[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77S1EEP0DDVVATHZTYF8KWA":3,"skill-same:01M77S1EEP0DDVVATHZTYF8KWA":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},"01M77S1EEP0DDVVATHZTYF8KWA","architecture-impact",null,"Analyze and document architecture impact for feature requests, Epic issues, UserStory issues, refactoring tasks, issue implementation, and review tasks. Use when Codex is asked to handle a feature request, decide whether feature work should become an Epic or UserStory, create or refine an Epic, mark a UserStory or refactoring issue, implement feature or refactoring work, review a pull request or review task, assess whether code changes affect architecture documentation, update affected arc42 sections, connect features or refactorings to ADRs, quality goals, quality scenarios, risks, components, runtime scenarios, deployment views, or create follow-up ADRs with diagrams.","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\u002Farchitecture-impact\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: architecture-impact\ndescription: Analyze and document architecture impact for feature requests, Epic issues, UserStory issues, refactoring tasks, issue implementation, and review tasks. Use when Codex is asked to handle a feature request, decide whether feature work should become an Epic or UserStory, create or refine an Epic, mark a UserStory or refactoring issue, implement feature or refactoring work, review a pull request or review task, assess whether code changes affect architecture documentation, update affected arc42 sections, connect features or refactorings to ADRs, quality goals, quality scenarios, risks, components, runtime scenarios, deployment views, or create follow-up ADRs with diagrams.\n---\n\n# Architecture Impact\n\n## Overview\n\nKeep feature work, refactorings, reviews, and architecture knowledge\nsynchronized. A feature request or refactoring task is not complete until the\nrelevant implementation, issue tracking, and architecture documentation tell the\nsame story.\n\nApply the repository contract hierarchy: this skill narrows `AGENTS.md`, and\n`AGENTS.md` adapts `general-semantic-contracts.md`. Do not duplicate general\narc42, metadata, anchor, Docs-as-Code, or traceability rules here.\n\nThis skill intentionally repeats a few backlog and issue-marking rules from\n`general-semantic-contracts.md` because they are operationally important while\nhandling feature and review work. Keep the general contract as the long-term\nsource of truth when these rules evolve.\n\n## Core Workflow\n\n1. Identify the feature request, Epic issue, UserStory issue, refactoring task,\n   implementation issue, pull request, or review task and read its title,\n   description, acceptance criteria, comments, linked issues, and linked PRs.\n2. Inspect the current architecture documentation before changing code or\n   judging a review. Read the affected arc42 chapter files, ADR index, existing\n   ADRs, quality goals, quality scenarios, risks, building blocks, runtime\n   scenarios, deployment views, and relevant source files.\n3. Classify each feature request before creating or updating backlog issues. If\n   the request is broad enough to coordinate multiple user stories or slices,\n   create or update an Epic. If it is small enough for one reviewable slice,\n   create or update a UserStory. If the size is unclear and the decision affects\n   issue structure, ask a short clarifying question before creating the issue.\n4. Mark Epics and UserStories in the remote project backlog following the type\n   and label taxonomy in `..\u002Freferences\u002Fissue-labels.md`. Use the repository's\n   Epic or UserStory issue type, label, or metadata when available; otherwise\n   prefix the issue title with `[EPIC]` or `[UserStory]`.\n5. Start every Epic and UserStory description with the pattern\n   `As a [Role], I want to [Action], so that [Benefit].`\n6. Assign each UserStory to a matching Epic when one exists. Prefer real\n   sub-issues or parent-child issue relations when the repository supports them;\n   otherwise link the UserStory from the Epic and the Epic from the UserStory.\n7. Mark every requested refactoring in the remote project issue. Use the\n   repository's refactoring issue type, label, or metadata when available; if no\n   dedicated metadata exists, prefix the issue title with `[REFACTORING]`.\n8. For any change that adds or changes observable behaviour, specify that\n   behaviour with `..