[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72TRTFRJQMSBV761SY6PA7E":3,"skill-same:01M72TRTFRJQMSBV761SY6PA7E":44},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M72TRTFRJQMSBV761SY6PA7E","ws-init",null,"Bootstrap or re-scope a project -- capture intent, seed first specs, bridge to strategy.","vempio\u002FWhittleSpec","vempio","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F226084226?v=4","01M72TQW11B57V5ZE8MQPKJ5QY","01M72TQW22F5C4SJ317ETCWHFW",4,"MIT","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.init\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: ws-init\ndescription: Bootstrap or re-scope a project -- capture intent, seed first specs, bridge to strategy.\n---\n# ws.init\n\nLoad shared context: `ws._meta\u002FSKILL.md` — the sibling skill in the same skills directory this skill loaded from (resolves under any clone name, install location, or skills-root override). Also load: `ws._meta\u002Fshaping.md`, `ws._meta\u002Flifecycle.md`.\n\n## Purpose\n\nCapture project-level intent, set up governance proportional to weight, create spec seeds for first features. Sits *before* SDD feature pipeline (`\u002Fws.0-start` -> `\u002Fws.1-requirements` -> ...). Also handles re-scoping when direction changes significantly.\n\n**Stratum**: Operates at **project level**. SDD strata: **Project** (`\u002Fws.init`) -- why project exists, scope, tier, governance, which features. **Feature** (`\u002Fws.0-start` through `\u002Fws.9-retro`) -- what feature does, how built.\n\nws.init bridges: PROJECT_INTENT.md (project context) + spec seeds (feature starting points) -> hands off to `\u002Fws.0-start`.\n\n## When to Use\n\nNew project \u002F significant scope change \u002F graduating experiment to operational \u002F formalizing organic project.\n\n## Process\n\n### 1. Detect Context\n\nCheck working directory: `.git\u002F`, `CLAUDE.md`\u002F`AGENTS.md` (read-only -- existence and content, never written here), `PROJECT_PRINCIPLES.md`, `PROJECT_INTENT.md`, `specs\u002F` (+ `seed.md`), `Makefile`, `pyproject.toml`, `package.json`.\n\n**New project**: No intent doc, minimal governance. **Re-scope**: Intent doc exists or significant structure present (see Re-Scope Mode). State which.\n\n### 2. Elicit Intent\n\nFor new projects, ask: **Problem** (\"What problem, for whom?\") \u002F **Approach** (\"How solve it?\") \u002F **Success** (\"Observable outcomes?\") \u002F **Boundaries** (\"Explicitly NOT?\")\n\n**Challenge intent** before accepting -- cheapest place to kill bad ideas.\n\n#### Value Challenge\n\n- **\"Who has this problem today, and how?\"** Nobody \u002F adequate solution -> maybe not worth starting.\n- **\"What if we don't build this?\"** Probe: must-have vs nice-to-have \u002F time criticality \u002F risk reduction \u002F learning value (changes decision, or just curiosity?) \u002F maintenance burden (existing tool handles 80%?)\n- **\"Could existing tool handle this?\"** Build-vs-buy. Spreadsheet\u002Fscript\u002Fexisting CLI might suffice.\n- **\"Problem you have, or solution you want to build?\"** Engineers gravitate toward interesting tech. \"Build clip pipeline\" might need reframing as \"produce clips with less friction.\"\n\nPush back if answers vague \u002F problem hypothetical \u002F approach over-engineered.\n\n#### Capacity Competition Check\n\nStarting new work always costs attention on work already in flight -- weigh that trade-off consciously before committing. Whether you scan a portfolio or just ask \"what else is on your plate right now?\", the question is the same, and it holds even when there is nothing to scan.\n\n\u003C!