[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M74HG4XTYW219YCW322EPKM2":3,"skill-same:01M74HG4XTYW219YCW322EPKM2":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":44},"01M74HG4XTYW219YCW322EPKM2","onboard",null,"Use when the user explicitly invokes \u002Fonboard or asks to \"give me a tour of this codebase\" \u002F \"I'm new here, where do I start?\" \u002F \"summarize this project for me.\" Performs a structured codebase tour, infers conventions from the existing files, and proposes a CLAUDE.md (or updates an existing one) so subsequent sessions have working context.","drumfiend21\u002Fclaude-tdd-pro","drumfiend21","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F10619389?v=4","01M74HCNYY9VCB2B7FNCSPQSZN","Siddharth Joshi","01M74HCNZHQP883HA9WSN1G6TR",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro\u002Fblob\u002Fmain\u002Fskills\u002Fonboard\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: onboard\ndescription: Use when the user explicitly invokes \u002Fonboard or asks to \"give me a tour of this codebase\" \u002F \"I'm new here, where do I start?\" \u002F \"summarize this project for me.\" Performs a structured codebase tour, infers conventions from the existing files, and proposes a CLAUDE.md (or updates an existing one) so subsequent sessions have working context.\ndisable-model-invocation: true\n---\n\n# Onboard\n\nYou are giving a new contributor (human or future-Claude session) a\nstructured tour of an unfamiliar codebase. The output is both a\ntour-narrative and an artifact (CLAUDE.md) future sessions can read.\n\n## Process\n\n### 1. Survey the layout\n\n```bash\n# Top-level shape\nls -la\n# Detect monorepo \u002F multi-project\nfind . -name \"package.json\" -not -path \"*\u002Fnode_modules\u002F*\" | head -20\nfind . -name \"pyproject.toml\" -not -path \"*\u002F.venv\u002F*\" | head -10\nfind . -name \"Cargo.toml\" -not -path \"*\u002Ftarget\u002F*\" | head\nfind . -name \"go.mod\" | head\n# Existing docs\nls README* CLAUDE.md AGENTS.md CONVENTIONS.md adr\u002F 2>\u002Fdev\u002Fnull\n```\n\n### 2. Identify the stack\n\nPer project (or per sub-project in a monorepo):\n- Language(s) and version (from `engines` \u002F `python_requires` \u002F etc.)\n- Framework (React, Express, FastAPI, Rails, etc.)\n- Test runner\n- Lint\u002Fformat tools\n- Build system\n\n### 3. Find the \"story shape\"\n\nWhat does this code DO at a one-paragraph level? Read:\n- The top of the main README.\n- The 2-3 most recent merged PR descriptions (`git log --oneline -20`).\n- The largest source file (often a hint at where complexity lives).\n\n### 4. Detect conventions\n\nWithout writing anything yet, infer:\n- Naming conventions in use (camelCase \u002F snake_case).\n- Test file location convention (sibling vs `__tests__\u002F` mirror).\n- Error-handling style (exceptions \u002F Result-types \u002F nulls).\n- Comment style (sparse \u002F heavy JSDoc \u002F docstrings).\n- Anti-patterns the codebase already avoids or doesn't.\n\n### 5. Surface what's missing\n\n- Is there a `CLAUDE.md`? If not, propose one.\n- Is there a `CONVENTIONS.md`? If not, suggest scaffolding from the\n  plugin's template.\n- Is there a `REMEDIATION.md`? If not, propose surveying for known\n  bugs \u002F hot files.\n- Is the lint\u002Ftest setup detectable? If not, suggest `\u002Finit-guardrails`.\n\n### 6. Write the tour\n\nShow the user a structured tour:\n\n```markdown\n# Codebase tour: \u003Cproject name>\n\n## What this is\n\n[One paragraph from the survey.]\n\n## Layout\n\n[Tree-style; just the meaningful directories.]\n\n## Stack\n\n| Layer | Tech |\n|---|---|\n| Frontend | ... |\n| Backend | ... |\n| Database | ... |\n| Tests | ... |\n\n## How to run\n\n[The 3-5 commands a new contributor needs.]\n\n## Where the complexity lives\n\nThe 2-3 files \u002F modules new contributors should read first. Any\nknown fragile zones.\n\n## Conventions in use\n\n[Short list inferred from grep + sample reading.]