[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72TRZCXVCK62D890Q440FD1":3,"skill-same:01M72TRZCXVCK62D890Q440FD1":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},"01M72TRZCXVCK62D890Q440FD1","ws-review",null,"Review specs for gaps, ambiguity, over-specification. Covers value, architecture, and testability perspectives.","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.review\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: ws-review\ndescription: Review specs for gaps, ambiguity, over-specification. Covers value, architecture, and testability perspectives.\n---\n# ws.review\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\u002Fexecuting.md`, `ws._meta\u002Flifecycle.md`, `ws._meta\u002Fissue-tracking.md`, `ws._meta\u002Freview-lenses.md` (steps 2-4), and `ws.tdd._meta\u002Fdebt-protocol.md` (the cross-cutting debt audit).\n\n## Purpose\n\nReview spec artifacts through three lenses in single pass: user value (analyst), technical feasibility (architect), testability (QA). User can weight perspective via context (e.g., \"\u002Fws.review focus on testability\").\n\nBoth **user-invocable** and **composable** -- `ws.fix` and `ws.refine` invoke it as a composable review (a subagent by default; see Modes for the no-subagent fallback). Name only the skills that actually do: a claimed caller that does not call is a promise the corpus cannot keep, and whether more skills *should* compose this way is a separate design question.\n\n## Stance\n\nSkeptical but constructive. Assume author knows domain; surface what they overlooked or left implicit.\n\n## Closed-spec handling\n\nIf the spec lives in `specs\u002F_completed\u002F\u003Cfeature>\u002F`, it is **CLOSED** — a historical run document. Review of a closed spec is rarely useful because it no longer binds current behaviour. Default behaviour: decline review of the closed spec with a brief note that it is referenceable archaeology, not an active contract. If the user wants a fidelity check on current behaviour, redirect to the project's authoritative surface (`ws-binding get current-behaviour-authority`; default: operator-guide \u002F README+API-docs \u002F tests \u002F code — see `ws._meta\u002Flifecycle.md` § Current-behaviour authority binding). Override only if the user explicitly asks to review the historical spec (e.g., for archaeology or to inform a successor spec).\n\nSee `ws._meta\u002Flifecycle.md` § Capture Surfaces and Commitment Gradient.\n\n## Modes\n\n- **Manual** (user calls \u002Fws.review): Full review, interactive. Ask clarifying questions. Present by severity.\n\u003C!-- WS:DEFAULT independent-review-agent -->\n- **Composable** (subagent by default): Abbreviated, structured output. No clarifying questions -- work with what's available. Return findings as structured list (severity + category + description) for caller to merge and deduplicate. Where the runtime offers no subagent, the caller runs this review as a clean-context second pass (fed only the artefact under review), escalating to a human checkpoint when the stakes are high -- the independent perspective is the requirement, the subagent is the default means.\n\u003C!-- \u002FWS -->\n\n## Process\n\n### 1. Identify Artifact\n\nAsk \"What would you like me to review?\" or infer from context. Load relevant files. If user requests specific focus, weight that perspective but still check others.\n\n### 2. Review Lenses, Cross-Cutting Checks, Adversarial Challenge\n\nSteps 2 through 4 live in `ws._meta\u002Freview-lenses.md`: the value, feasibility and\ntestability perspectives with their challenges, the cross-cutting checks, the\nadversarial challenge to run before reporting, and the red flags that stop a review.\n`ws.fix` loads the same file as its spec-review stream.\n\nIf test code exists, extend with `\u002Fws.tdd.review`.\n\n### 5. Report\n\n```markdown\n## Ambiguities\n- **[Location]**: [Quote\u002Fdescription]\n  - Risk: [What could go wrong]\n  - Suggestion: [How to clarify]\n\n## Gaps\n- **[What's missing]**: [Why it matters]\n  - Questions to answer: [Specific questions]\n\n## Over-Specification\n- **[Location]**: [What's over-specified]\n  - Risk: [Wasted effort if requirements change]\n  - Suggestion: [Appropriate detail level]\n```\n\n### 6. Prioritize\n\n- **Must fix**: Blocks implementation or high misinterpretation risk\n- **Should fix**: Significant clarity improvement\n- **Could fix**: Minor polish\n\n## Output\n\nEnd with:\n- Summary: \"Found N issues: X must-fix, Y should-fix, Z could-fix\"\n- Recommendation: \"Address must-fix before proceeding\" or \"Looks good\"\n","# ws.review\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\u002Fexecuting.md`, `ws._meta\u002Flifecycle.md`, `ws._meta\u002Fissue-tracking.md`, `ws._meta\u002Freview-lenses.md` (steps 2-4), and `ws.tdd._meta\u002Fdebt-protocol.md` (the cross-cutting debt audit).