[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72TS76RJ3K1HNGQXJ2S09HT":3,"skill-same:01M72TS76RJ3K1HNGQXJ2S09HT":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},"01M72TS76RJ3K1HNGQXJ2S09HT","ws-sweep",null,"Completeness sweep -- exhaustively verify nothing was missed after a change.","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.sweep\u002FSKILL.md",[],[],"2026-11-10 22:39:42",false,"---\nname: ws-sweep\ndescription: Completeness sweep -- exhaustively verify nothing was missed after a change.\n---\n# ws.sweep\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\u002Fsweep-procedure.md` (steps 1-4c), and `ws.tdd._meta\u002Fdebt-protocol.md` (step 6's debt audit).\n\n## Purpose\n\nAfter any non-trivial change, exhaustively verify nothing missed. Goes beyond search-and-replace: covers stale references, orphaned content, broken cross-references, inconsistent docs. Shallow verification is proven, recurring failure mode. Checking only files you touched is not verification -- value is in finding what you DIDN'T touch but should have.\n\n**This skill never mutates.** That is the promise, and it is not carved out for trivial findings: a sweep that also edits is a diff to review rather than an observation to trust. Findings go out as a report with a one-line fix each; `\u002Fws.fix` is the skill that applies them.\n\n## When to Use\n\nAfter renaming files\u002Ffunctions\u002Fvariables\u002Fcommands \u002F after migrating patterns \u002F after moving content between files \u002F after changing doc structure\u002Fworkflows \u002F after any change applying consistently across multiple files \u002F paranoia check before committing cross-cutting changes.\n\n## Process\n\nSteps 1 through 4c live in `ws._meta\u002Fsweep-procedure.md`: state what changed, think\nthrough what could ripple, run the exhaustive residual search, then the structural, CLI\nand BDD-correspondence checks that a text search cannot reach. `ws.fix` loads the same\nfile as its completeness stream, so a sweep run either way covers the same ground.\n\n### 5. Report\n\n```markdown\n## Sweep Results\n\n**Change**: [Brief description]\n**Scope**: [What was searched]\n\n### Residual Matches (old patterns)\n\n| Pattern | Matches | Files |\n|---------|---------|-------|\n| `old_name` | 0 | -- |\n| `\u002Fold_name` | 2 | file_a.md:31, file_b.md:72 |\n\n### Structural Issues\n\n| Issue | Location | Detail |\n|-------|----------|--------|\n| Stale cross-ref | workflow.md:68 | Points to old command name |\n| Index mismatch | README.md | Lists 5 items, 6 exist on disk |\n\n### BDD Scenario Audit (when .feature and task files exist)\n\n| Scenario | Task | Task Status | Scenario Status | Finding |\n|----------|------|-------------|-----------------|---------|\n| ... | ... | ... | ... | OK \u002F CRITICAL \u002F ORPHAN \u002F MISSING |\n\n- **Critical**: N scenarios @todo under completed tasks\n- **Orphans**: N scenarios not traced to any task\n- **Missing**: N task commitments with no corresponding scenario\n\n### Verdict\n\n[CLEAN \u002F N issues found -- list them]\n```\n\n### 6. Technical Debt Spot Check\n\nAfter residual\u002Fstructural checks: dead imports\u002Fconfig from removing\u002Frenaming? \u002F orphaned files from migration? \u002F stale comments referencing old names? \u002F debt marker consistency (run the audit from `ws.tdd._meta\u002Fdebt-protocol.md` § Technical Debt Protocol -- each `FIXME: [DEBT]` must have paired `@debt` test and vice versa; has any marker's re-enable condition been met?).\n\n**Threshold**: Trivial debt (\u003C 5 min, no risk) -- report it with the one-line fix, do not\napply it. Substantial -- flag for a dedicated task. The sweep's job is to leave nothing\nunseen, not to leave the tree changed.\n\n### 7. Hand Off\n\nSweep does not mutate -- that is the promise, and it is what lets a finding be read as an\nobservation rather than a diff to review. Give every finding a one-line proposed fix, so\nthe operator can answer \"fix the reported issues as proposed\" in one sentence, or reach\nfor `\u002Fws.fix` next time as the no-stop shortcut. Once the fixes land, re-run the sweep:\nzero residuals is the close.\n\n## Anti-Patterns\n\n- Declaring \"done\" once the reported matches are fixed, without re-running the sweep\n- Searching only files you touched\n- Searching one variant but not others (`\u002Ffoo` but not `foo` in backticks)\n- Asserting \"nothing references X\" without grep proof\n- Checking only text patterns when change was structural\n- Skipping docs and workflow files because \"they're not code\"\n- Trusting task `[x]` status without verifying BDD scenario state -- `@todo` invisible to runner (skipped), \"all tests pass\" is not evidence\n- Checking only top-down from task claims -- always also scan bottom-up from scenarios\n- Grepping for `--help` handling instead of actually running CLI\n- Assuming documentation exists because no one complained\n- Trusting BDD scenarios cover documented workflows without bidirectional check\n","# ws.sweep\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\u002Fsweep-procedure.md` (steps 1-4c), and `ws.tdd._meta\u002Fdebt-protocol.md` (step 6's debt audit).