[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DEP659MES18XFY5XYSQRJX":3,"skill-same:01M6DEP659MES18XFY5XYSQRJX":79},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":54,"ownerDescription":6,"updatedAt":55,"install":56,"resources":68},"01M6DEP659MES18XFY5XYSQRJX","architecture-guard",null,"Detects pattern drift against architecture decisions. Read-only enforcer. Invoked by Impetus — do not invoke directly.","iamsteveholmes\u002Fmomentum","iamsteveholmes","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92353?v=4","01M6DENK56DRSF72CJ6FJQ4RT1","Steve Holmes","01M6DENK9KCZRYFFEB0M689F7D",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Farchitecture-guard\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"architecture","guard","architecture guard","Bash","grep","decisions","read","only","do","drift","pattern","impetus","read-only","fork","invoke","2026-11-10 10:12:30",false,"---\nnamespace: aiwg\nname: doc-sync\ndescription: Synchronize documentation and code with bounded, scope-first drift checks\ncommandHint:\n  argumentHint: \"\u003Cdirection> [--dry-run] [--scope \u003Cpath>] [--incremental] [--parallel N]\"\n  allowedTools: Task, Read, Write, Bash, Glob, Grep, Edit\n  category: utilities\n  orchestration: true\nplatforms: [all]\n\n---\n\n# Doc Sync\n\nDetect and resolve documentation drift without front-loading a full repository\naudit. Treat standard Claude Code Sonnet context as the baseline.\n\n## Triggers\n\nUsers may say:\n- \"doc sync\"\n- \"sync docs\"\n- \"fix doc drift\"\n- \"reconcile docs\"\n- \"update docs to match code\"\n- \"update code to match docs\"\n- \"check for documentation drift\"\n\n## Parameters\n\n`direction` is required:\n- `code-to-docs`: update docs to match code\n- `docs-to-code`: identify code gaps against docs\n- `full`: bidirectional reconciliation with human review for conflicts\n\nOptions:\n- `--dry-run`: report only, no file edits\n- `--scope \u003Cpath>`: limit the audit to a subtree or file group\n- `--incremental`: start from changed files since the last sync, then current\n  git changed files if no last-run record exists\n- `--parallel N`: cap concurrent auditors; default `2`, maximum `4`\n\n## Artifact root resolution\n\nTreat every `.aiwg\u002F...` path below as a logical artifact path. Before reading\nor writing sync state, working evidence, or reports, run `aiwg artifacts path`\nfrom the active workspace and use the returned absolute directory as\n`AIWG_ARTIFACT_ROOT`. Never write these payloads to a literal project-local\n`.aiwg\u002F` when `AIWG_ARTIFACTS_PATH` or `.aiwg-location` redirects the corpus.\n\n## Context Budget Rules\n\n- Start with `git status --short`, `git diff --name-only`, and\n  `git diff --cached --name-only`.\n- If no `--scope` or `--incremental` is supplied, derive a candidate scope from\n  changed files and ask before expanding to the full repo.\n- Use inventories (`rg --files`, `find`, git path lists) before reading file\n  bodies.\n- Dispatch auditors only for domains implicated by the scoped files.\n- Each auditor returns at most 10 findings and 600 words to the parent context.\n  Detailed evidence goes under `$AIWG_ARTIFACT_ROOT\u002Fworking\u002Fdoc-sync\u002F`.\n- Do not preload other skills into auditor agents.\n- For combined doc-sync, blog, and commit requests, keep blog\u002Frelease coverage\n  as one scoped lane and return a handoff summary for `commit-and-push`.\n\n## Workflow\n\n1. Parse direction and options.\n2. Build the cheap scope inventory from git path lists.\n3. Select relevant lanes only: CLI\u002FAPI docs, provider docs, skill\u002Fagent catalogs,\n   README\u002Fchangelog\u002Frelease\u002Fblog material, or config\u002Fschema docs.\n4. Run bounded auditors for selected lanes only.\n5. Write `$AIWG_ARTIFACT_ROOT\u002Freports\u002Fdoc-sync-{timestamp}.md` with scope, findings,\n   auto-fixable items, human-review items, and changed files.\n6. If not `--dry-run`, apply high-confidence fixes only.\n7. Validate modified files with targeted checks.