-- WS:EXAMPLE portfolio-scan -->\nWhere a portfolio surface exists, make the competition concrete by scanning it: the tracker's active epics\u002Fissues, sibling project dirs with a `PROJECT_INTENT.md` (status != complete), your planning\u002Froadmap doc for commitments. Absent that infrastructure, ask the operator directly instead -- the trade-off still stands, unscanned.\n\u003C!-- \u002FWS -->\n\n1. **Present**: \"N active projects: [list]. Starting [new] means one gets less attention. Which absorbs hit, or replaces one?\"\n2. **Reaction**: \"Genuinely urgent\" -> proceed. \"You're right\" -> shiny-thing caught, capture as seed, return to current work. \"Just small experiment\" -> exploratory tier, minimal governance, set timebox. \"Replaces Y\" -> re-scope, archive Y.\n\nNot a gate. User may have good reasons despite full plate. Overloaded + low time-criticality -> say so.\n\nFor re-scope: \"What triggered change?\" \u002F \"What stays vs differs?\" \u002F \"Specs need revisiting?\" \u002F **\"Genuine scope change, or scope creep wearing hat?\"**\n\n### 3. Assess Tier\n\nDefault to the lowest defensible amount of ceremony; more weight earns more structure, never the reverse. Manufacturing governance a project's weight doesn't warrant is the failure, not the safeguard.\n\n\u003C!-- WS:DEFAULT tiers -->\nA recommended weight scheme -- replace the bands if your context wants different ones:\n\n| Tier | Signals | Examples |\n|------|---------|----------|\n| **Exploratory** | Experiment, PoC, learning, time-limited | LLM comparison, tooling spike, prototype |\n| **Operational** | Ongoing tool\u002Fservice with real users | Internal CLI, training material, client project |\n| **Strategic** | Tied to a strategy\u002Fplanning initiative or business priority | Product launch, revenue stream, partnership |\n\nNot permanent. State graduation criteria: \"Graduates to operational if [condition].\"\n\n**Challenge tier.** \"Strategic\" without an initiative doc or revenue link -> push back. Re-scope: check if tier changed.\n\u003C!-- \u002FWS -->\n\n### 4. Strategy Linkage\n\nStrategic-weight work should trace to a higher purpose; most work should not be forced to. Not every project needs an initiative -- pushing one onto exploratory work is inflation, not rigor.\n\n\u003C!-- WS:EXAMPLE strategy-linkage -->\nWhere a strategy\u002Fplanning area exists: **Exploratory**: No link needed. **Operational**: check your strategy\u002Fplanning docs; note the connection if one exists. **Strategic**: an initiative doc (in that area) is required -- exists -> cross-reference; missing -> \"Needs initiative doc before tracker epics.\"\n\u003C!-- \u002FWS -->\n\n### 5. Work-ledger Posture\n\nResolve the work ledger (`ws-binding get work-ledger`; see `ws._meta\u002FSKILL.md` § Work-ledger binding). `local` → track in the SDD spec\u002Ftask files (or PROJECT_INTENT.md while exploratory); no external issues. When a tracker is bound, at the org's granularity:\n\n**Exploratory**: No tracker issue. Track in PROJECT_INTENT.md. Create if\u002Fwhen graduating. **Operational**: Epic when first feature concrete enough for `\u002Fws.1-requirements`. Until then, an issue under an existing epic if anchor needed. **Strategic**: Epic linked to initiative. Create after `\u002Fws.0-start` or now if scope clear.\n\n### 6. Set Up Governance\n\nProportional to tier. **All tiers**: PROJECT_INTENT.md (core output) -- WhittleSpec's own structure, never the adopter's `CLAUDE.md`\u002F`AGENTS.md` (INV-2: the only sanctioned write into those is `ws-binding anchor`'s pointer line, added later during `\u002Fws.0-start` setup, never here). **Operational+Strategic**: `specs\u002F` directory \u002F PROJECT_PRINCIPLES.md (only if non-obvious constraints). **Strategic only**: Cross-reference to\u002Ffrom initiative doc. Don't generate empty boilerplate -- skip and note why. Don't generate a `Makefile` either -- that's the adopter's build tooling, not a WhittleSpec artefact.