{"id":48368394,"url":"https://github.com/junerdd/skills","last_synced_at":"2026-05-19T14:01:35.208Z","repository":{"id":343286243,"uuid":"1177074478","full_name":"JUNERDD/skills","owner":"JUNERDD","description":"Reusable AI agent skills for Codex and compatible local runtimes","archived":false,"fork":false,"pushed_at":"2026-05-10T16:34:42.000Z","size":2437,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-10T17:26:57.868Z","etag":null,"topics":["agent-skill","ai-agents","codex","developer-tools","prompt-engineering","skills"],"latest_commit_sha":null,"homepage":"https://junerdd-skills.vercel.app","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/JUNERDD.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-09T17:06:23.000Z","updated_at":"2026-05-10T16:34:43.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/JUNERDD/skills","commit_stats":null,"previous_names":["junerdd/runtime-debug-skill","junerdd/skills"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/JUNERDD/skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JUNERDD%2Fskills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JUNERDD%2Fskills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JUNERDD%2Fskills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JUNERDD%2Fskills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JUNERDD","download_url":"https://codeload.github.com/JUNERDD/skills/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JUNERDD%2Fskills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33219365,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-19T07:54:09.561Z","status":"ssl_error","status_checked_at":"2026-05-19T07:54:08.508Z","response_time":58,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skill","ai-agents","codex","developer-tools","prompt-engineering","skills"],"created_at":"2026-04-05T15:31:02.632Z","updated_at":"2026-05-19T14:01:35.200Z","avatar_url":"https://github.com/JUNERDD.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# JUNERDD Skills\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"./docs/images/readme-hero.png\" alt=\"JUNERDD Skills hero\" width=\"960\"\u003e\n\u003c/p\u003e\n\nReusable AI agent skills published from a single repository.\n\nCurrent collection version: [`0.1.8`](./VERSION). Release notes are tracked in [`CHANGELOG.md`](./CHANGELOG.md) and published through GitHub Releases.\n\nThis repository is a skill collection, not a single-skill package. Installable skills live under [`skills/`](./skills/), and each subfolder is meant to be independently installable and expanded over time. The root [`VERSION`](./VERSION) file tracks the published version of the collection as a whole using SemVer; Git tags and GitHub Releases use the `vX.Y.Z` form. Individual tools or subpackages may keep their own runtime versions when needed.\n\nStable production URL: [https://junerdd-skills.vercel.app](https://junerdd-skills.vercel.app)\n\n## Website (Vercel)\n\nThe companion landing page is a Next.js app in [`web/`](./web/).\nEnglish is served from unprefixed paths such as `/` and `/skills/\u003cslug\u003e`;\nChinese is served from `/zh-CN` and `/zh-CN/skills/\u003cslug\u003e`.\n\n1. In the [Vercel dashboard](https://vercel.com/new), import this GitHub repository.\n2. Under **Configure Project**, set **Root Directory** to **`web`** (critical for this monorepo layout).\n3. Add **Environment Variable** on **Production**: **`NEXT_PUBLIC_SITE_URL`** = your production domain (example: `https://skills.example.com`, no trailing slash). This should match the **primary Production domain** configured under **Project → Settings → Domains** so Open Graph, canonical URLs, `sitemap.xml`, and `robots.txt` stay consistent.\n4. After the first successful Production deployment, open your GitHub repo **Settings → General** and set **Website** to that same production URL so the repository “About” box links to the live site.