\n\n## What's missing (suggested next steps)\n\n- [ ] CLAUDE.md (would help future Claude sessions)\n- [ ] CONVENTIONS.md (suggested scaffold via \u002Fsync-rules later)\n- [ ] CI workflow\n- [ ] REMEDIATION.md (if known bugs)\n```\n\n### 7. Offer to commit the artifact\n\nIf the user wants the tour persisted, save as `CLAUDE.md` (or\n`CLAUDE.md` + `docs\u002Fcodebase-tour.md` if a CLAUDE.md exists). Do NOT\noverwrite an existing CLAUDE.md without asking.\n\n## Constraints\n\n- **Read-only survey**. Do not edit, install, or build during onboard.\n- **One pass**. If the user asks \"tell me more about X,\" that's a\n  follow-up question, not another full tour.\n- **Don't fabricate**. If you can't tell what a directory is for from\n  reading, say \"(unclear from contents — ask the team)\".\n- **Time-box**: 5-10 file reads should be enough. Reading every file\n  is the wrong shape.\n","# Onboard\n\nYou are giving a new contributor (human or future-Claude session) a\nstructured tour of an unfamiliar codebase. The output is both a\ntour-narrative and an artifact (CLAUDE.md) future sessions can read.\n\n## Process\n\n### 1. Survey the layout\n\n```bash\n# Top-level shape\nls -la\n# Detect monorepo \u002F multi-project\nfind . -name \"package.json\" -not -path \"*\u002Fnode_modules\u002F*\" | head -20\nfind . -name \"pyproject.toml\" -not -path \"*\u002F.venv\u002F*\" | head -10\nfind . -name \"Cargo.toml\" -not -path \"*\u002Ftarget\u002F*\" | head\nfind . -name \"go.mod\" | head\n# Existing docs\nls README* CLAUDE.md AGENTS.md CONVENTIONS.md adr\u002F 2>\u002Fdev\u002Fnull\n```\n\n### 2. Identify the stack\n\nPer project (or per sub-project in a monorepo):\n- Language(s) and version (from `engines` \u002F `python_requires` \u002F etc.)\n- Framework (React, Express, FastAPI, Rails, etc.)\n- Test runner\n- Lint\u002Fformat tools\n- Build system\n\n### 3. Find the \"story shape\"\n\nWhat does this code DO at a one-paragraph level? Read:\n- The top of the main README.\n- The 2-3 most recent merged PR descriptions (`git log --oneline -20`).\n- The largest source file (often a hint at where complexity lives).\n\n### 4. Detect conventions\n\nWithout writing anything yet, infer:\n- Naming conventions in use (camelCase \u002F snake_case).\n- Test file location convention (sibling vs `__tests__\u002F` mirror).\n- Error-handling style (exceptions \u002F Result-types \u002F nulls).\n- Comment style (sparse \u002F heavy JSDoc \u002F docstrings).\n- Anti-patterns the codebase already avoids or doesn't.\n\n### 5. Surface what's missing\n\n- Is there a `CLAUDE.md`? If not, propose one.\n- Is there a `CONVENTIONS.md`? If not, suggest scaffolding from the\n  plugin's template.\n- Is there a `REMEDIATION.md`? If not, propose surveying for known\n  bugs \u002F hot files.\n- Is the lint\u002Ftest setup detectable? If not, suggest `\u002Finit-guardrails`.\n\n### 6. Write the tour\n\nShow the user a structured tour:\n\n```markdown\n# Codebase tour: \u003Cproject name>\n\n## What this is\n\n[One paragraph from the survey.]\n\n## Layout\n\n[Tree-style; just the meaningful directories.]\n\n## Stack\n\n| Layer | Tech |\n|---|---|\n| Frontend | ... |\n| Backend | ... |\n| Database | ... |\n| Tests | ... |\n\n## How to run\n\n[The 3-5 commands a new contributor needs.]\n\n## Where the complexity lives\n\nThe 2-3 files \u002F modules new contributors should read first. Any\nknown fragile zones.\n\n## Conventions in use\n\n[Short list inferred from grep + sample reading.]\n\n## What's missing (suggested next steps)\n\n- [ ] CLAUDE.md (would help future Claude sessions)\n- [ ] CONVENTIONS.md (suggested scaffold via \u002Fsync-rules later)\n- [ ] CI workflow\n- [ ] REMEDIATION.md (if known bugs)\n```\n\n### 7. Offer to commit the artifact\n\nIf the user wants the tour persisted, save as `CLAUDE.md` (or\n`CLAUDE.md` + `docs\u002Fcodebase-tour.md` if a CLAUDE.md exists). Do NOT\noverwrite an existing CLAUDE.md without asking.\n\n## Constraints\n\n- **Read-only survey**. Do not edit, install, or build during onboard.\n- **One pass**. If the user asks \"tell me more about X,\" that's a\n  follow-up question, not another full tour.\n- **Don't fabricate**. If you can't tell what a directory is for from\n  reading, say \"(unclear from contents — ask the team)\".