\n\n### 7. Create Spec Seeds\n\n**Challenge before seeding**: \"Serves stated problem or adjacent?\" \u002F \"If only one feature, this one?\" \u002F \"Feature user needs or capability builder finds interesting?\" \u002F \"Cheapest way to test if it matters?\"\n\nSurvivors get seed at `specs\u002F\u003Cfeature>\u002Fseed.md`. Seeds bridge intent and pipeline -- enough to resume without context loss. NOT requirements (no Given\u002FWhen\u002FThen), NOT plans (no architecture).\n\n#### Seed Content\n\nSections appear when applicable -- don't force empty: **Problem\u002FDiscovery** (why needed, what gap) \u002F **Present Understanding** (known approach, prior research, spike results) \u002F **Open Questions** (what we don't know; often determines spike vs `\u002Fws.0-start`) \u002F **Dependencies** (relates to, builds on, blocks) \u002F **Recommended Next Step** (spike \u002F `\u002Fws.0-start` \u002F more research).\n\nOptional for mature seeds: Spike Definition \u002F Scale Considerations \u002F Related Research \u002F Resolved Questions \u002F Deferred ideas.\n\n```markdown\n# Spec Seed: [Feature Name]\n\nStatus: seed (not yet activated for SDD)\nCreated: [date]\nSource: [where idea came from]\n\n## Problem\n[Why needed]\n\n## Present Understanding\n[What we know]\n\n## Open Questions\n- [What we don't know]\n\n## Dependencies\n- [Relations]\n\n## Recommended Next Step\n[Spike \u002F `\u002Fws.0-start` \u002F needs research]\n```\n\n#### Seed Discipline\n\nDon't over-specify (reading like a `requirements.md` \u002F `umbrella-requirements.md` = crossed into `\u002Fws.1-requirements`). Don't under-specify (\"Build feature X\" = no value). Vary depth by knowledge. Seeds are cheap -- minutes to create, prevent context loss.\n\n### 8. Hand Off\n\n**New project** -> \"Run `\u002Fws.0-start` on first seed. Seeds at: [paths].\" \u002F **Re-scope** -> \"Run `\u002Fws.refine` on [affected features].\" \u002F **Graduation** -> \"Tier upgraded. [governance additions]. Run `\u002Fws.0-start`.\"\n\n## Output Structure\n\nWrite `PROJECT_INTENT.md` in project root:\n\n```markdown\n# Project: [Name]\n\n## Problem\n[1-3 sentences: what problem, for whom]\n\n## Approach\n[1-3 sentences: how addresses it]\n\n## Success Looks Like\n- [Observable outcome]\n\n## Boundaries\n- NOT: [exclusion]\n\n## Tier\n[Exploratory \u002F Operational \u002F Strategic]\n[Exploratory: \"Graduates if: [condition]\"]\n[Strategic: \"Initiative: \u003Cstrategy\u002Fplanning area>\u002F[name]\u002F\"]\n\n## Issue Tracker\n[Not yet \u002F Epic: PROJ-xxx]\n\n## Related Projects\n- [Project] -- [feeds into \u002F depends on \u002F overlaps \u002F replaces]\n\n## Spec Seeds\n| Feature | Seed | Status |\n|---------|------|--------|\n| [Name] | specs\u002F[name]\u002Fseed.md | seed |\n\n## Phases (operational\u002Fstrategic only)\n1. [Phase]: [goal]\n\n## History\n- [YYYY-MM-DD]: Created. [context]\n```\n\nHistory for major direction changes only. Spec Seeds table = living index -- update as seeds graduate.\n\n## Re-Scope Mode\n\n1. Read existing PROJECT_INTENT.md (or infer from the project's principles file and existing specs)\n2. Present: \"Current intent: [summary]. What's changing?