\n\n## 🧭 Skills At A Glance\n\nIf you are deciding what to install, start here:\n\n- [`comment-strategist`](#comment-strategist) - add high-value code comments without comment noise\n- [`exhaustive-code-slimmer`](#exhaustive-code-slimmer) - exhaustively reduce maintained code with AST-first evidence\n- [`git-commit`](#git-commit) - draft a Conventional Commit message from the staged diff\n- [`split-commits`](#split-commits) - split a mixed working tree into focused local commits\n- [`multitask-coordinator`](#multitask-coordinator) - coordinate complex subagent work with clear ownership boundaries\n- [`debug`](#debug) - debug runtime issues with an evidence-first logging workflow\n- [`hack-review`](#hack-review) - review whether an implementation relies on brittle hack-like shortcuts\n- [`receiving-hack-review`](#receiving-hack-review) - consume a hack-review report and verify each finding before changing code\n- [`regression-review`](#regression-review) - review code changes for user-visible behavioral regressions\n- [`receiving-regression-review`](#receiving-regression-review) - consume a regression-review report and verify each finding before changing code\n- [`react-wide-api-review`](#react-wide-api-review) - audit excessive React and TypeScript API field flow\n- [`receiving-react-wide-api-review`](#receiving-react-wide-api-review) - consume a React wide API review and resolve every item with evidence\n\n## 📦 Install\n\nIf you want an agent to install this repository for you without copying files, tell it:\n\n```text\nFetch and follow instructions from https://raw.githubusercontent.com/JUNERDD/skills/refs/heads/main/docs/INSTALL.md\n```\n\nIf the agent already has this repository open locally, it can read [`./docs/INSTALL.md`](./docs/INSTALL.md) directly instead of fetching the raw GitHub URL.\n\nThe CLI examples below intentionally use the latest `skills` tool version to avoid mismatches with older local installs.\n\nList the skills currently published from this repository:\n\n```bash\nnpx skills@latest add JUNERDD/skills --list\n```\n\nInstall a specific skill:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill \u003cskill-name\u003e\n```\n\nInstall globally for Codex:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill \u003cskill-name\u003e -g -a codex -y\n```\n\nExamples:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill debug\nnpx skills@latest add JUNERDD/skills --skill git-commit\nnpx skills@latest add JUNERDD/skills --skill split-commits\nnpx skills@latest add JUNERDD/skills --skill multitask-coordinator\nnpx skills@latest add JUNERDD/skills --skill comment-strategist\nnpx skills@latest add JUNERDD/skills --skill exhaustive-code-slimmer\nnpx skills@latest add JUNERDD/skills --skill hack-review\nnpx skills@latest add JUNERDD/skills --skill receiving-hack-review\nnpx skills@latest add JUNERDD/skills --skill regression-review\nnpx skills@latest add JUNERDD/skills --skill receiving-regression-review\nnpx skills@latest add JUNERDD/skills --skill react-wide-api-review\nnpx skills@latest add JUNERDD/skills --skill receiving-react-wide-api-review\n```\n\nManual symlink install still works if you prefer not to use the agent prompt:\n\n```bash\nmkdir -p ~/.agents/skills\nln -s \"$PWD/skills\" ~/.agents/skills/junerdd-skill\n```\n\n## 🧱 Repository Model\n\n- The collection version lives in the root [`VERSION`](./VERSION) file.\n- Release notes live in [`CHANGELOG.md`](./CHANGELOG.md), and published GitHub releases should use matching `vX.Y.Z` tags.\n- Use the release workflow to prepare a collection release. It opens a release PR that updates `VERSION`, the README version line, website version metadata, and `CHANGELOG.md` from one workflow input; merging that PR publishes the matching GitHub Release.\n- Each installable skill lives under `skills/\u003cskill-name\u003e/`.\n- Each skill owns its own `SKILL.md` plus any optional `agents/`, `references/`, `scripts/`, or `assets/` directories.\n- Root-level files describe the repository as a collection. Skill-specific behavior and deep operational details stay inside the relevant skill folder.\n- Shared repository assets such as screenshots can live outside `skills/` when they are not part of the installable package itself.\n\n## 🗂️ Current Skills\n\nUse the anchor list above for a quick jump, then read the section that matches your task.