\n\n## Purpose\n\nAfter any non-trivial change, exhaustively verify nothing missed. Goes beyond search-and-replace: covers stale references, orphaned content, broken cross-references, inconsistent docs. Shallow verification is proven, recurring failure mode. Checking only files you touched is not verification -- value is in finding what you DIDN'T touch but should have.\n\n**This skill never mutates.** That is the promise, and it is not carved out for trivial findings: a sweep that also edits is a diff to review rather than an observation to trust. Findings go out as a report with a one-line fix each; `\u002Fws.fix` is the skill that applies them.\n\n## When to Use\n\nAfter renaming files\u002Ffunctions\u002Fvariables\u002Fcommands \u002F after migrating patterns \u002F after moving content between files \u002F after changing doc structure\u002Fworkflows \u002F after any change applying consistently across multiple files \u002F paranoia check before committing cross-cutting changes.\n\n## Process\n\nSteps 1 through 4c live in `ws._meta\u002Fsweep-procedure.md`: state what changed, think\nthrough what could ripple, run the exhaustive residual search, then the structural, CLI\nand BDD-correspondence checks that a text search cannot reach. `ws.fix` loads the same\nfile as its completeness stream, so a sweep run either way covers the same ground.\n\n### 5. Report\n\n```markdown\n## Sweep Results\n\n**Change**: [Brief description]\n**Scope**: [What was searched]\n\n### Residual Matches (old patterns)\n\n| Pattern | Matches | Files |\n|---------|---------|-------|\n| `old_name` | 0 | -- |\n| `\u002Fold_name` | 2 | file_a.md:31, file_b.md:72 |\n\n### Structural Issues\n\n| Issue | Location | Detail |\n|-------|----------|--------|\n| Stale cross-ref | workflow.md:68 | Points to old command name |\n| Index mismatch | README.md | Lists 5 items, 6 exist on disk |\n\n### BDD Scenario Audit (when .feature and task files exist)\n\n| Scenario | Task | Task Status | Scenario Status | Finding |\n|----------|------|-------------|-----------------|---------|\n| ... | ... | ... | ... | OK \u002F CRITICAL \u002F ORPHAN \u002F MISSING |\n\n- **Critical**: N scenarios @todo under completed tasks\n- **Orphans**: N scenarios not traced to any task\n- **Missing**: N task commitments with no corresponding scenario\n\n### Verdict\n\n[CLEAN \u002F N issues found -- list them]\n```\n\n### 6. Technical Debt Spot Check\n\nAfter residual\u002Fstructural checks: dead imports\u002Fconfig from removing\u002Frenaming? \u002F orphaned files from migration? \u002F stale comments referencing old names? \u002F debt marker consistency (run the audit from `ws.tdd._meta\u002Fdebt-protocol.md` § Technical Debt Protocol -- each `FIXME: [DEBT]` must have paired `@debt` test and vice versa; has any marker's re-enable condition been met?).\n\n**Threshold**: Trivial debt (\u003C 5 min, no risk) -- report it with the one-line fix, do not\napply it. Substantial -- flag for a dedicated task. The sweep's job is to leave nothing\nunseen, not to leave the tree changed.\n\n### 7. Hand Off\n\nSweep does not mutate -- that is the promise, and it is what lets a finding be read as an\nobservation rather than a diff to review. Give every finding a one-line proposed fix, so\nthe operator can answer \"fix the reported issues as proposed\" in one sentence, or reach\nfor `\u002Fws.fix` next time as the no-stop shortcut. Once the fixes land, re-run the sweep:\nzero residuals is the close.\n\n## Anti-Patterns\n\n- Declaring \"done\" once the reported matches are fixed, without re-running the sweep\n- Searching only files you touched\n- Searching one variant but not others (`\u002Ffoo` but not `foo` in backticks)\n- Asserting \"nothing references X\" without grep proof\n- Checking only text patterns when change was structural\n- Skipping docs and workflow files because \"they're not code\"\n- Trusting task `[x]` status without verifying BDD scenario state -- `@todo` invisible to runner (skipped), \"all tests pass\" is not evidence\n- Checking only top-down from task claims -- always also scan bottom-up from scenarios\n- Grepping for `--help` handling instead of actually running CLI\n- Assuming documentation exists because no one complained\n- Trusting BDD scenarios cover documented workflows without bidirectional check\n",{"name":5,"description":7},"main","1ad262fc695612ff484ee364ff66ab5298bdda58","skills\u002Fws.sweep",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-sweep",{"tool":36,"command":37},"bunx","bunx skills add vempio\u002FWhittleSpec --skill ws-sweep",{"tool":39,"command":40},"pnpm","pnpm dlx skills add vempio\u002FWhittleSpec --skill ws-sweep","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fvempio\u002FWhittleSpec\u002Fblob\u002Fmain\u002Fskills\u002Fws.sweep\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",[],[]]