skills/shipshitdev__skills
1
0
Fork 0
mirror of https://github.com/shipshitdev/skills.git synced 2026-09-19 06:04:15 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
v1.0.0
shipshitdev__skills/scripts/provenance-manifest.json
T
Vincent 496c535ee9 docs: correct model-policy drift found by routine audit (#90) 
- skill-standards.md: model-reference check is a hard error since 400068d, not a warning
- provenance-manifest.json + upstream-tracking.md: tool-design no longer retains a pinned model name; its code example uses the YOUR_MODEL placeholder
2026-07-23 18:36:45 +02:00

309 lines
24 KiB
JSON
Raw Permalink Blame History

{
"skills": [
{
"skill": "writing-plans",
"desc": "Turn a spec into a bite-sized, TDD-structured implementation plan that agentic workers can execute reliably.",
"source": "https://github.com/obra/superpowers/blob/main/skills/writing-plans/SKILL.md",
"source_path": "skills/writing-plans/SKILL.md",
"upstream_repo": "obra/superpowers",
"upstream_ref": "main",
"upstream_commit": "f2cbfbefebbf",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"drop_author": true,
"modifications": "Vendored as a standalone, platform-neutral marketplace plugin (Claude Code + Codex). The prior `author: Ship Shit Dev` frontmatter was incorrect and has been removed — this skill derives from obra/superpowers. No behavioral changes beyond provenance metadata."
},
{
"skill": "systematic-debugging",
"desc": "A disciplined root-cause debugging methodology — reproduce, isolate, hypothesize, verify — instead of guess-and-check.",
"source": "https://github.com/obra/superpowers/blob/main/skills/systematic-debugging/SKILL.md",
"source_path": "skills/systematic-debugging/SKILL.md",
"upstream_repo": "obra/superpowers",
"upstream_ref": "main",
"upstream_commit": "030a222af19c",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"drop_author": true,
"modifications": "Vendored from obra/superpowers as a standalone, platform-neutral marketplace plugin; ported self-contained with no behavioral changes beyond provenance metadata."
},
{
"skill": "verification-before-completion",
"desc": "Force explicit verification of every claim before marking work done — no “should work” without proof.",
"source": "https://github.com/obra/superpowers/blob/main/skills/verification-before-completion/SKILL.md",
"source_path": "skills/verification-before-completion/SKILL.md",
"upstream_repo": "obra/superpowers",
"upstream_ref": "main",
"upstream_commit": "48410c7f1973",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"drop_author": true,
"modifications": "Vendored from obra/superpowers as a standalone, platform-neutral marketplace plugin; ported self-contained with no behavioral changes beyond provenance metadata."
},
{
"skill": "receiving-code-review",
"desc": "Receive and act on code-review feedback without defensiveness — triage, address, and close the loop.",
"source": "https://github.com/obra/superpowers/blob/main/skills/receiving-code-review/SKILL.md",
"source_path": "skills/receiving-code-review/SKILL.md",
"upstream_repo": "obra/superpowers",
"upstream_ref": "main",
"upstream_commit": "1455ac0631e2",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"drop_author": true,
"modifications": "Vendored from obra/superpowers as a standalone, platform-neutral marketplace plugin. The prior `author: Ship Shit Dev` frontmatter was incorrect and has been removed. No behavioral changes beyond provenance metadata."
},
{
"skill": "finishing-a-development-branch",
"desc": "Cleanly finish a development branch — verify, merge, prune — without leaving loose ends.",
"source": "https://github.com/obra/superpowers/blob/main/skills/finishing-a-development-branch/SKILL.md",
"source_path": "skills/finishing-a-development-branch/SKILL.md",
"upstream_repo": "obra/superpowers",
"upstream_ref": "main",
"upstream_commit": "f2cbfbefebbf",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"drop_author": true,
"modifications": "Vendored from obra/superpowers as a standalone, platform-neutral marketplace plugin. The prior `author: Ship Shit Dev` frontmatter was incorrect and has been removed. No behavioral changes beyond provenance metadata."
},
{
"skill": "frontend-design",
"desc": "Create distinctive, production-grade frontend interfaces that avoid generic AI aesthetics.",
"source": "https://github.com/anthropics/skills/blob/main/skills/frontend-design/SKILL.md",
"source_path": "skills/frontend-design/SKILL.md",
"upstream_repo": "anthropics/skills",
"upstream_ref": "main",
"upstream_commit": "2235be7c60b5",
"last_synced": "2026-06-12",
"license": "Apache-2.0",
"mode": "rolling",
"modifications": "Vendored from Anthropic's official skills repo as a standalone marketplace plugin. No behavioral changes beyond provenance metadata."