\n\n### `comment-strategist`\n\n[`skills/comment-strategist/`](./skills/comment-strategist/) is for documenting existing code without adding low-value comment noise. It focuses on intent, contracts, constraints, field meaning, and control-flow rationale instead of rewriting syntax in prose.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill comment-strategist\n```\n\nBest for:\n\n- documenting exported functions, interfaces, classes, and config objects\n- replacing outdated or redundant comments with durable explanations\n- adding guided comments inside complex logic while preserving the local comment style\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/comment-strategist/SKILL.md`](./skills/comment-strategist/SKILL.md)\n- Optional runtime metadata: [`skills/comment-strategist/agents/openai.yaml`](./skills/comment-strategist/agents/openai.yaml)\n\n### `exhaustive-code-slimmer`\n\n[`skills/exhaustive-code-slimmer/`](./skills/exhaustive-code-slimmer/) exhaustively searches for behavior-preserving code reductions. It combines AST-first structural evidence, audit scripts, deletion-first candidate search, oracle design, and an approval gate for architecture-level refactors so slimming improves maintainability instead of producing dense or risky code.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill exhaustive-code-slimmer\n```\n\nBest for:\n\n- finding removable files, branches, exports, dependencies, wrappers, and duplicate logic\n- using AST, language-server, parser, or static-tool evidence before text search for structural deletion claims\n- running deletion candidates against a build/test/lint/smoke oracle before accepting changes\n- identifying architecture problems that block safe code reduction and presenting DX-oriented options before refactoring\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/exhaustive-code-slimmer/SKILL.md`](./skills/exhaustive-code-slimmer/SKILL.md)\n- AST-first candidate generation: [`skills/exhaustive-code-slimmer/references/ast_first_candidate_generation.md`](./skills/exhaustive-code-slimmer/references/ast_first_candidate_generation.md)\n- Code-slim audit script: [`skills/exhaustive-code-slimmer/scripts/code_slim_audit.py`](./skills/exhaustive-code-slimmer/scripts/code_slim_audit.py)\n- Exhaustive shrink script: [`skills/exhaustive-code-slimmer/scripts/exhaustive_shrink.py`](./skills/exhaustive-code-slimmer/scripts/exhaustive_shrink.py)\n- Optional runtime metadata: [`skills/exhaustive-code-slimmer/agents/openai.yaml`](./skills/exhaustive-code-slimmer/agents/openai.yaml)\n\n### `git-commit`\n\n[`skills/git-commit/`](./skills/git-commit/) drafts a Conventional Commit message from the staged diff only. It is intentionally narrow: it reads what is already staged, proposes one accurate message, and does not mutate Git state.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill git-commit\n```\n\nBest for:\n\n- generating a clean commit subject from the current index\n- checking whether a staged batch is too mixed for one honest commit message\n- keeping commit wording grounded in staged files instead of unstaged work\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/git-commit/SKILL.md`](./skills/git-commit/SKILL.md)\n- Optional runtime metadata: [`skills/git-commit/agents/openai.yaml`](./skills/git-commit/agents/openai.yaml)\n\n### `split-commits`\n\n[`skills/split-commits/`](./skills/split-commits/) helps break a mixed working tree into a sequence of focused local commits. It stages one logical batch at a time, asks `$git-commit` for a message, and requires explicit confirmation before each `git commit`.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill split-commits\n```\n\nBest for:\n\n- separating unrelated concerns in the same working tree\n- isolating refactors from behavior changes\n- building a short series of reviewable local commits without pushing\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/split-commits/SKILL.md`](./skills/split-commits/SKILL.md)\n- Optional runtime metadata: [`skills/split-commits/agents/openai.yaml`](./skills/split-commits/agents/openai.yaml)\n\n### `multitask-coordinator`\n\n[`skills/multitask-coordinator/`](./skills/multitask-coordinator/) coordinates non-trivial multi-step work where an agent may use background subagents. It keeps the parent agent responsible for framing, shared contracts, delegation decisions, worker ownership boundaries, synthesis, verification, and user communication.