\"\n3. Check existing seeds, note which affected\n4. Update PROJECT_INTENT.md -- append History, update sections\n5. Tier changed -> add governance proportionally (don't remove when downgrading)\n6. Create\u002Fupdate seeds as needed\n7. Scan affected specs\u002Ftasks: \"These may need revisiting: [list]\"\n8. Recommend: `\u002Fws.refine` for in-flight, `\u002Fws.0-start` for new seeds\n\n## Retro Feedback Loop\n\nFeature retros (`\u002Fws.9-retro`) may surface project-level impact. Minor -> edit directly. Significant (tier graduation, pivot) -> run `\u002Fws.init` re-scope. Relies on ws.9-retro to escalate.\n\n## Anti-Patterns\n\n**Over-governing** (strategic governance for experiment) \u002F **Premature tracking** (epics before first feature concrete) \u002F **Intent as requirements** (ACs in PROJECT_INTENT.md) \u002F **Seeds as requirements** (Given\u002FWhen\u002FThen in seeds) \u002F **Strategy inflation** (every project must link to initiative) \u002F **Skipping intent** (3-line doc prevents scope drift) \u002F **Scope creep into design** (architecture\u002FACs = crossed into `\u002Fws.1-requirements` \u002F `\u002Fws.2-plan`) \u002F **Skipping capacity check** (overcommit should be conscious) \u002F **Shiny-thing accommodation** (\"small experiment\" without timebox = permanent side project)\n","# ws.init\n\nLoad shared context: `ws._meta\u002FSKILL.md` — the sibling skill in the same skills directory this skill loaded from (resolves under any clone name, install location, or skills-root override). Also load: `ws._meta\u002Fshaping.md`, `ws._meta\u002Flifecycle.md`.\n\n## Purpose\n\nCapture project-level intent, set up governance proportional to weight, create spec seeds for first features. Sits *before* SDD feature pipeline (`\u002Fws.0-start` -> `\u002Fws.1-requirements` -> ...). Also handles re-scoping when direction changes significantly.\n\n**Stratum**: Operates at **project level**. SDD strata: **Project** (`\u002Fws.init`) -- why project exists, scope, tier, governance, which features. **Feature** (`\u002Fws.0-start` through `\u002Fws.9-retro`) -- what feature does, how built.\n\nws.init bridges: PROJECT_INTENT.md (project context) + spec seeds (feature starting points) -> hands off to `\u002Fws.0-start`.\n\n## When to Use\n\nNew project \u002F significant scope change \u002F graduating experiment to operational \u002F formalizing organic project.\n\n## Process\n\n### 1. Detect Context\n\nCheck working directory: `.git\u002F`, `CLAUDE.md`\u002F`AGENTS.md` (read-only -- existence and content, never written here), `PROJECT_PRINCIPLES.md`, `PROJECT_INTENT.md`, `specs\u002F` (+ `seed.md`), `Makefile`, `pyproject.toml`, `package.json`.\n\n**New project**: No intent doc, minimal governance. **Re-scope**: Intent doc exists or significant structure present (see Re-Scope Mode). State which.\n\n### 2. Elicit Intent\n\nFor new projects, ask: **Problem** (\"What problem, for whom?\") \u002F **Approach** (\"How solve it?\") \u002F **Success** (\"Observable outcomes?\") \u002F **Boundaries** (\"Explicitly NOT?\")\n\n**Challenge intent** before accepting -- cheapest place to kill bad ideas.\n\n#### Value Challenge\n\n- **\"Who has this problem today, and how?\"** Nobody \u002F adequate solution -> maybe not worth starting.\n- **\"What if we don't build this?\"** Probe: must-have vs nice-to-have \u002F time criticality \u002F risk reduction \u002F learning value (changes decision, or just curiosity?) \u002F maintenance burden (existing tool handles 80%?)\n- **\"Could existing tool handle this?\"** Build-vs-buy. Spreadsheet\u002Fscript\u002Fexisting CLI might suffice.\n- **\"Problem you have, or solution you want to build?\"** Engineers gravitate toward interesting tech. \"Build clip pipeline\" might need reframing as \"produce clips with less friction.