},
{
"skill": "mcp-builder",
"desc": "Build Model Context Protocol servers — tools, resources, and prompts — to extend agent capabilities.",
"source": "https://github.com/anthropics/skills/blob/main/skills/mcp-builder/SKILL.md",
"source_path": "skills/mcp-builder/SKILL.md",
"upstream_repo": "anthropics/skills",
"upstream_ref": "main",
"upstream_commit": "ef740771ac90",
"last_synced": "2026-06-12",
"license": "Apache-2.0",
"mode": "rolling",
"modifications": "Vendored from Anthropic's official skills repo as a standalone marketplace plugin. No behavioral changes beyond provenance metadata."
},
{
"skill": "skill-creator",
"desc": "Guide for authoring effective Agent Skills — structure, description discipline, and progressive disclosure.",
"source": "https://github.com/anthropics/skills/blob/main/skills/skill-creator/SKILL.md",
"source_path": "skills/skill-creator/SKILL.md",
"upstream_repo": "anthropics/skills",
"upstream_ref": "main",
"upstream_commit": "b0cbd3df1533",
"last_synced": "2026-06-12",
"license": "Apache-2.0",
"mode": "rolling",
"modifications": "Vendored from Anthropic's official skills repo as a standalone marketplace plugin. No behavioral changes beyond provenance metadata."
},
{
"skill": "artifacts-builder",
"desc": "Build elaborate multi-component claude.ai HTML artifacts with shared UI and state management.",
"source": "https://github.com/anthropics/skills/blob/main/skills/web-artifacts-builder/SKILL.md",
"source_path": "skills/web-artifacts-builder/SKILL.md",
"upstream_repo": "anthropics/skills",
"upstream_ref": "main",
"upstream_commit": "ef740771ac90",
"last_synced": "2026-06-12",
"license": "Apache-2.0",
"mode": "rolling",
"modifications": "Vendored from Anthropic's `web-artifacts-builder` (renamed locally to `artifacts-builder`); the shared-UI import was repointed to `@agenticindiedev/ui` for this marketplace. Otherwise tracks upstream."
},
{
"skill": "theme-factory",
"desc": "Apply one of 10 preset themes (colors/fonts) to any artifact, or generate a new theme on the fly.",
"source": "https://github.com/anthropics/skills/blob/main/skills/theme-factory/SKILL.md",
"source_path": "skills/theme-factory/SKILL.md",
"upstream_repo": "anthropics/skills",
"upstream_ref": "main",
"upstream_commit": "ef740771ac90",
"last_synced": "2026-06-12",
"license": "Apache-2.0",
"mode": "rolling",
"modifications": "Vendored from Anthropic's official skills repo as a standalone marketplace plugin. No behavioral changes beyond provenance metadata."
},
{
"skill": "react-component-performance",
"desc": "Diagnose and fix React component render performance — memoization, ref stability, and re-render tracing.",
"source": "https://github.com/Dimillian/Skills/blob/main/react-component-performance/SKILL.md",
"source_path": "react-component-performance/SKILL.md",
"upstream_repo": "Dimillian/Skills",
"upstream_ref": "main",
"upstream_commit": "3db84e63d050",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"modifications": "Vendored as a standalone marketplace plugin. The prior `source: \"Dimillian/Skills (MIT)\"` shorthand was upgraded to a verifiable upstream URL + pinned commit. No behavioral changes."
},
{
"skill": "agent-browser",
"desc": "Drive a headless browser from the CLI — navigate, fill forms, screenshot, mock network, and extract data for web testing.",
"source": "https://github.com/vercel-labs/agent-browser/blob/main/skills/agent-browser/SKILL.md",
"source_path": "skills/agent-browser/SKILL.md",
"upstream_repo": "vercel-labs/agent-browser",
"upstream_ref": "main",
"upstream_commit": "d33bdb36f3f7",
"last_synced": "2026-06-12",
"license": "Apache-2.0",
"mode": "rolling",
"modifications": "Vendored from Vercel's agent-browser repo as a standalone marketplace plugin. Tracks the upstream `agent-browser` CLI (npm). No behavioral changes beyond provenance metadata."