\n8. Record `$AIWG_ARTIFACT_ROOT\u002Freports\u002Fdoc-sync-last-run.json`.\n9. Return report path, files changed, validation commands, and remaining review\n   items.\n\n## Output Contract\n\nReturn:\n- report path\n- scope audited\n- files changed\n- validation commands run\n- remaining human-review items\n- recommended handoff skill, if any\n","# Doc Sync\n\nDetect and resolve documentation drift without front-loading a full repository\naudit. Treat standard Claude Code Sonnet context as the baseline.\n\n## Triggers\n\nUsers may say:\n- \"doc sync\"\n- \"sync docs\"\n- \"fix doc drift\"\n- \"reconcile docs\"\n- \"update docs to match code\"\n- \"update code to match docs\"\n- \"check for documentation drift\"\n\n## Parameters\n\n`direction` is required:\n- `code-to-docs`: update docs to match code\n- `docs-to-code`: identify code gaps against docs\n- `full`: bidirectional reconciliation with human review for conflicts\n\nOptions:\n- `--dry-run`: report only, no file edits\n- `--scope \u003Cpath>`: limit the audit to a subtree or file group\n- `--incremental`: start from changed files since the last sync, then current\n  git changed files if no last-run record exists\n- `--parallel N`: cap concurrent auditors; default `2`, maximum `4`\n\n## Artifact root resolution\n\nTreat every `.aiwg\u002F...` path below as a logical artifact path. Before reading\nor writing sync state, working evidence, or reports, run `aiwg artifacts path`\nfrom the active workspace and use the returned absolute directory as\n`AIWG_ARTIFACT_ROOT`. Never write these payloads to a literal project-local\n`.aiwg\u002F` when `AIWG_ARTIFACTS_PATH` or `.aiwg-location` redirects the corpus.\n\n## Context Budget Rules\n\n- Start with `git status --short`, `git diff --name-only`, and\n  `git diff --cached --name-only`.\n- If no `--scope` or `--incremental` is supplied, derive a candidate scope from\n  changed files and ask before expanding to the full repo.\n- Use inventories (`rg --files`, `find`, git path lists) before reading file\n  bodies.\n- Dispatch auditors only for domains implicated by the scoped files.\n- Each auditor returns at most 10 findings and 600 words to the parent context.\n  Detailed evidence goes under `$AIWG_ARTIFACT_ROOT\u002Fworking\u002Fdoc-sync\u002F`.\n- Do not preload other skills into auditor agents.\n- For combined doc-sync, blog, and commit requests, keep blog\u002Frelease coverage\n  as one scoped lane and return a handoff summary for `commit-and-push`.\n\n## Workflow\n\n1. Parse direction and options.\n2. Build the cheap scope inventory from git path lists.\n3. Select relevant lanes only: CLI\u002FAPI docs, provider docs, skill\u002Fagent catalogs,\n   README\u002Fchangelog\u002Frelease\u002Fblog material, or config\u002Fschema docs.\n4. Run bounded auditors for selected lanes only.\n5. Write `$AIWG_ARTIFACT_ROOT\u002Freports\u002Fdoc-sync-{timestamp}.md` with scope, findings,\n   auto-fixable items, human-review items, and changed files.\n6. If not `--dry-run`, apply high-confidence fixes only.\n7. Validate modified files with targeted checks.\n8. Record `$AIWG_ARTIFACT_ROOT\u002Freports\u002Fdoc-sync-last-run.json`.\n9. Return report path, files changed, validation commands, and remaining review\n   items.\n\n## Output Contract\n\nReturn:\n- report path\n- scope audited\n- files changed\n- validation commands run\n- remaining human-review items\n- recommended handoff skill, if any\n",{"name":39,"namespace":40,"platforms":41,"commandHint":43,"description":48},"doc-sync","aiwg",[42],"all",{"category":44,"allowedTools":45,"argumentHint":46,"orchestration":47},"utilities","Task, Read, Write, Bash, Glob, Grep, Edit","\u003Cdirection> [--dry-run] [--scope \u003Cpath>] [--incremental] [--parallel N]",true,"Synchronize documentation and code with bounded, scope-first drift checks","main","6754967c344ccb087a8de06972f55a41067b291b","skills\u002Fmomentum\u002Fskills\u002Farchitecture-guard","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes","http:\u002F\u002Fcapitalcodemonkey.blogspot.com","2026-11-09 