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill multitask-coordinator\n```\n\nBest for:\n\n- deciding whether complex repo work should be handled locally or delegated\n- assigning disjoint worker scopes in large repositories, monorepos, or dirty worktrees\n- keeping shared contracts, package exports, sequencing, and destructive migration boundaries under parent-agent ownership\n- synthesizing explorer, implementation, review, or verification results without duplicating work\n- preserving parent-agent ownership of final integration, validation, and user-facing status\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/multitask-coordinator/SKILL.md`](./skills/multitask-coordinator/SKILL.md)\n- Optional runtime metadata: [`skills/multitask-coordinator/agents/openai.yaml`](./skills/multitask-coordinator/agents/openai.yaml)\n\n### `debug`\n\n[`skills/debug/`](./skills/debug/) provides evidence-first runtime debugging for application bugs, regressions, flaky behavior, and unclear runtime failures. It is the most operational skill in the repository and includes both workflow guidance and a local log collector.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill debug\n```\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/debug/SKILL.md`](./skills/debug/SKILL.md)\n- Operator reference: [`skills/debug/references/runtime-debugging.md`](./skills/debug/references/runtime-debugging.md)\n- Local NDJSON collector: [`skills/debug/scripts/local_log_collector/`](./skills/debug/scripts/local_log_collector/)\n- Optional runtime metadata: [`skills/debug/agents/openai.yaml`](./skills/debug/agents/openai.yaml)\n\n### `debug` Skill Snapshot\n\nThe `debug` skill is designed to prevent speculative fixes by forcing a prove-it loop:\n\n1. Generate precise hypotheses.\n2. Attach to or start an authoritative logging session.\n3. Add minimal temporary instrumentation.\n4. Reproduce the issue and read the recorded log file.\n5. Mark each hypothesis as `CONFIRMED`, `REJECTED`, or `INCONCLUSIVE`.\n6. Apply a fix only after the root cause is proven.\n7. Verify with fresh post-fix logs before removing instrumentation.\n\nThis keeps the skill focused on evidence, not guesswork.\n\n### `debug` Architecture\n\n```mermaid\nflowchart LR\n  User[\"Developer / Operator\"] --\u003e Agent[\"Agent Runtime\"]\n  Agent --\u003e Skill[\"debug/SKILL.md\u003cbr/\u003eworkflow + guardrails\"]\n  Agent --\u003e Ref[\"runtime-debugging.md\u003cbr/\u003ebootstrap + log format\"]\n  Agent --\u003e App[\"Target app under debug\"]\n  Agent --\u003e Logs[\"Temporary instrumentation\"]\n  Logs --\u003e Collector[\"Local NDJSON collector\u003cbr/\u003esame-origin dashboard + APIs\"]\n  App --\u003e Logs\n  Collector --\u003e File[\"Session log file\"]\n  Collector --\u003e UI[\"Live dashboard\"]\n  File --\u003e Agent\n  UI --\u003e Agent\n  Agent --\u003e Fix[\"Proven fix + post-fix verification\"]\n```\n\n### `debug` Highlights\n\n- Evidence-first debugging instead of inspection-only reasoning\n- Minimal instrumentation with explicit cleanup after verification\n- Per-hypothesis logging and before/after comparison\n- Local collector bootstrap when the host does not already provide logging\n- Browser-first log transport for frontend debugging, with explicit prohibition on app-local proxy routes unless direct delivery is proven blocked\n\n### `debug` Runtime Support\n\nThe current `debug` skill is intentionally portable. It works with:\n\n- OpenAI Codex and similar local-skill runtimes\n- Agent shells that read `~/.agents/skills/\u003cname\u003e/SKILL.md`\n- Custom agent frameworks that mount a skill folder and inject `SKILL.md` into context\n- Internal toolchains that want the collector, references, or workflow as reusable assets\n\nIf your runtime ignores [`skills/debug/agents/openai.yaml`](./skills/debug/agents/openai.yaml), the core logic is still fully available through [`skills/debug/SKILL.md`](./skills/debug/SKILL.md).