262da50f98
fix(context-timeline): detect Opus 1M context window dynamically ( #548 )
...
CONTEXT_LIMIT was hardcoded at 200_000 tokens. Users on Claude Opus 4.7
with the 1M context window (model: "opus[1m]") saw the dashboard report
80–90% usage when actual usage was 16–18%, producing constant false
alarms and making the meter unusable on long sessions.
Replace the constant with _detect_context_limit(cwd) which resolves the
limit in this order:
1. CONTEXT_TIMELINE_LIMIT env var (explicit override).
2. "[1m]" / "[1000k]" / "[200k]" suffix in the model field of
<cwd>/.claude/settings.json or ~/.claude/settings.json.
3. 200_000 fallback (current behaviour).
The limit is resolved once per _Builder instance, not per update tick,
so there is no per-event filesystem cost.
No new dependencies (still stdlib only). Default behaviour is unchanged
for users without [1m] in settings.
Verified live on a real Opus 1M session of ~178K tokens: meter went
from 89% (red, false alarm) to 17.9% (cyan, correct).
2026-04-27 20:10:27 -04:00
e11ff2e105
fix(context-timeline): cross-platform path encoding for transcript lookup ( #550 )
...
The `_encode_cwd` function only replaced `/` with `-`, which fails on
Windows where paths use `\` and include drive letters like `D:`.
Use regex to replace any non-alphanumeric character with `-`.
This handles all edge cases across platforms in a single expression.
Before: D:\Claude\mcx -> lookup failed
After: D:\Claude\mcx -> D--Claude-mcx (matches Claude Code encoding)
2026-04-27 20:09:13 -04:00
e44ddb78ca
improve: enhance accessibility-tester agent based on automated review ( #546 )
...
- Add correct YAML frontmatter with name, description, tools, and model fields
- Target WCAG 2.2 explicitly with all 9 new criteria listed in reference table
- Mandate hybrid testing methodology (automated + manual) with 40% coverage note
- Restrict tools to Read, Grep, Glob, Bash — no Write/Edit (auditor pattern)
- Set model to sonnet for deep ARIA and compliance reasoning
- Add two example blocks with user/assistant/commentary tags
- Add legal compliance mapping to ADA, Section 508, and EAA (June 2025)
- Add structured finding format with WCAG criterion, severity, remediation, verification
- Add summary scorecard template with severity counts and WCAG 2.2 criterion status
- Add ARIA patterns reference (dialog, combobox, tabs, navigation, live regions)
- Add screen reader test matrix (VoiceOver, NVDA, TalkBack, JAWS)
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-04-26 17:10:24 -04:00
fc2155655c
fix(context-timeline): reload sessions from disk on cache miss when daemon predates session
2026-04-25 23:24:30 -04:00
99f423049d
feat(hook): add monitoring/context-timeline real-time session visualizer
...
Persistent local HTTP daemon (port 7878, 1h watchdog) that reads Claude Code
JSONL transcripts and renders a git-graph timeline in the browser — one column
per agent (main + subagents), tool nodes color-coded by type, context-window
sidebar with cache/input/output breakdown. Pure stdlib Python, zero pip deps.
2026-04-25 23:08:28 -04:00
dc8d99bbc5
improve: enhance ai-ethics-advisor based on automated review ( #542 )
...
- Rewrote description with concrete usage triggers and 3 inline examples
- Added ISO/IEC 42001 (AI Management System) and ISO/IEC 42005 (AI System Impact Assessment) to Regulatory Compliance Framework
- Added UNESCO AI Ethics Recommendation (2021) with all 10 principles
- Added new "Agentic AI Ethics" section covering goal manipulation, minimal footprint, oversight checkpoints, inter-agent trust, and tool misuse surface
- Expanded tools list to include Edit, Bash, and Glob
- Replaced broken BiasMonitor Python skeleton with production-ready tooling inventory (IBM AIF360, Fairlearn, What-If Tool, Alibi Detect)
- Added "Output Artifacts" subsection defining 5 concrete deliverable files
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-04-25 22:10:19 -04:00
5948b4716f
improve: enhance data-scientist agent based on automated review ( #541 )
...