\"\n\nPush back if answers vague \u002F problem hypothetical \u002F approach over-engineered.\n\n#### Capacity Competition Check\n\nStarting new work always costs attention on work already in flight -- weigh that trade-off consciously before committing. Whether you scan a portfolio or just ask \"what else is on your plate right now?\", the question is the same, and it holds even when there is nothing to scan.\n\n\u003C!-- WS:EXAMPLE portfolio-scan -->\nWhere a portfolio surface exists, make the competition concrete by scanning it: the tracker's active epics\u002Fissues, sibling project dirs with a `PROJECT_INTENT.md` (status != complete), your planning\u002Froadmap doc for commitments. Absent that infrastructure, ask the operator directly instead -- the trade-off still stands, unscanned.\n\u003C!-- \u002FWS -->\n\n1. **Present**: \"N active projects: [list]. Starting [new] means one gets less attention. Which absorbs hit, or replaces one?\"\n2. **Reaction**: \"Genuinely urgent\" -> proceed. \"You're right\" -> shiny-thing caught, capture as seed, return to current work. \"Just small experiment\" -> exploratory tier, minimal governance, set timebox. \"Replaces Y\" -> re-scope, archive Y.\n\nNot a gate. User may have good reasons despite full plate. Overloaded + low time-criticality -> say so.\n\nFor re-scope: \"What triggered change?\" \u002F \"What stays vs differs?\" \u002F \"Specs need revisiting?\" \u002F **\"Genuine scope change, or scope creep wearing hat?\"**\n\n### 3. Assess Tier\n\nDefault to the lowest defensible amount of ceremony; more weight earns more structure, never the reverse. Manufacturing governance a project's weight doesn't warrant is the failure, not the safeguard.\n\n\u003C!-- WS:DEFAULT tiers -->\nA recommended weight scheme -- replace the bands if your context wants different ones:\n\n| Tier | Signals | Examples |\n|------|---------|----------|\n| **Exploratory** | Experiment, PoC, learning, time-limited | LLM comparison, tooling spike, prototype |\n| **Operational** | Ongoing tool\u002Fservice with real users | Internal CLI, training material, client project |\n| **Strategic** | Tied to a strategy\u002Fplanning initiative or business priority | Product launch, revenue stream, partnership |\n\nNot permanent. State graduation criteria: \"Graduates to operational if [condition].\"\n\n**Challenge tier.** \"Strategic\" without an initiative doc or revenue link -> push back. Re-scope: check if tier changed.\n\u003C!-- \u002FWS -->\n\n### 4. Strategy Linkage\n\nStrategic-weight work should trace to a higher purpose; most work should not be forced to. Not every project needs an initiative -- pushing one onto exploratory work is inflation, not rigor.\n\n\u003C!-- WS:EXAMPLE strategy-linkage -->\nWhere a strategy\u002Fplanning area exists: **Exploratory**: No link needed. **Operational**: check your strategy\u002Fplanning docs; note the connection if one exists. **Strategic**: an initiative doc (in that area) is required -- exists -> cross-reference; missing -> \"Needs initiative doc before tracker epics.\"\n\u003C!-- \u002FWS -->\n\n### 5. Work-ledger Posture\n\nResolve the work ledger (`ws-binding get work-ledger`; see `ws._meta\u002FSKILL.md` § Work-ledger binding). `local` → track in the SDD spec\u002Ftask files (or PROJECT_INTENT.md while exploratory); no external issues. When a tracker is bound, at the org's granularity:\n\n**Exploratory**: No tracker issue. Track in PROJECT_INTENT.md. Create if\u002Fwhen graduating. **Operational**: Epic when first feature concrete enough for `\u002Fws.1-requirements`. Until then, an issue under an existing epic if anchor needed. **Strategic**: Epic linked to initiative. Create after `\u002Fws.0-start` or now if scope clear.