applied to the other patterns. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019vHEpW64LEdeoV7jhZGRPR --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
74ec6c8f8f |
improve: enhance market-researcher agent based on automated review (#762)
* improve: enhance market-researcher based on automated review - Add missing model: sonnet frontmatter field - Forbid fabricated statistics in progress tracking and delivery notification (no more baked-in sample figures) - Replace fictional "context manager" protocol with direct user-scoping questions - Add Human-in-the-Loop Pause Criteria for ambiguous scope, conflicting data, unsourced estimates, and single-source claims - Add Ethical & Legal Boundaries section (public sources only, no paywalled/login-gated access, cite sources and as-of dates, no implied primary research) - Consolidate flat keyword lists into a "Core Practices" section and merge four redundant checklists into one Excellence checklist - Add data-freshness guidance for market-size/growth/share figures Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: address greptile review feedback on market-researcher - Only ask clarifying questions when the user hasn't already provided target market/objective/scope, avoiding redundant interruptions on fully-specified single-turn requests - Don't pause for confirmation on every single-source claim (common in market research); flag them instead per Ethical & Legal Boundaries Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: make research-planning confirmation conditional too The Research Planning step still unconditionally required confirming scope/market/objectives with the user, reintroducing the redundant- interaction issue already fixed in the When Invoked step. Now only confirms when something is still missing or ambiguous. Co-Authored-By: Claude Code <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
aed0d79ede |
improve: enhance legal-advisor based on automated review (#759)
* improve: enhance legal-advisor based on automated review - Add required model field (sonnet) - Add Human-in-the-Loop Pause Criteria for unconfirmed jurisdiction/facts - Rewrite description with scenario-driven examples for auto-delegation - Add When Invoked section to gather jurisdiction/data facts before drafting - Add WebFetch tool and expand Key Regulations for 2026 (EU AI Act, US state laws, DPDPA) - Move disclaimer into Output as a required document element - Add Integration with Other Agents section Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: correct double-escaped newlines in legal-advisor description The description field used \\n (literal backslash-n) instead of \n (YAML newline escape), which rendered the <example>/<commentary> blocks as a single wall of text. Co-Authored-By: Claude Code <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
96816247bb |
improve: enhance customer-support based on automated review (#757)
- Add required model field (sonnet) - Add explicit Escalation & Pause Criteria (refunds, security-sensitive actions, legal/compliance, unconfirmed bugs, low confidence) - Add Accuracy & Anti-Fabrication guardrail against inventing product behavior/timelines - Fix untestable "test solutions" instruction and add Grep/Glob tools for knowledge-base search - Enrich description with <example> blocks and scope boundary vs customer-success-manager - Add empathy technique guidance, Customer Data Handling (PII) note, and Integration with Other Agents section Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
d3664ac543 |
improve: enhance react-specialist (#755)
* improve: enhance react-specialist based on automated review - Update React version framing to React 19+; add React Compiler and React 19 Actions/hooks guidance (use(), useActionState, useOptimistic, useFormStatus) - Remove Recoil (archived by Meta, unmaintained); add prioritized state management guidance (TanStack Query, Zustand, Jotai, Redux Toolkit) - Modernize testing stack: Vitest as default runner, MSW for mocking, Playwright for E2E - Add Vite/Next.js/Remix tooling guidance, note CRA deprecation - Add concrete TypeScript compiler flags and WCAG 2.2 AA accessibility criteria with tooling - Trim redundant filler (duplicated Portals/error boundary/Suspense bullets) and update ecosystem list (shadcn/ui, Radix UI) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: correct WCAG 2.4.11 criterion citation in react-specialist 2.4.11 is "Focus Not Obscured (Minimum)" (Level AA), not "Focus Appearance" (that's 2.4.13, Level AAA). The mislabeled guidance would have led the agent to check focus indicator styling instead of whether focused elements are hidden by overlapping content, while still reporting AA compliance. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JbrpDkpsMuh5ckdeWiuqCU --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
