[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77S3RY6VQPBNM5JA06GWSCF":3,"skill-same:01M77S3RY6VQPBNM5JA06GWSCF":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},"01M77S3RY6VQPBNM5JA06GWSCF","traceability-review",null,"Review explicit architecture traceability metadata for gaps, inconsistencies, unsupported claims, stale links, dangling references, and metamodel violations. Use when Codex needs to inspect artifact relations, validate ADR-to-risk or quality-scenario coverage, propose relation updates, or produce an evidence-backed traceability review report.","docs-as-code-toolkit\u002Farchitecture-knowledge-toolkit","docs-as-code-toolkit","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F273816461?v=4","01M77S1546130CS9RH10VAW9DT","01M77S1559YEN3JKTVX724CJ8K",4,"MIT","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftraceability-review\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: traceability-review\ndescription: Review explicit architecture traceability metadata for gaps, inconsistencies, unsupported claims, stale links, dangling references, and metamodel violations. Use when Codex needs to inspect artifact relations, validate ADR-to-risk or quality-scenario coverage, propose relation updates, or produce an evidence-backed traceability review report.\n---\n\n# Traceability Review Skill\n\n## Purpose\n\nReview explicit architecture traceability metadata for gaps, inconsistencies,\nand unsupported claims. Treat every AI-suggested relation, finding, and impact\nclaim as proposed until a human reviewer accepts it in the repository.\n\nThis skill is guidance and reusable content only. Do not implement AI execution,\ndo not implement a generator, and do not add automation as part of using this\nskill.\n\nApply the repository contract hierarchy: this skill narrows `AGENTS.md`, and\n`AGENTS.md` adapts `general-semantic-contracts.md`. Do not duplicate general\nmetadata, anchor, Docs-as-Code, arc42, or traceability rules here unless the\ntraceability review workflow needs a stricter rule.\n\n## Core Workflow\n\n1. Inspect the requested documentation scope before writing findings.\n2. Read artifact metadata and relation metadata from repository source files.\n3. Inspect the relevant AsciiDoc prose only to verify relation rationale,\n   visible references, anchors, and evidence.\n4. Inspect relevant source code, tests, configuration, or operational evidence\n   only when relation claims depend on those artifacts.\n5. Validate relation endpoints, relation types, ownership, status, rationale,\n   and review state against the metamodel.\n6. Compare explicit metadata relations with visible AsciiDoc `xref` links when\n   both are expected.\n7. Identify missing, weak, stale, dangling, conflicting, or unsupported\n   relations.\n8. Propose relation additions or changes as `proposed`; do not silently create\n   accepted relations.\n9. Update affected artifacts with **outgoing** relations only when the user\n   requested edits. Never create reciprocal incoming relations; they are derived\n   automatically during generation.\n10. Prefer deterministic ordering by source ID, relation type, target ID, then\n    rationale.\n11. Prefer small, reviewable patches.\n12. Run the repository validator after changes if one is available.\n\n## Required Reading\n\nRead these references as needed:\n\n- `..\u002F..\u002Fsrc\u002Fdocs\u002Farc42\u002F04-solution-strategy\u002Fdoc-04001-metamodel.adoc` before reviewing\n  artifact metadata, artifact types, lifecycle states, or relation semantics.\n- `..\u002Freferences\u002Fmetadata-rules.md` before reviewing YAML front matter.\n- `..\u002Freferences\u002Frelation-rules.md` before proposing or updating relations.\n- `..\u002Freferences\u002Fadr-writing-guide.md` before reviewing ADR relations.\n- `..\u002Freferences\u002Frisk-writing-guide.md` before reviewing risk relations.\n- `..\u002Freferences\u002Fquality-scenario-guide.md` before reviewing quality scenario\n  relations.\n\nUse these templates:\n\n- `..\u002F..\u002Ftemplates\u002Fimpact-report.adoc` for review reports when the user wants\n  analysis without direct artifact changes.\n\n## Inputs\n\n- Artifact metadata conforming to `metamodel\u002Fartifact.schema.yaml`.\n- Relation metadata conforming to `metamodel\u002Frelations.schema.yaml`.\n- Relevant AsciiDoc source documents.\n- Review focus, such as ADR-to-risk coverage or quality-scenario coverage.\n- Optional evidence sources, such as code, tests, configuration, deployment\n  files, issue references, or operational data.\n- Review scope: report-only, update proposed relations, or validate a changed\n  artifact set.\n\n## Output\n\nProduce a review report with:\n\n- Missing or weak relations.\n- Stale, dangling, or conflicting relations.\n- Suggested relation additions marked as `proposed`.\n- Questions for human reviewers.\n- Validation notes against the metamodel.\n\n## Inspection Rules\n\n- Prefer reviewed repository source files over conversational memory.\n- Do not load derived output as evidence or architecture context. This includes\n  `generated\u002F`, `build\u002F`, `dist\u002F`, `target\u002F`, `out\u002F`, rendered HTML\u002FPDF,\n  generated indexes, traceability views, and assembled documentation.\n- Treat explicit metadata as authoritative over inferred prose.\n- Treat visible `xref` links as documentation references, not as substitutes for\n  metadata relations when traceability is required.\n- Check the artifact and relation schemas before declaring a relation invalid.