- Add model field (claude-sonnet-4-5) to frontmatter
- Remove duplicate Statistical methods and ML algorithms sections
- Replace non-functional context manager JSON block with plain-language context gathering instructions
- Modernize Tools & libraries: add Polars, DuckDB, MLflow, Great Expectations/Pandera, CatBoost, Altair
- Add Responsible Analysis section covering bias auditing, data privacy, reproducibility, transparency, and fairness metrics
- Add reproducibility and fairness items to data science checklist
- Remove hardcoded fabricated metrics from progress tracking JSON block
- Merge ANOVA/MANOVA into Statistical modeling section from removed duplicate
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-04-25 17:10:33 -04:00
0eec42a824
chore: sync claude-api skill from anthropics/skills (April 2026)
...
Adds memory_stores support to Managed Agents: new managed-agents-memory.md
reference, updated beta headers, reading guide, and API reference docs.
2026-04-24 15:27:14 -04:00
b066c26983
chore: sync pdf skill from anthropics/skills (April 2026)
...
Updated SKILL.md (new subscripts/superscripts section, improved description),
forms.md (simplified structure extraction workflow), and 7 scripts.
Added new extract_form_structure.py script.
2026-04-20 11:20:35 -04:00
4439f9b3f2
improve: enhance debugger agent based on automated review ( #531 )
...
- Add model: claude-sonnet-4-5 frontmatter field for consistent reasoning quality
- Remove fictional JSON Communication Protocol and Progress Tracking blocks
- Replace generic 3-phase workflow with 6-step fault-localization decision tree
- Add Observability-Driven Debugging section (traces, logs, change correlation)
- Trim description from ~2300 to ~1200 chars by tightening commentary blocks
- Remove non-executable rubber duck debugging technique
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-04-18 20:06:30 -04:00
5d84560b69
chore: sync claude-api skill from anthropics/skills (April 2026) ( #530 )
...
Synced cli-tool/components/skills/development/claude-api/ with upstream
anthropics/skills repo (commits March 22 – April 16, 2026).
Updated existing files (21):
- SKILL.md: grew from 20,548 to 32,987 bytes (Managed Agents dispatch logic)
- curl/examples.md, java/claude-api.md, php/claude-api.md, ruby/claude-api.md
- python/claude-api/{README,batches,files-api,streaming,tool-use}.md
- typescript/claude-api/{README,batches,files-api,streaming,tool-use}.md
- shared/{error-codes,live-sources,models,prompt-caching,tool-use-concepts}.md
- shared/managed-agents-{api-reference,client-patterns,core,environments,
events,onboarding,overview,tools}.md (previously existed, now updated)
- curl/managed-agents.md (previously existed, now updated)
Added new files (7 language + 1 shared):
- curl/managed-agents.md (new entry; prior file was empty placeholder)
- go/managed-agents/README.md
- java/managed-agents/README.md
- php/managed-agents/README.md
- python/managed-agents/README.md
- ruby/managed-agents/README.md
- typescript/managed-agents/README.md
- shared/agent-design.md
- shared/model-migration.md (65 KB consolidated migration guide)
Local-only files preserved (not touched):
- python/agent-sdk/{README,patterns}.md
- typescript/agent-sdk/{README,patterns}.md
Also updated:
- cli-tool/components/skills/ANTHROPIC_ATTRIBUTION.md: Last Updated → April 18, 2026
- Regenerated docs/components.json and dashboard/public/components.json
2026-04-18 19:01:17 -04:00
bb5fa62226
Merge pull request #519 from socialproKGCMG/add-szamlazz-command
...
Add szamlazz Hungarian invoicing command
2026-04-18 18:37:13 -04:00
cbaaec3257
Merge pull request #520 from yurukusa/add-shell-wrapper-guard
...
Add shell-wrapper-guard: detect destructive commands in interpreter one-liners
2026-04-18 18:36:20 -04:00
c1044aa26f
Merge pull request #522 from ipunithgowda/add-ai-agent-audit-and-llm-redteam
...
Add two security agent templates: ai-agent-audit-specialist and llm-redteam-specialist
2026-04-18 18:35:36 -04:00
6a84209134
Merge pull request #524 from apappascs/feature/claude-code-sessions-skill
...
feat(skills): add claude-code-sessions productivity skill
2026-04-18 18:34:54 -04:00
ccfc5b46c2
Add premium-web-design skill
...