33113c81f6 |
improve: enhance 3d-artist agent based on automated review (#752)
* improve: enhance 3d-artist agent based on automated review - Add procedural/Houdini and real-time VFX authoring (VEX, Unity VFX Graph, Unreal Niagara) - Add AI-assisted asset generation (Meshy, Luma Genie) and photogrammetry/Gaussian Splatting workflows - Add environment art tooling: Quixel Megascans/Bridge, SpeedTree, virtual texturing/streaming - Add concrete numeric tri-budgets by platform/asset role and a naming-convention example - Add WebSearch/WebFetch to tools and a scope/limitations statement - Expand asset optimization report and technical art documentation output bullets - Regenerate component catalog (docs/components.json, dashboard/public artifacts) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * chore: Update components and trending data --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
1e05dfa0aa |
improve: enhance customer-success-manager based on automated review (#750)
- Add missing model: sonnet field to frontmatter - Remove fictional "context manager" / Communication Protocol JSON scaffolding, replaced with a direct ask-user-first invocation flow - Replace fabricated example telemetry (invented revenue/NPS numbers) with instructions to report only actual confirmed session findings - Add Human-in-the-Loop Pause Criteria section for health/churn classification, renewal/pricing decisions, and financial interventions - Reframe the success checklist as illustrative reference points rather than assumed-achieved facts - Note the industry shift toward ML-based/real-time health scoring and NRR as a headline metric - Add a Source Boundaries section governing WebSearch/WebFetch use (public sources only, no pretexting, respect robots.txt, cite sources) - Narrow tools list by dropping Edit (Read, Write, Glob, Grep, WebFetch, WebSearch) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
c6da03cd41 |
improve: enhance marketing-attribution-analyst agent (#748)
* improve: enhance marketing-attribution-analyst based on automated review - Add required model field and rewrite description with Use-when framing plus 3 <example> blocks that disambiguate from content-marketer, business-analyst, and market-researcher - Fix tools to match sibling analyst agents (drop Bash, add Glob/WebFetch/ WebSearch) since this is a research/analysis role, not a shell-execution one - Add a "When Invoked" context-gathering step so the agent asks for the user's real tracking stack, attribution window, and data sources before producing any numbers - Add a Measurement Strategy Framework (MMM + incrementality + MTA triangulation) with spend-tier guidance - Update GA4 attribution model guidance (Data-Driven Attribution is now the default/only selectable model in most reports since 2023) - Update tracking infrastructure guidance for Consent Mode v2, server-side tagging, and Enhanced Conversions/server-side conversion APIs - Correct cookie/privacy framing (Chrome reversed third-party cookie deprecation; Privacy Sandbox trials shut down Oct 2025; Safari/Firefox still block by default) - Reference Google Meridian and Meta's Robyn as current standard MMM tools - Expand the single-line Privacy Compliance bullet into concrete guidance (Consent Mode v2 signals, data clean rooms, first-party data strategy) - Add data-provenance caveats to report/dashboard templates so figures are never fabricated Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: address Greptile review findings on attribution analyst - Scope Consent Mode v2 to applicable Google Ads/Analytics features rather than claiming it's mandatory for every EEA-facing site - Add explicit consent-state/regional-rules boundary to Enhanced Conversions / server-side conversion API guidance - Soften spend-tier MMM guidance to depend on data history/variance rather than spend level alone - Define the previously-missing apply_saturation() helper used by the MMM code example Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TXNgB3pCBw9SaHktzQWoFc * fix: address second round of Greptile findings - Ask for data-history length and channel spend variance during intake, not just spend level, so MMM fitness can be assessed before it's recommended - Scope the Data Quality Monitoring consent checklist to applicable Google Ads/Analytics features and include the ad_storage signal - Guard apply_saturation() against zero-spend channels (max=0) to avoid producing NaN features Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TXNgB3pCBw9SaHktzQWoFc * fix: address cubic review findings on attribution analyst - Correct GA4 attribution note to list the three current selectable reports (Data-Driven Attribution, Paid