\u002Fbdd-specification\u002FSKILL.md`. This is the strict default and\n   covers new features, behavioural enhancements, and behaviour-changing bug\n   fixes. Capture the acceptance behaviour as a language-agnostic Gherkin\n   `.feature` spec as early as request or analysis time. The specification and\n   its scenario-to-test bridge are mandatory at the latest when the change is\n   implemented. Relax this only with an explicit human waiver, recorded with its\n   rationale in the issue, pull request, or Q&A document. Pure refactorings add\n   no behaviour and need no new scenarios, but must keep the existing specs and\n   their bridged tests passing.\n9. Record the feature or refactoring at every affected place in the\n   architecture documentation. Prefer a short `Affected Features` or\n   `Affected Refactorings` section or table with stable issue links, status,\n   and explicit `xref` links to related architecture artifacts.\n10. Explicitly mention affected existing ADRs, quality goals, quality scenarios,\n   risks, constraints, components, interfaces, runtime scenarios, and deployment\n   elements in the issue, implementation notes, review output, or architecture\n   changes.\n11. If the feature or refactoring conflicts with an accepted or proposed ADR,\n   quality goal, quality scenario, risk treatment, or constraint, stop treating\n   the conflict as an implementation detail. Use `..\u002Fadr\u002FSKILL.md` to draft a\n   new proposed ADR or update the affected decision trail.\n12. Document new or changed components, runtime scenarios, and deployment\n   changes with a matching PlantUML diagram plus a short textual description.\n   Use C4-PlantUML for building-block diagrams.\n13. Add diagrams to new ADRs when they help readers compare options. If the same\n   diagram or description is also included in the official arc42 structure,\n   author it once and include it with `include::...[tags=...]` instead of\n   copying it.\n14. Add or update quality scenarios and risks only when existing artifacts do\n   not already cover the feature impact. Use `..\u002Fquality-scenario\u002FSKILL.md` and\n   `..\u002Frisk\u002FSKILL.md` for those artifacts.\n15. Run the relevant validators, generators, render checks, tests, or manual\n    checks. Report any unavailable verification and remaining open human\n    decisions.\n16. Before the work is treated as complete, run `..\u002Fconvergence-check\u002FSKILL.md`.\n    Impact analysis establishes what the change touches; the gate asks whether\n    the request, the specification, the architecture record, the implementation\n    and the delivery metadata still agree afterwards.\n\n## Required Reading\n\nRead these files when the feature or review touches the corresponding scope:\n\n- `..\u002F..\u002Fgeneral-semantic-contracts.md` for architecture documentation,\n  Docs-as-Code, metadata, traceability, quality, risks, backlog management, and\n  review rules.\n- `..\u002F..\u002FAGENTS.md` for automated-contributor rules.\n- `..\u002Fbdd-specification\u002FSKILL.md` by default for any new or changed observable\n  behaviour, to specify it as Gherkin and bridge it into tests.\n- `..\u002Fadr\u002FSKILL.md` before creating or changing ADRs, or when a feature\n  conflicts with an existing decision.\n- `..\u002Fquality-scenario\u002FSKILL.md` before creating or changing quality scenarios.\n- `..\u002Frisk\u002FSKILL.md` before creating or changing risks.\n- `..\u002Ftraceability-review\u002FSKILL.md` before changing relation metadata or\n  reviewing traceability.\n- `..\u002Fslice-issues\u002FSKILL.md` when the Epic or UserStory needs child issues or\n  reviewable implementation slices.\n- `..\u002Fimplement-issue-workflow\u002FSKILL.md` when continuing from feature analysis\n  into implementation.\n- `..\u002Fpr-review\u002FSKILL.md` when the task is a pull request or review task.\n\n## Backlog Issue Rules\n\n- Treat an Epic as the coordination artifact for a feature that is too large for\n  one reviewable slice or naturally contains multiple UserStories.\n- Treat a UserStory as a reviewable slice of user value that can fit into one\n  focused implementation flow.\n- Prefer real Epic and UserStory issue types, labels, or metadata if the remote\n  repository supports them.\n- If no Epic metadata is available, prefix the Epic issue title with `[EPIC]`.\n- If no UserStory metadata is available, prefix the UserStory issue title with\n  `[UserStory]`.