\n\n## Purpose\n\nReview spec artifacts through three lenses in single pass: user value (analyst), technical feasibility (architect), testability (QA). User can weight perspective via context (e.g., \"\u002Fws.review focus on testability\").\n\nBoth **user-invocable** and **composable** -- `ws.fix` and `ws.refine` invoke it as a composable review (a subagent by default; see Modes for the no-subagent fallback). Name only the skills that actually do: a claimed caller that does not call is a promise the corpus cannot keep, and whether more skills *should* compose this way is a separate design question.\n\n## Stance\n\nSkeptical but constructive. Assume author knows domain; surface what they overlooked or left implicit.\n\n## Closed-spec handling\n\nIf the spec lives in `specs\u002F_completed\u002F\u003Cfeature>\u002F`, it is **CLOSED** — a historical run document. Review of a closed spec is rarely useful because it no longer binds current behaviour. Default behaviour: decline review of the closed spec with a brief note that it is referenceable archaeology, not an active contract. If the user wants a fidelity check on current behaviour, redirect to the project's authoritative surface (`ws-binding get current-behaviour-authority`; default: operator-guide \u002F README+API-docs \u002F tests \u002F code — see `ws._meta\u002Flifecycle.md` § Current-behaviour authority binding). Override only if the user explicitly asks to review the historical spec (e.g., for archaeology or to inform a successor spec).\n\nSee `ws._meta\u002Flifecycle.md` § Capture Surfaces and Commitment Gradient.\n\n## Modes\n\n- **Manual** (user calls \u002Fws.review): Full review, interactive. Ask clarifying questions. Present by severity.\n\u003C!-- WS:DEFAULT independent-review-agent -->\n- **Composable** (subagent by default): Abbreviated, structured output. No clarifying questions -- work with what's available. Return findings as structured list (severity + category + description) for caller to merge and deduplicate. Where the runtime offers no subagent, the caller runs this review as a clean-context second pass (fed only the artefact under review), escalating to a human checkpoint when the stakes are high -- the independent perspective is the requirement, the subagent is the default means.\n\u003C!-- \u002FWS -->\n\n## Process\n\n### 1. Identify Artifact\n\nAsk \"What would you like me to review?\" or infer from context. Load relevant files. If user requests specific focus, weight that perspective but still check others.\n\n### 2. Review Lenses, Cross-Cutting Checks, Adversarial Challenge\n\nSteps 2 through 4 live in `ws._meta\u002Freview-lenses.md`: the value, feasibility and\ntestability perspectives with their challenges, the cross-cutting checks, the\nadversarial challenge to run before reporting, and the red flags that stop a review.\n`ws.fix` loads the same file as its spec-review stream.\n\nIf test code exists, extend with `\u002Fws.tdd.review`.\n\n### 5. Report\n\n```markdown\n## Ambiguities\n- **[Location]**: [Quote\u002Fdescription]\n  - Risk: [What could go wrong]\n  - Suggestion: [How to clarify]\n\n## Gaps\n- **[What's missing]**: [Why it matters]\n  - Questions to answer: [Specific questions]\n\n## Over-Specification\n- **[Location]**: [What's over-specified]\n  - Risk: [Wasted effort if requirements change]\n  - Suggestion: [Appropriate detail level]\n```\n\n### 6. Prioritize\n\n- **Must fix**: Blocks implementation or high misinterpretation risk\n- **Should fix**: Significant clarity improvement\n- **Could fix**: Minor polish\n\n## Output\n\nEnd with:\n- Summary: \"Found N issues: X must-fix, Y should-fix, Z could-fix\"\n- Recommendation: \"Address must-fix before proceeding\" or \"Looks good\"\n",{"name":5,"description":7},"main","1ad262fc695612ff484ee364ff66ab5298bdda58","skills\u002Fws.review",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-review",{"tool":36,"command":37},"bunx","bunx skills add vempio\u002FWhittleSpec --skill ws-review",{"tool":39,"command":40},"pnpm","pnpm dlx skills add vempio\u002FWhittleSpec --skill ws-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.review\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",[],[]]