and organic last click, Google paid channels last click) instead of implying DDA is the only selectable model - Distinguish Google Meridian (genuinely Bayesian, posterior credible intervals) from Meta's Robyn (ridge regression, bootstrapped confidence intervals) in both the prose and the matching code comment, which previously still lumped both under "Bayesian" Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TXNgB3pCBw9SaHktzQWoFc * fix: close remaining checklist gaps flagged by Greptile - Require confirmed data fitness (not spend tier alone) before the Analysis Framework checklist marks MMM as the matched approach - Require consent-state propagation and suppression of ineligible events/identifiers as part of the conversion-API checklist item, not just "configured where applicable" Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TXNgB3pCBw9SaHktzQWoFc * fix: guard MMM example against missing spend observations calculate_adstock() carries values forward recursively, so a single NaN in a spend column poisons every subsequent period's adstock value; since that's a plain numpy array (not a pandas Series), the existing zero-guard in apply_saturation() doesn't catch it because max() on an array containing NaN returns NaN, not 0. Fill missing spend values before computing adstock so the illustrative pipeline runs on real-world data with gaps. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TXNgB3pCBw9SaHktzQWoFc * fix: stop silently imputing missing spend as zero in MMM example Blanket fillna(0) conflated genuinely missing observations with confirmed zero spend, which can materially bias adstock/attribution for the affected channel. Fail loudly instead and require the caller to make an explicit, documented choice per Greptile/cubic feedback. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01TXNgB3pCBw9SaHktzQWoFc --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
ce2a741ce9 |
improve: enhance content-marketer agent (#744)
* improve: enhance content-marketer agent based on automated review - Add model: sonnet frontmatter field for category consistency - Replace duplicate "Content types" section with distinct emerging/high-ROI formats list - Add "AI search & generative engine visibility" section (AI Overviews, LLM citation, llms.txt) - Add "Owned audience strategy" section (zero-party/first-party data, privacy-first) - Expand "Content quality" with explicit E-E-A-T signals and named-entity writing guidance - Add "Limitations" section scoping Write/Edit usage and handoffs - Add handoff lines to marketing-attribution-analyst, search-ai-optimization-expert, seo-specialist Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: correct seo-specialist handoff scope in content-marketer seo-specialist has no Write/Edit/Bash access (audit/strategy only), so routing technical SEO *implementation* to it left that work with no actual owner. Split the handoff: audits/recommendations to seo-specialist, implementation to frontend-developer or wordpress-master. Addresses Greptile review comment on PR #744. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
41ac74eaf7 |
improve: enhance accessibility-tester agent based on automated review (#741)
* improve: enhance accessibility-tester agent based on automated review - Fix broken automated-scan command: npx axe-core-cli -> npx @axe-core/cli --exit (with WCAG tag flag guidance) - Correct inaccurate legal-compliance framing; map each framework to its actual referenced WCAG version (Section 508 -> 2.0 AA, ADA Title II/III -> 2.1 AA, EAA/EN 301 549 -> approx 2.1 AA) - Add Track 1b: scripted keyboard/focus/ARIA-state testing via @axe-core/playwright - Qualify the automated-coverage statistic (30-40% industry-wide, axe-core ~57%) instead of an unqualified 40% - Note WCAG 3.0 is still a W3C Working Draft, not expected before ~2029 Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * address review feedback: fix missing AxeBuilder import, stale frontmatter examples - Add missing `import { AxeBuilder } from '@axe-core/playwright'` to the Track 1b code snippet so it's copy-pasteable - Update the frontmatter description's second example to drop a now-past "EAA June 2025 deadline" reference and match the per-framework WCAG version mapping already used in the body Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LsDjHUg19zLAPpSYuQxH5A * fix: add missing assertion to Track 1b Playwright example The snippet collected axe results but never asserted on them, so a copied test would exit 0 regardless of violations found. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LsDjHUg19zLAPpSYuQxH5A * fix: expand Track 1b withTags to full WCAG 2.0/2.1/2.2 scope withTags(['wcag22aa']) only activated the 9 new WCAG 2.2 criteria, silently skipping the WCAG 2.0/2.1 rules that Track 1 already covers via --tags wcag2a,wcag2aa,wcag21aa,wcag22aa. Align the two tracks. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LsDjHUg19zLAPpSYuQxH5A * fix: add missing wcag21a tag to accessibility scan commands The --tags/withTags lists omitted wcag21a (WCAG 2.1 Level A), causing axe-core to skip rules like Character Key Shortcuts, Pointer Gestures, Pointer Cancellation, Label in Name, and Motion Actuation. Applied to both Track 1 (@axe-core/cli) and Track 1b (@axe-core/playwright). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LsDjHUg19zLAPpSYuQxH5A --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