05:58:39",{"source":8,"skillName":39,"commands":57,"prompt":67,"zipAvailable":47},[58,61,64],{"tool":59,"command":60},"npx","npx skills add iamsteveholmes\u002Fmomentum --skill doc-sync",{"tool":62,"command":63},"bunx","bunx skills add iamsteveholmes\u002Fmomentum --skill doc-sync",{"tool":65,"command":66},"pnpm","pnpm dlx skills add iamsteveholmes\u002Fmomentum --skill doc-sync","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Farchitecture-guard\u002FSKILL.md",[69,75],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"evals\u002Feval-no-drift-detection-attempted.md","REFERENCE","参考文档",528,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Farchitecture-guard\u002Fevals\u002Feval-no-drift-detection-attempted.md",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"evals\u002Feval-stub-invocation-response.md",531,"https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Farchitecture-guard\u002Fevals\u002Feval-stub-invocation-response.md",[80,101,119,141,158,176],{"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":34},"01M6DES6J0HGT27SEJJWF316FV","upstream-fix","Traces quality failures upstream to spec, rule, or workflow root cause. Proposes fixes at the right level.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fupstream-fix\u002FSKILL.md",[],[87,88,89,90,91,92,93,94,95,96,97,98,99,100],"upstream","upstream fix","fix","to spec","root cause","traces","fixes","at","high","root","rule","quality","workflow","spec",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":34},"01M6DES4A08NFWQM0AJBR2RRX5","triage","Dedup gate + batch-classify observations into five classes, enrich ARTIFACTs, batch-approve, delegate to intake\u002Fdecision or queue.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Ftriage\u002FSKILL.md",[],[103,108,109,110,111,112,113,114,95,115,116,117,118],"batch","intake","artifacts","decision","queue","delegate","approve","observations","enrich","classify","gate",{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":34},"01M6DERYX8W6Z9Z4RM5V6E9HED","sprint-planning","Sprint planning — story selection, team composition, Gherkin specs, and visual companion plan gate for developer sign-off.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-planning\u002FSKILL.md",[],[126,127,128,95,129,130,131,132,133,134,135,136,137,138,139,140,118],"planning","sprint","sprint planning","visual companion","plan gate","for","companion","sign","visual","selection","Composition","Story","plan","team","developer",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":34},"01M6DERWCP7Y0WDY5KG6109RQB","sprint-manager","Sole writer of stories\u002Findex.json and sprints\u002Findex.json — validates state transitions, activates sprints, manages epic membership.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-manager\u002FSKILL.md",[],[148,127,149,150,151,152,153,154,155,156,157],"sprint manager","manager","writer","stories","sprints","EPIC","transitions","json","index","state",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":34},"01M6DERS7B4QHAH5GZHHBA4AHB","sprint-dev","Sprint execution — dependency-driven story development, post-merge AVFL, and team review.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fsprint-dev\u002FSKILL.md",[],[165,166,127,139,167,168,169,170,171,172,95,173,174,175,137],"dev","sprint dev","execution","team review","development","merge","review","dependency","post","avfl","driven",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":34},"01M6DERP0A271FYSAXCV85GF04","retro","Sprint retrospective — transcript audit engine (dynamic Workflow), story verification, findings document, and sprint closure.","https:\u002F\u002Fgithub.com\u002Fiamsteveholmes\u002Fmomentum\u002Fblob\u002Fmain\u002Fskills\u002Fmomentum\u002Fskills\u002Fretro\u002FSKILL.md",[],[178,183,184,95,185,127,186,137,187,188,189,190,191,99],"sprint retrospective","closure","dynamic workflow","document","engine","audit","verification","transcript","retrospective"]