Adds a new skill under creative-design for generating premium,
Awwwards-quality website designs as React components. Teaches Claude
the AI-aesthetic blacklist, a 15-entry Structural DNA Catalog, deep
industry reference research, a Spline 3D playbook, and a 15-point
prompt checklist that every build must answer before writing JSX.
2026-04-17 15:15:48 -04:00
6ef73fd752
feat(skills): add claude-code-sessions productivity skill
...
Add session intelligence skill for searching, analyzing, and managing
Claude Code session history. Provides 11 slash commands and a web
dashboard for full-text search, token analytics, task management,
and session comparison.
GitHub: https://github.com/apappascs/claude-code-sessions
Signed-off-by: Alexandros Pappas <apappascs@gmail.com >
2026-04-15 14:35:18 +02:00
5d80745513
Merge pull request #521 from kiliancm94/narrow-simple-notifications
2026-04-14 09:07:36 -04:00
303b0407e0
Add SwarmVault skill
2026-04-13 23:17:58 +01:00
40ed4aec94
Add llm-redteam-specialist agent
2026-04-14 00:45:10 +05:30
3407b5a59b
Add ai-agent-audit-specialist agent
2026-04-14 00:45:08 +05:30
aa977104c9
fix: address P1 review issues from cubic-dev-ai
...
1. Python one-liner: detect version-suffixed executables (python3.11, python3.12)
Pattern: python[23]? → python[23]?(\.[0-9]+)?
2. Pipe-to-shell: detect shell invocations with arguments (| sh -s, | bash -c)
Pattern: \|\s*(sh|bash|zsh)\s*$ → (\s|$)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 20:44:36 +09:00
7d83fa8647
fix(hooks): narrow simple-notifications to Stop and Notification events
...
The PostToolUse hook with a wildcard matcher fires on every single tool
call, flooding the user with dozens of notifications per turn. Replace
with Stop (fires once when Claude finishes) and Notification (fires
when Claude needs user input), matching the pattern already used by
discord-notifications and slack-notifications hooks.
2026-04-13 10:59:52 +02:00
5299c0c18d
Add shell-wrapper-guard hook to security category
...
Detects destructive commands hidden in shell wrappers (sh -c, bash -c,
python3 -c, node -e, etc). Complements dangerous-command-blocker by
catching 8 bypass vectors that evade direct command checks.
From cc-safe-setup (667 hooks, 9,200+ tests, 800hrs autonomous operation).
https://github.com/yurukusa/cc-safe-setup
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-13 17:45:08 +09:00
35eba22bc4
Add szamlazz Hungarian invoicing command
2026-04-12 19:29:24 +02:00
c9a7778177
feat(skills): sync claude-api skill with upstream anthropics/skills
...
Added 10 upstream files from https://github.com/anthropics/skills to
cli-tool/components/skills/development/claude-api/:
New files (Managed Agents beta support):
- shared/agent-design.md — agent design patterns: bash vs dedicated tools,
context management, caching principles
- shared/managed-agents-overview.md — reading guide, beta headers, mandatory flow
- shared/managed-agents-core.md — core concepts and data model
- shared/managed-agents-environments.md — per-session container configuration
- shared/managed-agents-tools.md — tools available in Managed Agents
- shared/managed-agents-events.md — SSE event stream reference
- shared/managed-agents-client-patterns.md — stream reconnect, interrupts, gotchas
- shared/managed-agents-onboarding.md — step-by-step setup interview script
- shared/managed-agents-api-reference.md — full API endpoint reference
- curl/managed-agents.md — raw HTTP examples for Managed Agents
Updated SKILL.md:
- Added "Before You Start" section (non-Anthropic provider guard)
- Added "Output Requirement" section (SDK vs raw HTTP rules)
- Added "Subcommands" dispatch block
- Updated language support table: "Agent SDK" → "Managed Agents (beta)"
with expanded language coverage (Java, Go, Ruby, PHP, cURL now listed)
- Replaced "Agent SDK" surface with "Managed Agents" in surface comparison table
- Updated decision tree with Managed Agents branch and 3P provider exclusion note
- Added full "Managed Agents (Beta)" section with reading guide and subcommand
- Updated reading guide with agent-design.md and Managed Agents task paths
- Preserved local YAML frontmatter customizations (trigger/no-trigger description)
Regenerated docs/components.json (805 skills total).