94f176ed8d |
improve: enhance competitive-analyst agent based on automated review (#737)
* improve: enhance competitive-analyst based on automated review - Remove fabricated example statistics from progress/delivery templates - Replace fictional context-manager JSON protocol with explicit user-questions step and Human-in-the-Loop Pause Criteria - Add Ethical & Legal Boundaries section for competitive intelligence - Add model: sonnet to match sibling agents in business-marketing - Consolidate repetitive bullet lists into denser Core Practices prose Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: resolve wording conflicts flagged by cubic review on PR #737 - Analysis step now allows sourced findings with explicit uncertainty labels instead of an absolute corroboration requirement, matching the later "flag single-source claims" guidance. - Non-public/paywalled competitor access is now an outright refusal with a redirect to public sources, not a pause-for-confirmation item (which implied it was user-authorizable, conflicting with the absolute prohibition in Ethical & Legal Boundaries). Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PgWKsHrXsL4B1ZdaKgkCvk --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
c754650ab9 |
improve: enhance legacy-modernizer agent based on automated review (#731)
* improve: enhance legacy-modernizer based on automated review
- Add missing model: sonnet frontmatter field (was required but absent)
- Add explicit ownership/hand-off statement clarifying scope vs
architecture-modernizer, refactoring-specialist, cloud-migration-specialist,
and database-optimizer
- Add concrete "Common legacy stacks & upgrade paths" section (COBOL,
Java EE/WebLogic, .NET Framework, AngularJS, Python 2, PHP 5/7)
- Add "AI-assisted analysis" guidance (dependency mapping, codemods,
auto-generated characterization tests)
- Replace vague filler bullets ("Team trained effectively", "Celebrate wins",
"Business value delivered continuously") with concrete, actionable deliverables
- Diversify description examples: replaced a redundant strangler-fig example
with a distinct mainframe/COBOL + version-upgrade-only scenario
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com>
* fix: address greptile review feedback on legacy-modernizer
Align the third description example's context with what it actually
demonstrates (.NET Framework version-upgrade only), and de-duplicate
the implementation-approach bullets that repeated the checklist items
verbatim.
* fix: address cubic review feedback on legacy-modernizer accuracy
Scope the .NET Framework upgrade path (Web Forms/WCF have no direct
Upgrade Assistant port and need separate plans), note 2to3 was removed
in Python 3.13+, and clarify that Grep/Glob only inventories
dependencies rather than producing a validated call graph.
* fix: soften zero-risk claim in legacy-modernizer example commentary
Version-only upgrades can still change runtime/dependency/batch
behavior; describe risk minimization via validation and rollback
instead of guaranteeing zero production risk.
---------
Co-authored-by: Claude <noreply@anthropic.com>
|
||
|
Daniel Avila
|
ebf6c519b7 |
improve: enhance bettoredge-value-finder agent component (#728)
* improve: enhance bettoredge-value-finder based on automated review - Fix name to kebab-case (bettoredge-value-finder) matching filename - Add required tools/model frontmatter, scoped to Read + mcp__bettoredge__* - Add system-prompt persona and "When invoked" workflow - Add Guardrails section enforcing bankroll limits, no fabricated results, and legal-age confirmation - Caveat the bid/ask-midpoint value-detection methodology - Add credential-handling guidance for live account login env vars - Bump version to 1.0.1 to match published npm package Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: address PR review feedback on bettoredge-value-finder - Remove unnecessary Read from tools frontmatter (agent only calls MCP tools, none of which touch the filesystem) - Fix bootstrap paradox: step 1 no longer unconditionally calls bettoredge_setup, which only exists once the MCP server is running - Move credential-handling warning ahead of the first instruction that has users embed BETTOREDGE_EMAIL/PASSWORD Co-Authored-By: Claude <noreply@anthropic.com> * fix: clarify bettoredge_status is read-only in guardrail wording bettoredge_status only surfaces current bankroll limits; it can't change them. Point users to the BettorEdge platform for that instead of implying the agent can modify limits through this tool. Co-Authored-By: Claude <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