\n\n### `debug` Dashboard Preview\n\n![Runtime Debug dashboard preview](./docs/images/dashboard-overview.png)\n\n### `debug` Collector\n\nThe bundled collector is a zero-dependency Python app built on the standard library. It accepts JSON log events, appends them to an NDJSON file, and serves a same-origin dashboard for live inspection.\n\nFor frontend and browser debugging, the intended transport is direct client-to-collector HTTP posting. The collector already handles CORS and preflight, so the skill should not create temporary Next.js API routes or other app-local proxy layers unless direct browser delivery has been proven blocked in the current host.\n\nCollector endpoints:\n\n- `POST /ingest`\n- `GET /health`\n- `GET /api/state`\n- `GET /api/logs`\n- `GET /api/logs/detail`\n- `POST /api/clear`\n- `POST /api/shutdown`\n\nMinimal smoke test:\n\n```bash\nmkdir -p .debug-logs\npython3 skills/debug/scripts/local_log_collector/main.py \\\n  --log-file \"$PWD/.debug-logs/demo.ndjson\" \\\n  --ready-file \"$PWD/.debug-logs/demo.json\" \\\n  --session-id \"demo-session\"\n```\n\n### `hack-review`\n\n[`skills/hack-review/`](./skills/hack-review/) reviews whether an implementation is relying on hack-like tactics instead of sound ownership and abstraction boundaries. It produces a coverage-led reviewer report that enumerates all distinct hack-risk findings discovered within scope, records intentional exceptions, and marks uncovered ownership boundaries explicitly.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill hack-review\n```\n\nBest for:\n\n- identifying impossible-state fallbacks that hide a broken invariant\n- flagging symptom-masking patches that do not fix the root cause\n- catching duplicate abstractions or parallel wheels when a stable boundary already exists\n- showing which touched ownership boundaries were reviewed, skipped, or left uncovered\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/hack-review/SKILL.md`](./skills/hack-review/SKILL.md)\n- Report template: [`skills/hack-review/references/report-template.md`](./skills/hack-review/references/report-template.md)\n- Optional runtime metadata: [`skills/hack-review/agents/openai.yaml`](./skills/hack-review/agents/openai.yaml)\n\n### `receiving-hack-review`\n\n[`skills/receiving-hack-review/`](./skills/receiving-hack-review/) consumes a `hack-review` report and builds a disposition ledger for every finding, intentional exception, and open ownership coverage gap before deciding whether to fix, challenge, confirm, or carry it forward.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill receiving-hack-review\n```\n\nBest for:\n\n- re-checking that a hack report matches the exact requested review scope\n- fixing ownership problems without mechanically deleting necessary guards\n- narrowing or disproving hack findings with stronger code-path evidence\n- closing or explicitly carrying forward `Not covered` ownership boundaries from the coverage ledger\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/receiving-hack-review/SKILL.md`](./skills/receiving-hack-review/SKILL.md)\n- Optional runtime metadata: [`skills/receiving-hack-review/agents/openai.yaml`](./skills/receiving-hack-review/agents/openai.yaml)\n\n### `regression-review`\n\n[`skills/regression-review/`](./skills/regression-review/) reviews whether the current change set introduces user-visible behavioral regressions. It writes a coverage-led reviewer report that enumerates all distinct findings discovered within scope, records intentional visible changes, and marks uncovered surfaces explicitly.