\n\n### 6. Set Up Governance\n\nProportional to tier. **All tiers**: PROJECT_INTENT.md (core output) -- WhittleSpec's own structure, never the adopter's `CLAUDE.md`\u002F`AGENTS.md` (INV-2: the only sanctioned write into those is `ws-binding anchor`'s pointer line, added later during `\u002Fws.0-start` setup, never here). **Operational+Strategic**: `specs\u002F` directory \u002F PROJECT_PRINCIPLES.md (only if non-obvious constraints). **Strategic only**: Cross-reference to\u002Ffrom initiative doc. Don't generate empty boilerplate -- skip and note why. Don't generate a `Makefile` either -- that's the adopter's build tooling, not a WhittleSpec artefact.\n\n### 7. Create Spec Seeds\n\n**Challenge before seeding**: \"Serves stated problem or adjacent?\" \u002F \"If only one feature, this one?\" \u002F \"Feature user needs or capability builder finds interesting?\" \u002F \"Cheapest way to test if it matters?\"\n\nSurvivors get seed at `specs\u002F\u003Cfeature>\u002Fseed.md`. Seeds bridge intent and pipeline -- enough to resume without context loss. NOT requirements (no Given\u002FWhen\u002FThen), NOT plans (no architecture).\n\n#### Seed Content\n\nSections appear when applicable -- don't force empty: **Problem\u002FDiscovery** (why needed, what gap) \u002F **Present Understanding** (known approach, prior research, spike results) \u002F **Open Questions** (what we don't know; often determines spike vs `\u002Fws.0-start`) \u002F **Dependencies** (relates to, builds on, blocks) \u002F **Recommended Next Step** (spike \u002F `\u002Fws.0-start` \u002F more research).\n\nOptional for mature seeds: Spike Definition \u002F Scale Considerations \u002F Related Research \u002F Resolved Questions \u002F Deferred ideas.\n\n```markdown\n# Spec Seed: [Feature Name]\n\nStatus: seed (not yet activated for SDD)\nCreated: [date]\nSource: [where idea came from]\n\n## Problem\n[Why needed]\n\n## Present Understanding\n[What we know]\n\n## Open Questions\n- [What we don't know]\n\n## Dependencies\n- [Relations]\n\n## Recommended Next Step\n[Spike \u002F `\u002Fws.0-start` \u002F needs research]\n```\n\n#### Seed Discipline\n\nDon't over-specify (reading like a `requirements.md` \u002F `umbrella-requirements.md` = crossed into `\u002Fws.1-requirements`). Don't under-specify (\"Build feature X\" = no value). Vary depth by knowledge. Seeds are cheap -- minutes to create, prevent context loss.\n\n### 8. Hand Off\n\n**New project** -> \"Run `\u002Fws.0-start` on first seed. Seeds at: [paths].\" \u002F **Re-scope** -> \"Run `\u002Fws.refine` on [affected features].\" \u002F **Graduation** -> \"Tier upgraded. [governance additions]. Run `\u002Fws.0-start`.\"\n\n## Output Structure\n\nWrite `PROJECT_INTENT.md` in project root:\n\n```markdown\n# Project: [Name]\n\n## Problem\n[1-3 sentences: what problem, for whom]\n\n## Approach\n[1-3 sentences: how addresses it]\n\n## Success Looks Like\n- [Observable outcome]\n\n## Boundaries\n- NOT: [exclusion]\n\n## Tier\n[Exploratory \u002F Operational \u002F Strategic]\n[Exploratory: \"Graduates if: [condition]\"]\n[Strategic: \"Initiative: \u003Cstrategy\u002Fplanning area>\u002F[name]\u002F\"]\n\n## Issue Tracker\n[Not yet \u002F Epic: PROJ-xxx]\n\n## Related Projects\n- [Project] -- [feeds into \u002F depends on \u002F overlaps \u002F replaces]\n\n## Spec Seeds\n| Feature | Seed | Status |\n|---------|------|--------|\n| [Name] | specs\u002F[name]\u002Fseed.md | seed |\n\n## Phases (operational\u002Fstrategic only)\n1. [Phase]: [goal]\n\n## History\n- [YYYY-MM-DD]: Created. [context]\n```\n\nHistory for major direction changes only. Spec Seeds table = living index -- update as seeds graduate.