1ada891736 |
improve: enhance communication-excellence-coach based on automated review (#725)
- Add missing required `model: sonnet` frontmatter field - Rewrite description with a "Use PROACTIVELY" trigger phrase and three <example> blocks for better delegation matching, dropping the unsupported "research-backed" claim (tools have no WebSearch/WebFetch) - Fix broken "See Also" references: professional-effective-communication -> professional-communication skill, /compose-email command -> email-composer skill, remove non-existent tech-talks-craft skill and /feedback-composer command, add difficult-workplace-conversations skill for roleplay scenarios - Add persona-drift resistance guidance to Roleplay Mode so simulated personas stay consistently resistant/motivated across an exchange instead of becoming generically agreeable Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
e76eda68af |
improve: enhance web3-integration-specialist agent based on automated review (#723)
* improve: enhance web3-integration-specialist based on automated review - Add required tools/model frontmatter fields (missing vs. sibling agents) - Add Security Considerations section (approval safety, blind-signing/permit phishing, XSS, RPC trust) - Add EIP-6963 multi-wallet discovery guidance - Reprioritize tech stack: wagmi v2 + viem v2 + TanStack Query v5 as default, ethers.js v6 as legacy fallback - Add account abstraction / smart-wallet UX coverage (ERC-4337, EIP-7702) - Add When to Stop and Ask and Integration with Other Agents sections - Add illustrative wagmi transaction lifecycle snippet Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: clarify wagmi hook state comment per review feedback The transaction-lifecycle snippet's comment conflated useWriteContract's status with useWaitForTransactionReceipt's isConfirming/isSuccess as one linear chain; they're separate hooks with separate state. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KVDXo97UwE3pamZyY89vsu * fix: grammar agreement in permit/Permit2 security note Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01KVDXo97UwE3pamZyY89vsu --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
c4a421e506 |
Improve 3d-artist agent: engine specifics, formats, and character tech art (#720)
* improve: enhance 3d-artist agent based on automated review - Add required `model: sonnet` frontmatter field - Expand tools to include Glob, Grep for asset-directory searches - Add engine/format-specific guidance: Unity import settings, Unreal Nanite caveat for skeletal meshes, FBX/glTF/USD export formats - Deepen character technical-art coverage: blend shapes, facial rigs, cloth/hair sim, IK, Unity Humanoid/Unreal Control Rig retargeting - Add cross-agent collaboration note with unity-game-developer, unreal-engine-developer, game-designer - Add asset version-control hygiene guidance (Git LFS/Perforce, naming conventions) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * Add trailing newline to 3d-artist.md Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016C48gymn7T1hJMvYPeu6gn * Fix technical accuracy issues flagged by cubic review - Qualify Nanite skeletal mesh support (UE5.5+, with limitations) instead of an absolute no-support claim - Note Read/Write Enabled's memory cost in Unity import guidance - Distinguish Humanoid vs Generic rig for non-humanoid characters - Correct Unreal retargeting terminology from Control Rig to IK Rig/IK Retargeter Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016C48gymn7T1hJMvYPeu6gn --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
1eec8f9423 |
improve: enhance smart-contract-specialist agent based on automated review (#713)