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill regression-review\n```\n\nBest for:\n\n- checking whether a refactor or feature work breaks user-facing flows\n- auditing changed defaults, loading states, retries, ordering, or exported output\n- writing a review artifact that keeps severity aligned with the strongest unresolved finding while showing full reviewed coverage\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/regression-review/SKILL.md`](./skills/regression-review/SKILL.md)\n- Report template: [`skills/regression-review/references/report-template.md`](./skills/regression-review/references/report-template.md)\n- Optional runtime metadata: [`skills/regression-review/agents/openai.yaml`](./skills/regression-review/agents/openai.yaml)\n\n### `receiving-regression-review`\n\n[`skills/receiving-regression-review/`](./skills/receiving-regression-review/) consumes a `regression-review` report and builds a disposition ledger for every finding, intentional visible change, and open coverage gap before deciding whether to fix, challenge, confirm, or carry it forward.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill receiving-regression-review\n```\n\nBest for:\n\n- re-checking a regression gate against the current diff and baseline\n- fixing only proven user-visible regressions instead of blindly following review comments\n- separating real regressions from intentional product deltas with stronger evidence\n- closing or explicitly carrying forward `Not covered` user-visible surfaces from the coverage ledger\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/receiving-regression-review/SKILL.md`](./skills/receiving-regression-review/SKILL.md)\n- Optional runtime metadata: [`skills/receiving-regression-review/agents/openai.yaml`](./skills/receiving-regression-review/agents/openai.yaml)\n\n### `react-wide-api-review`\n\n[`skills/react-wide-api-review/`](./skills/react-wide-api-review/) performs a scoped, coverage-led audit of oversized React and TypeScript API surfaces. It traces field flow through component props, hooks, contexts, form controllers, table configs, view models, and pass-through chains, then writes a Markdown gate report with findings, intentional exceptions, and coverage ledgers.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill react-wide-api-review\n```\n\nBest for:\n\n- finding component props, hook returns, context values, or controller objects that are too wide for their consumers\n- tracing pass-through and spread propagation before recommending a narrower owner\n- producing an AST-first review report with field-flow and recursive coverage ledgers\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/react-wide-api-review/SKILL.md`](./skills/react-wide-api-review/SKILL.md)\n- Report template: [`skills/react-wide-api-review/references/report-template.md`](./skills/react-wide-api-review/references/report-template.md)\n- Inventory helper: [`skills/react-wide-api-review/scripts/react_wide_api_inventory.py`](./skills/react-wide-api-review/scripts/react_wide_api_inventory.py)\n- Trace helper: [`skills/react-wide-api-review/scripts/react_wide_api_trace.py`](./skills/react-wide-api-review/scripts/react_wide_api_trace.py)\n- Optional runtime metadata: [`skills/react-wide-api-review/agents/openai.yaml`](./skills/react-wide-api-review/agents/openai.yaml)\n\n### `receiving-react-wide-api-review`\n\n[`skills/receiving-react-wide-api-review/`](./skills/receiving-react-wide-api-review/) consumes a `react-wide-api-review` report or equivalent PR feedback. It builds a disposition ledger for every finding, intentional exception, field-flow row, and open coverage row before fixing, disproving, narrowing, confirming, or carrying items forward with evidence.\n\nInstall:\n\n```bash\nnpx skills@latest add JUNERDD/skills --skill receiving-react-wide-api-review\n```\n\nBest for:\n\n- verifying whether each wide React API finding still applies to the current code\n- fixing field ownership, subscription, context, hook return, or pass-through issues without broad rewrites\n- preserving Git staging state while reporting a complete disposition for every consumed item\n\nKey entry points:\n\n- Workflow and guardrails: [`skills/receiving-react-wide-api-review/SKILL.md`](./skills/receiving-react-wide-api-review/SKILL.md)\n- Disposition template: [`skills/receiving-react-wide-api-review/references/disposition-template.md`](./skills/receiving-react-wide-api-review/references/disposition-template.md)\n- Report intake helper: [`skills/receiving-react-wide-api-review/scripts/extract_react_wide_api_report_items.py`](./skills/receiving-react-wide-api-review/scripts/extract_react_wide_api_report_items.py)\n- Optional runtime metadata: [`skills/receiving-react-wide-api-review/agents/openai.yaml`](./skills/receiving-react-wide-api-review/agents/openai.yaml)\n\n## 🌱 Growing The Repository\n\nWhen you add more skills later:\n\n- Create a new folder under `skills/\u003cskill-name\u003e/`.