},
{
"skill": "changelog-generator",
"desc": "Generate user-facing release notes from git commit history — categorize changes and rewrite technical commits as customer-friendly entries.",
"source": "https://github.com/ComposioHQ/awesome-claude-skills/blob/master/changelog-generator/SKILL.md",
"source_path": "changelog-generator/SKILL.md",
"upstream_repo": "ComposioHQ/awesome-claude-skills",
"upstream_ref": "master",
"upstream_commit": "044d48b594f0",
"last_synced": "2026-06-12",
"license": "Unspecified (no upstream LICENSE)",
"mode": "rolling",
"modifications": "Vendored from ComposioHQ/awesome-claude-skills. NOTE: upstream repo ships NO LICENSE file — content is all-rights-reserved by default; redistribution permission is unconfirmed. Flag for review before relying on it."
},
{
"skill": "context-fundamentals",
"desc": "Understand the components, mechanics, and constraints of context in agent systems — for designing architectures and debugging context failures.",
"source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/context-fundamentals/SKILL.md",
"source_path": "skills/context-fundamentals/SKILL.md",
"upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
"upstream_ref": "main",
"upstream_commit": "cbc2c978133d",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"modifications": "Ported to upstream v2.2.0 (2026-05-15 corpus, commit cbc2c978133d) on 2026-06-12 — body, references, and scripts now match upstream, including the routing framework and gotchas sections. Cross-references to upstream sibling skills not vendored here (context-compression, filesystem-context, project-development, latent-briefing) were removed so routing only names skills present in this marketplace."
},
{
"skill": "context-optimization",
"desc": "Apply optimization techniques (compaction, observation masking, KV-cache, partitioning) to extend effective context capacity.",
"source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/context-optimization/SKILL.md",
"source_path": "skills/context-optimization/SKILL.md",
"upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
"upstream_ref": "main",
"upstream_commit": "cbc2c978133d",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"modifications": "Ported to upstream v2.1.0 (2026-05-15 corpus, commit cbc2c978133d) on 2026-06-12 — body and references match upstream. Cross-references to upstream sibling skills not vendored here (context-compression, filesystem-context, project-development, latent-briefing) were removed so routing only names skills present in this marketplace. scripts/compaction.py carries two local hardening fixes over upstream (CodeRabbit-flagged, candidates to push back): ContextBudget now rejects total_limit<=0 and scales the reserved buffer so reservation_limit stays non-negative; calculate_cache_metrics now debits the unhit remainder of a partial cache hit from misses, where upstream counted only the hit fraction and so inflated hit_rate."
},
{
"skill": "context-degradation",
"desc": "Recognize, diagnose, and mitigate context-degradation patterns (lost-in-middle, poisoning, distraction, confusion, clash) in agent systems.",
"source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/context-degradation/SKILL.md",
"source_path": "skills/context-degradation/SKILL.md",
"upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
"upstream_ref": "main",
"upstream_commit": "25e1fa79a33f",
"last_synced": "2026-06-13",
"license": "MIT",
"mode": "rolling",
"modifications": "Imported 2026-01-20 (this repo's commit ef42a98) from muratcankoylan/Agent-Skills-for-Context-Engineering at v1.0.0-era content. Ported forward 2026-06-13 to upstream HEAD (commit 25e1fa79a33f); local body now tracks upstream v2.1.0 — carried the 7-entry Gotchas section, claim-* evidence IDs, Examples 3-4, Model-Specific Degradation Thresholds table, and negative-activation routing. References to siblings not vendored here (context-compression, filesystem-context) were stripped so routing names only marketplace skills. Local divergence: scripts/degradation_detector.py adopts the upstream numpy->stdlib rewrite (dependency removed); references/patterns.md is byte-identical to upstream. A 2026-06-13 review-hardening pass (CodeRabbit on PR #21) further diverges scripts/degradation_detector.py: detect_lost_in_middle now excludes negative/out-of-range critical indices from the score denominator, and analyze_context_structure measures middle-band content by line-span overlap rather than section-start only — candidates to push upstream. To diff: compare the upstream path on main since commit 25e1fa79a33f."