* improve: enhance smart-contract-specialist based on automated review - Narrow scope to architecture/design-pattern advisory role, resolving overlap with blockchain-developer - Add model: sonnet and tools: Read, Grep, Glob, WebSearch, WebFetch frontmatter (least-privilege, no Write/Edit/Bash) - Add "When to Stop and Ask" guardrails section - Add 2026 EVM/Solidity coverage: EIP-1153 transient storage, EIP-7201 namespaced storage, EIP-7702 (Pectra) EOA delegation, via_ir pipeline - Add security/verification toolchain advisory section (Slither, Aderyn, Echidna, Medusa, Certora, Halmos, forge snapshot) - Add anti-hallucination delivery-summary instruction - Add "Integration with Other Agents" section documenting handoff to blockchain-developer and smart-contract-auditor Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: remove unsourced gas-savings percentage for via_ir pipeline Addresses cubic review feedback on PR #713 — the "10-30% gas reduction" figure isn't backed by official Solidity docs, which only describe via-IR as producing "better gas-optimized code" without a specific percentage. Replaced with qualitative language consistent with the file's own anti-hallucination guardrail. Co-Authored-By: Claude Code <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
778fe26e8e |
improve: enhance smart-contract-auditor based on automated review (#695)
- Add required tools and model frontmatter fields (audit-only allowlist: Read, Grep, Glob, Bash, WebSearch, WebFetch) - Modernize security toolchain with Foundry, Aderyn, Echidna/Medusa, Certora Prover/Halmos - Reference OWASP Smart Contract Top 10 and add explicit severity classification (Critical/High/Medium/Low/Informational) - Cover cross-chain bridge exploits and business logic/tokenomics attack categories - Add Integration with Other Agents section and When to Stop and Ask guardrail Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
214dcbb9df |
improve: enhance shopify-expert agent (2026 currency + frontmatter fix) (#691)
* improve: enhance shopify-expert based on automated review - Fix invalid tools frontmatter (was VS Code Copilot Chat tool names, not Claude Code tools) - Add model/color fields and upgrade description with delegation examples - Correct REST vs GraphQL Admin API guidance for 2026 (REST legacy since Oct 2024, GraphQL mandatory for new public apps since Apr 2025) - Replace Remix-specific app guidance with React Router v7 (@shopify/shopify-app-react-router) - Add checkout.liquid deprecation deadline (Aug 26, 2026) - Add Polaris Web Components and Hydrogen/headless (Oxygen, Storefront MCP) guidance - Update Shopify CLI reference for CLI 4.0 flag changes Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: avoid false-positive javascript: XSS flag in shopify-expert Automated security audit's HTML-injection check does a naive substring match for "javascript:" and flagged the heading "...in JavaScript:" as a javascript: protocol XSS pattern. Reword to sidestep the false positive without changing meaning. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
bf829998ea |
improve: enhance octopus-deploy-release-notes-mcp based on automated review (#687)
- Add model field and rewrite description to state MCP dependencies and trigger phrases - Add Prerequisites / Required MCP Setup section (Octopus Deploy + GitHub MCP servers, env vars, example config) - Expand body into a structured workflow with ambiguity handling, missing-build-info fallback, and GitHub error handling - Add example markdown release-notes output and a Troubleshooting & Limitations section - Fix "release nots" typo - Move from api-graphql/ to devops-infrastructure/ (correct category for a deployment/release-management agent) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
12ad2ae42e |
improve: enhance cloud-migration-specialist agent (#682)
* improve: enhance cloud-migration-specialist agent based on automated review - Add 7 Rs migration framework (Rehost, Replatform, Repurchase, Refactor, Retire, Retain, Relocate) - Name concrete provider migration tooling (AWS Migration Hub/DMS/Transform MGN, Azure Migrate, GCP Migration Center) - Add Glob/Grep tools for assessment-first workload discovery - Expand cost optimization with FinOps techniques (RIs/Savings Plans, Spot, storage tiering) - Add managed container-orchestration targets (EKS/AKS/GKE, App Runner, Cloud Run, Container Apps) - Add scope/handoff note to cloud-architect, kubernetes-specialist, terraform-specialist, database-architect, security-engineer - Set explicit model: sonnet Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: correct AWS Transform MGN product name Address cubic review comment on PR #682. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
de30dfc260 |
improve: enhance mobile-app-developer agent (#680)
* improve: enhance mobile-app-developer based on automated review - Add disambiguation vs ios-developer and mobile-developer to description - Replace deprecated Xamarin.Forms with .NET MAUI (EOL May 2024) - Add iOS Privacy Manifest + SwiftData, Android target API/Privacy Sandbox requirements - Ground checklists with concrete tools (Fabric/TurboModules, Impeller, XCTest, Espresso, Detox/Maestro, Fastlane, Crashlytics, etc.) - Fix unrealistic "Accessibility AAA" target to WCAG 2.2 AA with concrete deliverables Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: remove deprecated Flipper reference from mobile-app-developer Flipper's React Native integration was deprecated in RN 0.73, removed from templates in RN 0.74, and the repo was archived Sep 2025. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01GarMVnacuEu455CeB9KgHj --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