\n- Check existing artifact IDs before suggesting new IDs.\n- Never add reciprocal relations. Incoming relations are derived from outgoing\n  relations during generation.\n- Preserve accepted or reviewed relations unless repository evidence justifies a\n  proposed update.\n\n## Output Rules\n\n- Do not silently create accepted relations.\n- Identify dangling references by stable ID.\n- Mark AI-suggested additions as `status: proposed` and `reviewed: false`.\n- Prefer precise relation types over `relates_to`.\n- Prefer deterministic ordering by source ID, relation type, target ID, then\n  rationale.\n- Keep findings actionable and evidence-backed.\n- Check metadata, relation, anchor, and `xref` rules from\n  `general-semantic-contracts.md`.\n\n## Review Checklist\n\n- All relation endpoints exist.\n- Relation types match the intended semantics.\n- Accepted relations have evidence or rationale.\n- AI-suggested additions are not marked as reviewed.\n- Visible references to documentation artifacts use valid anchor-based\n  AsciiDoc `xref` links where required.\n- Visible references use the explicit target anchors from source files, not\n  raw numbered chapter file names.\n- Open questions identify the human decision needed to resolve each uncertain\n  relation.\n\n## Validation\n\nAfter edits, run the repository validator if available. Prefer existing commands\nfrom the repository documentation or scripts. If no validator exists, report\nthat validation was not available and describe the manual checks performed.\n","# Traceability Review Skill\n\n## Purpose\n\nReview explicit architecture traceability metadata for gaps, inconsistencies,\nand unsupported claims. Treat every AI-suggested relation, finding, and impact\nclaim as proposed until a human reviewer accepts it in the repository.\n\nThis skill is guidance and reusable content only. Do not implement AI execution,\ndo not implement a generator, and do not add automation as part of using this\nskill.\n\nApply the repository contract hierarchy: this skill narrows `AGENTS.md`, and\n`AGENTS.md` adapts `general-semantic-contracts.md`. Do not duplicate general\nmetadata, anchor, Docs-as-Code, arc42, or traceability rules here unless the\ntraceability review workflow needs a stricter rule.\n\n## Core Workflow\n\n1. Inspect the requested documentation scope before writing findings.\n2. Read artifact metadata and relation metadata from repository source files.\n3. Inspect the relevant AsciiDoc prose only to verify relation rationale,\n   visible references, anchors, and evidence.\n4. Inspect relevant source code, tests, configuration, or operational evidence\n   only when relation claims depend on those artifacts.\n5. Validate relation endpoints, relation types, ownership, status, rationale,\n   and review state against the metamodel.\n6. Compare explicit metadata relations with visible AsciiDoc `xref` links when\n   both are expected.\n7. Identify missing, weak, stale, dangling, conflicting, or unsupported\n   relations.\n8. Propose relation additions or changes as `proposed`; do not silently create\n   accepted relations.\n9. Update affected artifacts with **outgoing** relations only when the user\n   requested edits. Never create reciprocal incoming relations; they are derived\n   automatically during generation.\n10. Prefer deterministic ordering by source ID, relation type, target ID, then\n    rationale.\n11. Prefer small, reviewable patches.\n12. Run the repository validator after changes if one is available.\n\n## Required Reading\n\nRead these references as needed:\n\n- `..\u002F..\u002Fsrc\u002Fdocs\u002Farc42\u002F04-solution-strategy\u002Fdoc-04001-metamodel.adoc` before reviewing\n  artifact metadata, artifact types, lifecycle states, or relation semantics.\n- `..\u002Freferences\u002Fmetadata-rules.md` before reviewing YAML front matter.\n- `..\u002Freferences\u002Frelation-rules.md` before proposing or updating relations.\n- `..\u002Freferences\u002Fadr-writing-guide.md` before reviewing ADR relations.\n- `..\u002Freferences\u002Frisk-writing-guide.md` before reviewing risk relations.\n- `..\u002Freferences\u002Fquality-scenario-guide.md` before reviewing quality scenario\n  relations.\n\nUse these templates:\n\n- `..\u002F..\u002Ftemplates\u002Fimpact-report.adoc` for review reports when the user wants\n  analysis without direct artifact changes.\n\n## Inputs\n\n- Artifact metadata conforming to `metamodel\u002Fartifact.schema.yaml`.\n- Relation metadata conforming to `metamodel\u002Frelations.schema.yaml`.\n- Relevant AsciiDoc source documents.\n- Review focus, such as ADR-to-risk coverage or quality-scenario coverage.\n- Optional evidence sources, such as code, tests, configuration, deployment\n  files, issue references, or operational data.\n- Review scope: report-only, update proposed relations, or validate a changed\n  artifact set.\n\n## Output\n\nProduce a review report with:\n\n- Missing or weak relations.\n- Stale, dangling, or conflicting relations.\n- Suggested relation additions marked as `proposed`.\n- Questions for human reviewers.\n- Validation notes against the metamodel.\n\n## Inspection Rules\n\n- Prefer reviewed repository source files over conversational memory.\n- Do not load derived output as evidence or architecture context. This includes\n  `generated\u002F`, `build\u002F`, `dist\u002F`, `target\u002F`, `out\u002F`, rendered HTML\u002FPDF,\n  generated indexes, traceability views, and assembled documentation.\n- Treat explicit metadata as authoritative over inferred prose.