},
{
"skill": "memory-systems",
"desc": "Design layered agent memory architectures — working/short/long-term, entity, and temporal knowledge graphs — that persist state across sessions.",
"source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/memory-systems/SKILL.md",
"source_path": "skills/memory-systems/SKILL.md",
"upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
"upstream_ref": "main",
"upstream_commit": "25e1fa79a33f",
"last_synced": "2026-06-13",
"license": "MIT",
"mode": "rolling",
"modifications": "Imported 2026-01-20 (this repo's commit ef42a98) from muratcankoylan/Agent-Skills-for-Context-Engineering at v1.0.0-era content. Ported forward 2026-06-13 to upstream HEAD (commit 25e1fa79a33f); local body now tracks upstream v4.1.0 — the largest drift of this cluster — carrying the Production Framework Landscape table (Mem0, Zep/Graphiti, Letta, Cognee, LangMem), named benchmark tables (DMR, LoCoMo, HotPotQA), 8-entry Gotchas, Error Recovery subsection, claim-* IDs, and updated framework-integration examples in references/implementation.md and scripts/memory_store.py. References to siblings not vendored here (filesystem-context, context-compression, bdi-mental-states) were stripped. Local divergence: a Neo4j backend mention in the references Graphiti example was genericized to 'graph database backend'. A 2026-06-13 review-hardening pass (CodeRabbit on PR #21) further diverges scripts/memory_store.py (deterministic SHA-256 embedding seed replacing salted hash(); time_filter now applied to the vector-search filters) and references/implementation.md (same SHA-256 seed fix, local RNG instead of global np.random.seed) — candidates to push upstream. To diff: compare the upstream path on main since commit 25e1fa79a33f."
},
{
"skill": "multi-agent-patterns",
"desc": "Design multi-agent architectures (supervisor, swarm, hierarchical) that isolate context across instances without anthropomorphizing role division.",
"source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/multi-agent-patterns/SKILL.md",
"source_path": "skills/multi-agent-patterns/SKILL.md",
"upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
"upstream_ref": "main",
"upstream_commit": "25e1fa79a33f",
"last_synced": "2026-06-13",
"license": "MIT",
"mode": "rolling",
"modifications": "Imported 2026-01-20 (this repo's commit ef42a98) from muratcankoylan/Agent-Skills-for-Context-Engineering at v1.0.0-era content. Ported forward 2026-06-13 to upstream HEAD (commit 25e1fa79a33f); local body now tracks upstream v2.1.0 — carried the 8-entry Gotchas section, claim-* IDs, the 'Do not activate' routing block, the imperative rewrite of Detailed Topics, and the de-specified qualitative token-multiplier table. References to siblings not vendored here (project-development, hosted-agents, latent-briefing) were stripped; the cross-link to tool-design (vendored) is retained. Local divergence preserved: the 'Dispatching Parallel Agents' section does not exist upstream and was kept intact. references/frameworks.md is byte-identical to upstream. A 2026-06-13 review-hardening pass (CodeRabbit on PR #21) further diverges scripts/coordination.py: the three destructive-inbox call sites now re-queue non-target messages instead of dropping them, and submit_vote validates agent identity, the selection against the topic's options, and the confidence range — candidates to push upstream. To diff: compare the upstream path on main since commit 25e1fa79a33f."
},
{
"skill": "tool-design",
"desc": "Design tools agents can use effectively — consolidation, description engineering, response/error-format optimization, and MCP naming discipline.",
"source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/tool-design/SKILL.md",
"source_path": "skills/tool-design/SKILL.md",
"upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
"upstream_ref": "main",
"upstream_commit": "25e1fa79a33f",
"last_synced": "2026-06-13",
"license": "MIT",
"mode": "rolling",
"modifications": "Imported 2026-01-20 (this repo's commit ef42a98) from muratcankoylan/Agent-Skills-for-Context-Engineering at v1.0.0-era content. Ported forward 2026-06-13 to upstream HEAD (commit 25e1fa79a33f); local body now tracks upstream v2.2.0 — carried the 'Build for Future Models' subsection, the 8-point Tool Audit Checklist, the expanded Gotchas (4 unnamed bullets -> 9 named entries), negative-activation routing, and the rewritten scripts/description_generator.py (Protocol typing, dataclass spec, full evaluator methods). Reference to a sibling not vendored here (project-development) was stripped. Local divergence: Vercel-specific case-study and Sandbox references were genericized to neutral equivalents; the model name upstream uses in a code example was genericized to a YOUR_MODEL placeholder per the model-agnostic policy. references/best_practices.md is byte-identical to upstream. A 2026-06-13 review-hardening pass (CodeRabbit on PR #21) further diverges scripts/description_generator.py: ErrorMessageGenerator stores templates as dicts and interpolates values before json.dumps, fixing a runtime str.format crash on the literal JSON braces — candidate to push upstream. To diff: compare the upstream path on main since commit 25e1fa79a33f."