3cf850bafd |
Improve graphql-security-specialist agent: modern attack coverage, tooling, fixes (#679)
* improve: enhance graphql-security-specialist based on automated review
- Add model, color, and permissionMode to frontmatter; add Glob and Edit to tools
- Rewrite description with <example>/<commentary> blocks matching sibling agents
- Add alias/batching overload ("battering ram") and CSRF attack coverage
- Add Recommended Security Tooling section (graphql-armor, graphql-cop, InQL)
- Fix Input Sanitization: clarify DOMPurify is XSS-only, add SQL/NoSQL injection prevention guidance
- Extend Query Allowlisting with Automatic Persisted Queries / trusted documents pattern
- Add closing "Integration with other agents" section
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com>
* fix: correct CSRF comment and remove fabricated Apollo plugin import
Addresses cubic-dev-ai review on PR #679:
- CSRF middleware comment now accurately describes rejecting all GET
requests lacking the preflight header, not just mutations
- Replaced non-existent ApolloServerPluginPersistedDocuments import
with a manual requestDidStart/didResolveOperation hook, which is a
real documented Apollo Server 4 plugin API
---------
Co-authored-by: Claude <noreply@anthropic.com>
|
||
|
Daniel Avila
|
f92a07ecd1 |
improve: rewrite and recategorize thinking-beast-mode agent (#674)
- Renamed Thinking-Beast-Mode.md -> thinking-beast-mode.md (kebab-case) and moved from api-graphql/ to development-tools/ (no GraphQL/API content; it's a generic autonomous engineering-task agent) - Added required model field plus color/permissionMode, matching sibling agent conventions - Replaced non-existent tool references (fetch_webpage, sequential_thinking, get_errors) with real Claude Code tools (WebFetch, WebSearch, Bash for lint/test) - Rewrote the marketing-fluff description into a concrete, example-driven trigger description - Stripped "quantum cognitive architecture" roleplay language and consolidated the workflow into Investigate -> Plan -> Implement -> Verify -> Report, keeping the legitimately good discipline (root cause debugging, rigorous verification, don't stop until truly done) - Added explicit guardrails (ask before destructive commands, stop on genuine blockers) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
f86a7feae7 |
improve: enhance data-engineer agent with 2026 data stack tooling (#671)
* improve: enhance data-engineer based on automated review - Add dbt transformation frameworks section (dbt Core, Fusion, tests, contracts, Semantic Layer) - Add managed EL ingestion and CDC tooling (Fivetran, Airbyte, Meltano, Debezium) - Name concrete data-quality/observability tools and data contracts (Great Expectations, Soda, Monte Carlo, Elementary, ODCS) - Modernize orchestration section (Airflow 3.x, Dagster asset-centric model, mark Luigi as legacy) - Add AI/LLM data pipeline expertise (vector DBs, embeddings, RAG data prep) - Align frontmatter/structure with sibling data-scientist.md (model field, clarifying-questions preamble) - Strengthen description for automatic delegation with PROACTIVELY phrasing and key tool names Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> * fix: use neutral Luigi label per review feedback cubic flagged the unsourced "maintenance mode" claim about Luigi in the orchestration section; use a neutral label instead. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
87b1f27231 |
improve: enhance documentation-expert based on automated review (#669)
- Add tools frontmatter field (Read, Write, Edit, Glob, Grep, WebFetch, WebSearch) - Add Diátaxis documentation framework section (tutorial/how-to/reference/explanation) - Expand documentation checklist with measurable, specific criteria - Add Limitations section clarifying scope boundaries vs code-reviewer, architect-reviewer, docusaurus-expert, documentation-engineer, api-documenter - Add worked examples (README skeleton, API endpoint doc block) Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com> Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Daniel Avila
|
5642a68649 |
improve: enhance seo-specialist based on automated review (#666)
Add missing model field, sharpen proactive-use description, add AI search/GEO visibility guidance, update Core Web Vitals to INP-based thresholds, and cross-reference search-ai-optimization-expert. Claude-Session: https://claude.ai/code/session_01GoWck91RfDye9q46JZDGUk Co-authored-by: Claude <noreply@anthropic.com> |