2026-04-09 11:26:05 -04:00
bc6bd60c7d
improve: enhance context7 MCP config and docs ( #513 )
...
- Pin package to @upstash/context7-mcp@latest for reproducible installs
- Add optional env block with CONTEXT7_API_KEY placeholder
- Extend description to mention activation phrase and Upstash authorship
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-04-08 09:55:46 -04:00
638276cb45
improve(agent): update frontend-developer with 2025-2026 best practices ( #510 )
...
- Bump framework versions: React 19+, Vue 3.5+, Angular 20+; add Next.js 15 and Nuxt 4
- Add Framework Expertise section with per-framework modern patterns (React Compiler, Vue reactive props destructure, Angular Signals + zoneless)
- Add Tooling Defaults section: Vite 6+, Biome v2/ESLint v9 flat config, pnpm, Tailwind v4
- Add State Management Architecture section separating server state (TanStack Query) from client state (Zustand/Pinia/Signals); deprecate Redux for new projects
- Add Testing Stack section: Vitest + Testing Library, Vitest Browser Mode, MSW v2, Playwright E2E (3-5 flows)
- Upgrade accessibility from WCAG 2.1 to WCAG 2.2 AA with new criteria (2.4.11, 2.5.8, 3.3.8); add axe-core and Lighthouse CI
- Add Performance Patterns section with rendering strategy decision tree and Core Web Vitals targets (LCP/INP/CLS)
- Add AI-Assisted Development Guidelines (tsc --noEmit, CLS image flag, 200-line code-reviewer handoff)
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-04-08 08:57:21 -04:00
6bbce90087
feat: Add 15 new MCP servers from GitHub MCP Registry ( #508 )
...
Migrated popular MCP servers not yet in our catalog, sourced from
the GitHub MCP Registry (github.com/mcp) topic search.
New MCPs by category:
- Database: dbhub (multi-DB), redis (official), mongodb-official
- DevTools: github-official, jupyter, jina-ai, mermaid, android-mcp, sentry-local
- Integration: n8n-mcp, alpaca-trading
- Productivity: google-workspace
- Research: arxiv-mcp-server
- Web: searxng, apify
All components reviewed by component-reviewer agent. Fixes applied
for kebab-case naming, credential handling via env blocks, and
server key consistency.
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-05 13:27:33 -04:00
e72ce062de
claude/migration-agent-skills-xbNj9 ( #504 )
...
* feat: Migrate 100 high-impact skills from antigravity-awesome-skills
Add curated selection of 100 skills from sickn33/antigravity-awesome-skills:
- Development (30): Angular, Astro, Bash, C, C++, C#, Django, .NET, Elixir, FastAPI,
Flutter, Go, Haskell, Hono, Java, JavaScript, Kotlin, Laravel, Next.js, Node.js,
PHP, Python, Ruby, Rust, Scala, SQL, Swift, TypeScript, Convex
- Web Development (14): React state/perf, React Native, shadcn, Tailwind, SvelteKit,
PWA, Drizzle ORM, TanStack Query, Zod, Zustand, Expo, Chrome extensions, Electron
- Architecture (10): API design, ADRs, patterns, DDD, event sourcing, GraphQL,
microservices, monorepo, SaaS multi-tenant, backend architect
- DevOps (12): Cloud architect, K8s, Terraform, GitHub Actions, GitOps, Helm,
observability, Prometheus, Grafana, Cloudflare Workers, incident response
- AI/ML (8): ML engineer, prompt engineering, data science/engineering, Pydantic AI,
LLM eval/ops, deep research
- Security (6): Security audit, secrets mgmt, threat modeling, web/API security, SAST
- Testing (6): E2E, JS/Python patterns, TDD, Playwright, k6 load testing
- Database (5): PostgreSQL, optimization, migration, architect, optimizer
- Productivity (5): Debugger, debugging strategies, code review, simplifier, perf
- Automation (5): GitHub, Slack, n8n, Linear, Jira
Source: https://github.com/sickn33/antigravity-awesome-skills
https://claude.ai/code/session_01A2r3TUNWqBWsqNYHne5NPB
* chore: Regenerate components.json from main base with 100 new skills
Pulled components.json from main, then regenerated to include the 100
newly migrated skills. Total: 805 skills.
https://claude.ai/code/session_01A2r3TUNWqBWsqNYHne5NPB
* chore: Update components.json with latest download stats
https://claude.ai/code/session_01A2r3TUNWqBWsqNYHne5NPB
* chore: Regenerate components.json after merge with main
https://claude.ai/code/session_01A2r3TUNWqBWsqNYHne5NPB
---------
Co-authored-by: Claude <noreply@anthropic.com >
2026-04-04 19:08:10 -04:00
004d888cc1
refactor: migrate worktree commands from wt/* to claude/* branch prefix
...