\n- Keep each skill self-contained so it can be installed independently.\n- Add or update `agents/`, `references/`, `scripts/`, and `assets/` only when they materially help that specific skill.\n- Update the `Current Skills` section in this README with a one-line summary and relevant links.\n- Keep repo-level README content about the collection itself; move deep procedural detail into the skill that owns it.\n\n## 🏗️ Repository Layout\n\n```text\n.\n├── LICENSE\n├── README.md\n├── docs/\n│   └── images/\n│       └── dashboard-overview.png\n└── skills/\n    ├── comment-strategist/\n    │   ├── SKILL.md\n    │   └── agents/\n    │       └── openai.yaml\n    ├── debug/\n    │   ├── SKILL.md\n    │   ├── agents/\n    │   │   └── openai.yaml\n    │   ├── references/\n    │   │   └── runtime-debugging.md\n    │   └── scripts/\n    │       └── local_log_collector/\n    │           ├── main.py\n    │           ├── collector_server.py\n    │           ├── collector_state.py\n    │           ├── collector_browser.py\n    │           └── static/\n    ├── exhaustive-code-slimmer/\n    │   ├── SKILL.md\n    │   ├── agents/\n    │   │   └── openai.yaml\n    │   ├── references/\n    │   │   ├── ast_first_candidate_generation.md\n    │   │   ├── code_cleanliness_guide.md\n    │   │   ├── dx_architecture_gate.md\n    │   │   ├── language_tactics.md\n    │   │   ├── oracle_design.md\n    │   │   ├── research_basis.md\n    │   │   └── transformation_catalog.md\n    │   └── scripts/\n    │       ├── architecture_dx_scan.py\n    │       ├── code_slim_audit.py\n    │       └── exhaustive_shrink.py\n    ├── git-commit/\n    │   ├── SKILL.md\n    │   └── agents/\n    │       └── openai.yaml\n    ├── hack-review/\n    │   ├── SKILL.md\n    │   ├── agents/\n    │   │   └── openai.yaml\n    │   └── references/\n    │       └── report-template.md\n    ├── multitask-coordinator/\n    │   ├── SKILL.md\n    │   └── agents/\n    │       └── openai.yaml\n    ├── receiving-hack-review/\n    │   ├── SKILL.md\n    │   └── agents/\n    │       └── openai.yaml\n    ├── receiving-react-wide-api-review/\n    │   ├── SKILL.md\n    │   ├── agents/\n    │   │   └── openai.yaml\n    │   ├── references/\n    │   │   ├── ast-verification.md\n    │   │   ├── disposition-template.md\n    │   │   ├── fix-patterns.md\n    │   │   ├── report-intake.md\n    │   │   └── verification.md\n    │   └── scripts/\n    │       └── extract_react_wide_api_report_items.py\n    ├── receiving-regression-review/\n    │   ├── SKILL.md\n    │   └── agents/\n    │       └── openai.yaml\n    ├── react-wide-api-review/\n    │   ├── SKILL.md\n    │   ├── agents/\n    │   │   └── openai.yaml\n    │   ├── references/\n    │   │   ├── ast-first-analysis.md\n    │   │   ├── checklist.md\n    │   │   ├── field-flow-taxonomy.md\n    │   │   ├── migration.md\n    │   │   ├── patterns.md\n    │   │   ├── recursive-audit.md\n    │   │   ├── report-template.md\n    │   │   └── scoring-model.md\n    │   └── scripts/\n    │       ├── react_wide_api_inventory.py\n    │       └── react_wide_api_trace.py\n    ├── regression-review/\n    │   ├── SKILL.md\n    │   ├── agents/\n    │   │   └── openai.yaml\n    │   └── references/\n    │       └── report-template.md\n    └── split-commits/\n        ├── SKILL.md\n        └── agents/\n            └── openai.yaml\n```\n\n## ⚖️ License\n\nReleased under the [MIT License](./LICENSE).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjunerdd%2Fskills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjunerdd%2Fskills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjunerdd%2Fskills/lists"}