\n- **Time-box**: 5-10 file reads should be enough. Reading every file\n  is the wrong shape.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","41c38db9b8cf2d5b7743093654a12fdd9cd59c03","skills\u002Fonboard","https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro","https:\u002F\u002Fgithub.com\u002Fdrumfiend21","http:\u002F\u002Fjungleej.wordpress.com","2026-11-09 20:29:03",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":24},[34,37,40],{"tool":35,"command":36},"npx","npx skills add drumfiend21\u002Fclaude-tdd-pro --skill onboard",{"tool":38,"command":39},"bunx","bunx skills add drumfiend21\u002Fclaude-tdd-pro --skill onboard",{"tool":41,"command":42},"pnpm","pnpm dlx skills add drumfiend21\u002Fclaude-tdd-pro --skill onboard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro\u002Fblob\u002Fmain\u002Fskills\u002Fonboard\u002FSKILL.md",[],[46,53,60,67,74,80],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M74HHPZCJM1SJFPMAT28GZ1S","test-first-extract","Use when the user asks to EXTRACT or RELOCATE existing code into its own file, module, or component (\"extract X\", \"split out Y\", \"pull Z into its own file\", \"decompose god-file\"). NOT for net-new features (use tdd-feature-build) or behavior changes (use fix-bug). Enforces the 9-step extraction with isolated unit tests + integration regression tests as a two-tier safety net.","https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro\u002Fblob\u002Fmain\u002Fskills\u002Ftest-first-extract\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M74HHK1QJ5APDRM7WWMC90X9","tdd-feature-build","Use when the user describes a NEW feature to add (\"add X to Y\", \"implement Z\", \"build a feature that…\", \"make it possible to…\"). Enforces TDD — failing test first, minimum code to pass, refactor. Refuses to ship code without a test that demonstrably catches its absence. Does NOT trigger on bug fixes (use bug-fix-discipline) or refactors (use test-first-extract). Will ask 1-3 clarifying questions before writing any code; safe to delegate from \u002Ffeature command.","https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro\u002Fblob\u002Fmain\u002Fskills\u002Ftdd-feature-build\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M74HHEXN1MK9SK9JDGN52YDJ","sync","Multi-machine git-backed sync of local TDD Pro state via the `tdd-pro-sync` branch. Use when operators run claude-tdd-pro on more than one machine and want their FAILURE-LOG, decisions, audit checkpoints, workflow state, operator-curated URL registries, operator\u002Fcommunity trees, and paywalled attestations to follow them between hosts.","https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro\u002Fblob\u002Fmain\u002Fskills\u002Fsync\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M74HHBQ8K1FNZ5AXTEGGF8RW","strict-component-tests","Use when writing or reviewing test files. Enforces strict assertions that actually catch regressions (getByRole, exact counts, jest-dom matchers) in contrast to permissive tests (queryAllByText length > 0) that pass against broken UIs. References QUALITY-BAR.md for the canonical strictness rules.","https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro\u002Fblob\u002Fmain\u002Fskills\u002Fstrict-component-tests\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M74HHA5W00JK570KTA68MRZD","spec","https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro\u002Fblob\u002Fmain\u002Fskills\u002Fspec\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M74HH5HR9S2Q6HRAW0GTXATA","spec-first","Use when the user describes a non-trivial feature or system that should be specified in writing before any code is written. Pattern from Geoffrey Huntley's \"Ralph\" loop, OpenSpec, intent-driven.dev, and Kent Beck's \"augmented coding\" framing — specs+tests are the durable artifact, code is the disposable one. Produces a Markdown spec document that the user reviews; only after approval does any code get written (typically via tdd-feature-build or \u002Ffeature).","https:\u002F\u002Fgithub.com\u002Fdrumfiend21\u002Fclaude-tdd-pro\u002Fblob\u002Fmain\u002Fskills\u002Fspec-first\u002FSKILL.md",[],[]]