All worktree commands, skills, and guides now use claude/* as the default
branch prefix, matching Claude Code's actual worktree behavior. Updated
both .claude/commands/ and cli-tool/components/ versions.
2026-04-03 11:14:40 -04:00
119da71024
fix: apply date range filter to all dashboard charts ( #487 )
...
- Token Distribution by Type: compute totals from date-filtered
conversations instead of pre-aggregated detailedTokenUsage which
always contained all historical data regardless of the selected range
- Daily Productivity Trends: skip conversations outside the selected
date range (was iterating all conversations unconditionally)
- Workflow Intelligence charts: re-fetch /api/agents with startDate
and endDate query params on filter apply instead of reusing stale
initial-load data
Fixes #382
2026-04-01 21:21:55 -04:00
b68787aa41
improve: enhance code-reviewer agent with actionable review practices ( #492 )
...
- Remove fake JSON communication protocol blocks (request_type/status JSON)
- Add Review Setup section with concrete diff-scope commands
- Add Automated Pre-Checks section (npm audit, pip-audit, cargo audit, secret grep)
- Add Diff-First Reading Strategy with thresholds (<20, 20-100, >100 files)
- Replace noun-list checklist with imperative behavioral instructions per category
- Add Language-Specific Checks with concrete anti-patterns for TypeScript, Python, Rust, Go, SQL
- Add Output Format section with four-level severity classification (CRITICAL/HIGH/MEDIUM/LOW)
- Add Review Summary template with [N] placeholders and merge recommendation
- Replace hardcoded "47 files, 2 critical issues" delivery text with template
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-04-01 21:20:50 -04:00
6a4fa8213c
fix: recognize both "Task" and "Agent" tool names in analytics ( #491 )
...
Claude Code JSONL logs use `content.name === 'Agent'` but the
analytics code only checks for `'Task'`, causing Agent Usage
Distribution, Agent Activity Timeline, and Workflow Efficiency Score
charts to show empty data.
Accept both tool names in AgentAnalyzer, chats-mobile, and
teams-dashboard.
Fixes #488
Co-authored-by: easonysliu <easonysliu@tencent.com >
2026-04-01 13:38:01 -04:00
36fa6dbd5d
feat: Add supply-chain-guard skill, worktree commands, security hooks, and updated catalog
...
New components:
- supply-chain-guard skill (security): npm/PyPI/CI supply chain scanner with IOC database
- worktree-guide skill: parallel development with git worktrees
- dependabot-review skill: automated Dependabot PR management
- worktree-check/cleanup/deliver/init commands (git-workflow)
- edit-audit-log hook (development-tools)
- env-file-protection and force-push-blocker hooks (security)
Also includes:
- Regenerated components.json catalog (docs + dashboard)
- TinyFish featured page updates and logo
- .vercelignore and dashboard .gitignore updates
2026-03-31 21:13:20 -04:00
a1dde8b1d2
improve: Update python-pro agent with Python 3.12+, uv, Ruff, Polars ( #489 )
...
- Bump Python version target from 3.11+ to 3.12+ across frontmatter and body
- Add PEP 695 type parameter syntax to Type system mastery section
- Add free-threaded execution note (Python 3.13+, PEP 703) to async section
- Replace Poetry with uv as primary package manager; keep Poetry for legacy teams
- Replace Black with Ruff (ruff format + ruff check) in dev checklist and quality checklist
- Add pyright as alternative to mypy in type checking references
- Add Polars for high-performance DataFrame operations to data science section
- Add Polars mention to data pipeline optimization example in frontmatter
- Expand Pydantic to v2 (model_config, TypeAdapter, model_validate)
- Add SQLModel for FastAPI-native ORM to web framework section
- Remove Web scraping best practices section (niche, out of scope)
- Merge Memory management patterns and Scientific computing bullets into Performance optimization and Data science sections
- Update dependency analysis reference from pip/poetry to uv/pip
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-03-31 18:48:43 -04:00
31218fbfa5
feat: Add TinyFish Web Agent MCP component ( #486 )
...