\n\n## Re-Scope Mode\n\n1. Read existing PROJECT_INTENT.md (or infer from the project's principles file and existing specs)\n2. Present: \"Current intent: [summary]. What's changing?\"\n3. Check existing seeds, note which affected\n4. Update PROJECT_INTENT.md -- append History, update sections\n5. Tier changed -> add governance proportionally (don't remove when downgrading)\n6. Create\u002Fupdate seeds as needed\n7. Scan affected specs\u002Ftasks: \"These may need revisiting: [list]\"\n8. Recommend: `\u002Fws.refine` for in-flight, `\u002Fws.0-start` for new seeds\n\n## Retro Feedback Loop\n\nFeature retros (`\u002Fws.9-retro`) may surface project-level impact. Minor -> edit directly. Significant (tier graduation, pivot) -> run `\u002Fws.init` re-scope. Relies on ws.9-retro to escalate.\n\n## Anti-Patterns\n\n**Over-governing** (strategic governance for experiment) \u002F **Premature tracking** (epics before first feature concrete) \u002F **Intent as requirements** (ACs in PROJECT_INTENT.md) \u002F **Seeds as requirements** (Given\u002FWhen\u002FThen in seeds) \u002F **Strategy inflation** (every project must link to initiative) \u002F **Skipping intent** (3-line doc prevents scope drift) \u002F **Scope creep into design** (architecture\u002FACs = crossed into `\u002Fws.1-requirements` \u002F `\u002Fws.2-plan`) \u002F **Skipping capacity check** (overcommit should be conscious) \u002F **Shiny-thing accommodation** (\"small experiment\" without timebox = permanent side project)\n",{"name":5,"description":7},"main","1ad262fc695612ff484ee364ff66ab5298bdda58","skills\u002Fws.init",0,"https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec","https:\u002F\u002Fgithub.com\u002Fvempio","2026-10-06 16:08:48",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add vempio\u002FWhittleSpec --skill ws-init",{"tool":36,"command":37},"bunx","bunx skills add vempio\u002FWhittleSpec --skill ws-init",{"tool":39,"command":40},"pnpm","pnpm dlx skills add vempio\u002FWhittleSpec --skill ws-init","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.init\u002FSKILL.md",true,[],[45,52,59,66,73,80],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":18},"01M72TSQYBBJ3FG1MSMB9B33SZ","ws-tdd-review","Audit existing test code for quality, depth, and adherence to TDD principles.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.review\u002FSKILL.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"publishedAt":18},"01M72TSN33MN2J0CW29MBY4WC4","ws-tdd-red","Phase 3 -- implement failing tests, validating assertion quality and depth.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.red\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":18},"01M72TSJMTHFVC8FW2BGQ0NYD7","ws-tdd-outline","Phase 2 -- tree-level test design, examining intent and approach per test.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.outline\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M72TSFPHD749CY9KRV66T0RH","ws-tdd-idea","Phase 1 -- forest-level test case discovery, mapping the full problem space.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.idea\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M72TSD53VT09VF3EG67KA68E","ws-tdd-green","Phase 4 -- write minimal production code to make failing tests pass.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd.green\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M72TS9TXQ9RHYF3VBGR87BF6","ws-tdd-meta","TDD shared context -- phased protocol, quality standards, and standing instructions for all TDD skills.","https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.tdd._meta\u002FSKILL.md",[],[]]