},
{
"skill": "evaluation",
"desc": "Build evaluation frameworks for agent systems — deterministic validation plus model-judged quality, with attention to token/tool/model performance drivers.",
"source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/evaluation/SKILL.md",
"source_path": "skills/evaluation/SKILL.md",
"upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
"upstream_ref": "main",
"upstream_commit": "25e1fa79a33f",
"last_synced": "2026-06-13",
"license": "MIT",
"mode": "rolling",
"modifications": "Imported 2026-01-20 (this repo's commit ef42a98) from muratcankoylan/Agent-Skills-for-Context-Engineering at v1.0.0-era content. Ported forward 2026-06-13 to upstream HEAD (commit 25e1fa79a33f); local body now tracks upstream v1.2.0 — carried the deterministic-validation concept, Examples 3-4 (deterministic gate + quality-gate dimensions), 8-entry Gotchas, the claim-evaluation-browsecomp-variance ID, and the softened Performance Drivers table (concrete 80%/~10%/~5% -> qualitative Primary/Secondary labels). Reference to a sibling not vendored here (harness-engineering) was stripped. Local divergence: scripts/evaluator.py adopts the upstream citation-detection fix (naive bracket-matching -> academic-citation regex). references/metrics.md is byte-identical to upstream. A 2026-06-13 review-hardening pass (CodeRabbit on PR #21) further diverges scripts/evaluator.py: evaluation_history and samples are now bounded deques (10k/50k) to cap memory growth, and two no-op f-string prefixes were removed (Ruff F541) — candidates to push upstream. To diff: compare the upstream path on main since commit 25e1fa79a33f."
},
{
"skill": "advanced-evaluation",
"desc": "Master LLM-as-a-Judge techniques — direct scoring, pairwise comparison, rubric generation, and bias mitigation (position, length, verbosity, authority).",
"source": "https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/main/skills/advanced-evaluation/SKILL.md",
"source_path": "skills/advanced-evaluation/SKILL.md",
"upstream_repo": "muratcankoylan/Agent-Skills-for-Context-Engineering",
"upstream_ref": "main",
"upstream_commit": "25e1fa79a33f",
"last_synced": "2026-06-13",
"license": "MIT",
"mode": "rolling",
"modifications": "Imported 2026-01-20 (this repo's commit ef42a98) from muratcankoylan/Agent-Skills-for-Context-Engineering at v1.0.0-era content (then pinned to creation commit 0b9a3b81bfea). Ported forward 2026-06-13 to upstream HEAD (commit 25e1fa79a33f); local body now tracks upstream v2.1.0 — carried full direct-scoring and pairwise prompt templates, the Metric Selection Framework table, three worked JSON examples, a 10-item Guidelines section, 8-entry Gotchas, a Scaling Evaluation section, the claim-advanced-evaluation-position-swap ID, and a fully rewritten scripts/evaluation_example.py. references/full-guide.md was renamed to references/evaluation-pipeline.md to match upstream. Reference to a sibling not vendored here (harness-engineering) was stripped; cross-links to tool-design (vendored) are retained. Local divergence: gpt-5.2 and claude-4-5-sonnet model names in references were genericized. To diff: compare the upstream path on main since commit 25e1fa79a33f."
},
{
"skill": "shadcn",
"desc": "shadcn/ui best practices — 58 rules across 10 categories covering setup, architecture, accessibility, styling, forms, data tables, and composition.",
"source": "https://github.com/pproenca/dot-skills/blob/master/skills/.curated/shadcn/SKILL.md",
"source_path": "skills/.curated/shadcn/SKILL.md",
"upstream_repo": "pproenca/dot-skills",
"upstream_ref": "master",
"upstream_commit": "b94ecb3dae52",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"modifications": "Vendored from pproenca/dot-skills `.curated/shadcn`. No behavioral changes beyond provenance metadata."
},
{
"skill": "tailwind",
"desc": "Community Tailwind CSS v4 best practices — 44 rules across 8 categories covering config, @theme, utilities, responsive/dark mode, and CSS-generation performance.",
"source": "https://github.com/pproenca/dot-skills/blob/master/skills/.curated/tailwind/SKILL.md",
"source_path": "skills/.curated/tailwind/SKILL.md",
"upstream_repo": "pproenca/dot-skills",
"upstream_ref": "master",
"upstream_commit": "91a64a6e7d49",
"last_synced": "2026-06-12",
"license": "MIT",
"mode": "rolling",
"modifications": "Vendored from pproenca/dot-skills `.curated/tailwind` (formerly `tailwindcss-v4-style` upstream). No behavioral changes beyond provenance metadata."
}
]
}
Reference in New Issue View Git Blame Copy Permalink