Adds HTTP-based MCP for web browsing and data extraction via TinyFish.
Uses OAuth 2.1 auth with support for async tasks and stealth browser profiles.
2026-03-30 12:17:07 -04:00
fb27d6fe8d
Merge pull request #467 from davila7/dependabot/npm_and_yarn/cli-tool/jest-30.3.0
...
chore(deps-dev): bump jest from 30.0.4 to 30.3.0 in /cli-tool
2026-03-27 10:14:33 -04:00
f864744c58
enhance: Improve fullstack-developer agent (automated review) ( #475 )
...
- Add AI-native integration section covering LLM APIs, RAG pipelines, streaming responses, multi-provider abstraction, prompt versioning, and eval harnesses
- Anchor technology stack to specific versions: Next.js 15+/React 19, Node.js 22+/Hono/tRPC, PostgreSQL/Drizzle ORM, Vercel/Railway/Fly.io
- Expand monorepo tooling bullet with Turborepo vs Nx vs pnpm workspaces trade-offs
- Add edge computing and server component patterns section with per-route rendering decision framework (RSC/SSR/ISR/static/edge)
- Add 4th description example for AI-powered semantic search feature development
- Restructure from 8 flat bullet-list sections into focused action-oriented sections (Focus Areas, Approach, Edge Computing, AI-Native Integration, Implementation Workflow)
- Remove redundant JSON communication protocol blocks
- Tighten Implementation Workflow to 3 concise phases with concrete checklists
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-03-27 10:10:39 -04:00
6afad42f2e
Merge pull request #474 from xing-lin/feat/add-browseract-mcp
...
feat(mcp): add BrowserAct web data extraction service
2026-03-27 10:10:35 -04:00
1c2ec3a858
feat(mcp): add BrowserAct web data extraction service
...
Made-with: Cursor
2026-03-27 18:14:00 +08:00
50c3134b96
chore(deps-dev): bump jest from 30.0.4 to 30.3.0 in /cli-tool
...
Bumps [jest](https://github.com/jestjs/jest/tree/HEAD/packages/jest ) from 30.0.4 to 30.3.0.
- [Release notes](https://github.com/jestjs/jest/releases )
- [Changelog](https://github.com/jestjs/jest/blob/main/CHANGELOG.md )
- [Commits](https://github.com/jestjs/jest/commits/v30.3.0/packages/jest )
---
updated-dependencies:
- dependency-name: jest
dependency-version: 30.3.0
dependency-type: direct:development
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
2026-03-26 23:20:47 +00:00
ceafbd175d
chore(deps): bump ws from 8.18.3 to 8.20.0 in /cli-tool
...
Bumps [ws](https://github.com/websockets/ws ) from 8.18.3 to 8.20.0.
- [Release notes](https://github.com/websockets/ws/releases )
- [Commits](https://github.com/websockets/ws/compare/8.18.3...8.20.0 )
---
updated-dependencies:
- dependency-name: ws
dependency-version: 8.20.0
dependency-type: direct:production
update-type: version-update:semver-minor
...
Signed-off-by: dependabot[bot] <support@github.com >
2026-03-26 23:20:30 +00:00
29bb81c282
Feat/supply chain audit command ( #447 )
...
* feat(agent): add supply-chain-security analyst to security category
* feat(command): add supply-chain-audit analysis command
---------
Co-authored-by: Benjamin Barry <benjaminbarry@Mac.lan >
2026-03-26 17:50:29 -04:00
ee1d823a11
chore: Update claude-api skill from upstream anthropics/skills (March 26, 2026)
...
Synced 12 modified files and 1 new file (prompt-caching.md) from
https://github.com/anthropics/skills . Updates cover PHP expanded examples,
Go/Ruby/cURL additions, and prompt caching reference docs.
2026-03-26 11:06:03 -04:00
703b34104b
enhance: Improve prompt-engineer agent (automated review) ( #456 )
...