\n- Treat visible `xref` links as documentation references, not as substitutes for\n  metadata relations when traceability is required.\n- Check the artifact and relation schemas before declaring a relation invalid.\n- Check existing artifact IDs before suggesting new IDs.\n- Never add reciprocal relations. Incoming relations are derived from outgoing\n  relations during generation.\n- Preserve accepted or reviewed relations unless repository evidence justifies a\n  proposed update.\n\n## Output Rules\n\n- Do not silently create accepted relations.\n- Identify dangling references by stable ID.\n- Mark AI-suggested additions as `status: proposed` and `reviewed: false`.\n- Prefer precise relation types over `relates_to`.\n- Prefer deterministic ordering by source ID, relation type, target ID, then\n  rationale.\n- Keep findings actionable and evidence-backed.\n- Check metadata, relation, anchor, and `xref` rules from\n  `general-semantic-contracts.md`.\n\n## Review Checklist\n\n- All relation endpoints exist.\n- Relation types match the intended semantics.\n- Accepted relations have evidence or rationale.\n- AI-suggested additions are not marked as reviewed.\n- Visible references to documentation artifacts use valid anchor-based\n  AsciiDoc `xref` links where required.\n- Visible references use the explicit target anchors from source files, not\n  raw numbered chapter file names.\n- Open questions identify the human decision needed to resolve each uncertain\n  relation.\n\n## Validation\n\nAfter edits, run the repository validator if available. Prefer existing commands\nfrom the repository documentation or scripts. If no validator exists, report\nthat validation was not available and describe the manual checks performed.\n",{"name":5,"description":7},"main","209607df178aba11b58f76b19e45d58af0d44f52","skills\u002Ftraceability-review",2,"https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit","2026-11-10 03:36:06",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add docs-as-code-toolkit\u002Farchitecture-knowledge-toolkit --skill traceability-review",{"tool":36,"command":37},"bunx","bunx skills add docs-as-code-toolkit\u002Farchitecture-knowledge-toolkit --skill traceability-review",{"tool":39,"command":40},"pnpm","pnpm dlx skills add docs-as-code-toolkit\u002Farchitecture-knowledge-toolkit --skill traceability-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftraceability-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},"01M77S3NK6KC59ND1J2JSXFDW3","slice-issues","Slice GitHub parent issues into reviewable real sub-issues. Use when Codex is asked to split, slice, decompose, refine, or plan a GitHub issue into child issues, sub-issues, implementation slices, or reviewable follow-up issues before implementation work begins.","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fslice-issues\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},"01M77S3GN6ZDB3WM0ACCWV03EV","risk","Create proposed architecture risk artifacts and analyze their traceability to ADRs, quality scenarios, requirements, components, controls, and evidence. Use when Codex needs to identify, draft, update, prioritize, or review architecture risks, separate risks from issues and decisions, propose mitigations, or produce a risk impact report without deciding acceptance.","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Frisk\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},"01M77S3CH6QB0Y11BV002AS7PY","quality-scenario","Create proposed quality scenarios and analyze their traceability to quality objectives, ADRs, risks, requirements, architecture artifacts, and code evidence. Use when Codex needs to draft or update measurable quality scenarios, inspect existing arc42 Chapter 10 quality requirements, derive scenarios from source evidence without inventing targets, propose metadata relations, or produce a quality scenario impact report.","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fquality-scenario\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},"01M77S394HQDDQKQFPQKP8V0XW","presentation","Create or update docs-as-code presentation material as AsciiDoc reveal.js decks rendered with docs-toolbox. Use when Codex needs to prepare talks, meetup or conference proposals, speaker notes, demo scripts, event-specific artifacts under talks\u002F, or slide decks that must remain repository-native rather than PowerPoint or Google Slides files.","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fpresentation\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},"01M77S34KBA1J2VV3QHK9JFV3N","pr-review","Review GitHub pull requests and proposed branch changes for correctness, regressions, missing tests, documentation-contract violations, traceability gaps, and reviewability. Use when an AI assistant is asked to review a PR, review pull request changes, inspect a PR branch before merge, or produce PR review comments.","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fpr-review\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},"01M77S30N3KDD8EWKXNS9FVJ9C","post-merge-sync","Synchronize a local checkout after a pull request has been integrated: verify a clean worktree, switch to the base branch, fast-forward from the remote, confirm the PR changes are present, and clean up local and remote PR branches when safe. Use when an agent is asked to clean up after an integrated PR or return the repository to the latest base branch.","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Fpost-merge-sync\u002FSKILL.md",[],[]]