- Fix broken reasoning framework: complete Ordering field and Necessity scale
- Remove OpenAI attribution from description; add invocation example block
- Restrict tools to Read only (text-transformation agent needs no writes)
- Add XML Structure and CoT Opportunity dimensions to reasoning template
- Move meta-instruction NOTE out of output template, place as agent directive
- Fix stray markdown bold markers on Reasoning Before Conclusions guideline
- Integrate orphaned examples bullet into the Examples guideline line
- Add concrete worked example section (classify customer feedback)
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-03-26 10:10:20 -04:00
e42e8ba19c
fix: remove shorthand model names causing 404 API errors ( #453 )
...
Remove `model: sonnet/haiku/opus` from 396 component files. The Anthropic
API requires full model IDs (e.g., claude-sonnet-4-6), so shorthand names
cause 404 errors. Removing the field lets Claude Code use the user's
configured default model instead.
Fixes #99
https://claude.ai/code/session_01Hqx78XZNbdfh38YGZn4g4T
Co-authored-by: Claude <noreply@anthropic.com >
2026-03-25 20:19:17 -04:00
9594d221a2
chore: Update pdf, skill-creator, and webapp-testing skills from upstream anthropics/skills (March 22, 2026)
...
pdf (document-processing/pdf-processing):
- Replace SKILL.md with upstream pypdf-based version (was simplified pdfplumber version)
- Update FORMS.md with upstream changes
- Add reference.md (new)
- Add 8 Python scripts: check_bounding_boxes, check_fillable_fields, convert_pdf_to_images,
create_validation_image, extract_form_field_info, extract_form_structure,
fill_fillable_fields, fill_pdf_form_with_annotations
skill-creator (development/skill-development):
- Replace SKILL.md with upstream version
- Add agents/: analyzer.md, comparator.md, grader.md (new)
- Add assets/eval_review.html (new)
- Add eval-viewer/: generate_review.py, viewer.html (new)
- Add references/schemas.md (new, existing skill-creator-original.md preserved)
- Add 8 scripts: aggregate_benchmark, generate_report, improve_description, package_skill,
quick_validate, run_eval, run_loop, utils, __init__ (new)
webapp-testing (security/webapp-testing):
- Add examples/: console_logging.py, element_discovery.py, static_html_automation.py (new)
- SKILL.md unchanged (identical to upstream)
Regenerated catalog: 701 skills
2026-03-25 11:30:33 -04:00
ec68d49ea3
improve: enhance ultra-think command based on automated review ( #452 )
...
- Rewrote frontmatter description to be specific and outcome-oriented
- Removed performative Step 1 ("Initialize Ultra Think Mode") and replaced with a direct problem-framing opener
- Added scope-clarification gate to avoid unnecessary clarifying questions
- Replaced rigid 10-step waterfall with flexible "Required Analysis Elements" framework
- Integrated Key Principles (inversion, second-order thinking, cross-domain) into the analysis elements
- Replaced "2-4 pages" output target with quality-focused Output Expectations
- Preserved structured output template (Problem Analysis / Solution Options / Recommendation)
- Preserved all 4 usage examples
- Added extended thinking tip for hardest decisions
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
2026-03-25 10:31:29 -04:00
e2c15d2ae6
improve: enhance ui-ux-designer agent based on automated review ( #441 )
...
* improve: enhance ui-ux-designer agent based on automated review
- Rewrote description field as delegation-trigger prompt for better agent invocation
- Added WebFetch to tools for live resource lookups
- Added WCAG 2.2 criteria: focus not obscured (SC 2.4.11), dragging alternatives (SC 2.5.7), accessible authentication (SC 3.3.8), redundant entry (SC 3.3.7)
- Updated touch target guidance to cite WCAG 2.2 SC 2.5.8 (24x24px minimum, 44x44px design target)
- Added AI Interface Patterns (2024-2026) section covering input/output/refinement/trust/loading UX
- Added INP awareness to usability heuristics checklist (<200ms p75 target)
- Added JS-driven hover animation anti-pattern (kills INP scores) to Trendy But Bad
- Updated thumb zone guidance for variable grip patterns (Hoober follow-up research)
- Trimmed verbose CSS/HTML code blocks; replaced with concise instructions and implementation reminder
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com >
* Apply suggestions from code review
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
---------
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
2026-03-24 17:20:47 -04:00
Mario Hernandez