\n- Start every Epic and UserStory description with\n  `As a [Role], I want to [Action], so that [Benefit].`\n- Assign a UserStory to an existing matching Epic when one exists. Prefer a real\n  GitHub sub-issue or parent-child relation; use linked issue references only\n  when sub-issues are unavailable.\n- Keep child issues small and independently reviewable. Create sub-issues as\n  real sub-issues for Epics and UserStories when the repository allows it.\n- Do not create duplicate Epics or UserStories. Search open and recently closed\n  issues before creating a new one.\n\n## Refactoring Issue Rules\n\n- Treat refactoring as intentional structural work, not incidental cleanup.\n- Prefer a real refactoring issue type, label, or metadata field if the remote\n  repository supports it.\n- If no refactoring metadata is available, prefix the issue title with\n  `[REFACTORING]`.\n- Keep refactoring issues separate from behavioral feature changes unless a\n  human explicitly accepts a combined scope.\n- Link affected components, ADRs, risks, quality scenarios, tests, and follow-up\n  issues from the refactoring issue.\n\n## Documentation Rules\n\n- Use reviewed repository source files as the source of truth; conversational\n  context and generated prose are advisory until reviewed and committed.\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- Preserve stable IDs and accepted statuses. Mark AI-created or AI-modified\n  architecture content as draft or proposed unless human acceptance is already\n  recorded.\n- Add feature or refactoring references where the work affects the\n  documentation, not only in a central index. A component affected by a feature\n  or refactoring should name that issue near the component description or in an\n  `Affected Features` or `Affected Refactorings` section.\n- Use explicit AsciiDoc anchors and `xref` links for visible references.\n- Do not manually maintain generated include lists. Regenerate derived include\n  fragments when the repository provides a generator.\n- Keep reusable source content in one reviewed source location and include it\n  elsewhere. Use tagged includes for shared descriptions and diagrams:\n\n  ```asciidoc\n  \u002F\u002F tag::feature-auth-runtime[]\n  [plantuml,feature-auth-runtime,svg]\n  ----\n  @startuml\n  ' diagram body\n  @enduml\n  ----\n  \u002F\u002F end::feature-auth-runtime[]\n  ```\n\n  ```asciidoc\n  include::..\u002F06-runtime-view\u002Fdoc-06004-authentication.adoc[tags=feature-auth-runtime]\n  ```\n\n## Review Checklist\n\n- Does the feature, refactoring, or PR change an architecture-significant\n  behavior, boundary, dependency, interface, deployment concern, quality\n  attribute, risk, or operational workflow?\n- Is each Epic, UserStory, or refactoring issue marked with the repository's\n  native metadata, or with `[EPIC]`, `[UserStory]`, or `[REFACTORING]` in the\n  issue title when no metadata exists?\n- Does every Epic and UserStory begin with\n  `As a [Role], I want to [Action], so that [Benefit].`?\n- Is each UserStory assigned to a matching Epic when one exists?\n- Does every behaviour-adding or behaviour-changing change have a Gherkin\n  `.feature` specification bridged to tests per `..\u002Fbdd-specification\u002FSKILL.md`,\n  or an explicitly recorded human waiver?\n- Are affected ADRs and quality goals explicitly named?\n- Is there a conflict that requires a new or changed ADR?\n- Are all affected architecture locations updated with feature references?\n- Are new components, runtime scenarios, and deployment changes documented with\n  PlantUML diagrams and short text?\n- Are shared diagrams and descriptions included by tag instead of copied?\n- Do the Epic and UserStory links cover implementation, documentation, ADRs,\n  risks, quality scenarios, PRs, and real sub-issues where supported?\n- Are validators, generators, tests, and render checks run or explicitly noted\n  as not run?\n- Does the change carry a Convergence Check result, with every finding given a\n  disposition and every blocker its kind, per `..\u002Fconvergence-check\u002FSKILL.md`?\n","# Architecture Impact\n\n## Overview\n\nKeep feature work, refactorings, reviews, and architecture knowledge\nsynchronized. A feature request or refactoring task is not complete until the\nrelevant implementation, issue tracking, and architecture documentation tell the\nsame story.\n\nApply the repository contract hierarchy: this skill narrows `AGENTS.md`, and\n`AGENTS.md` adapts `general-semantic-contracts.md`. Do not duplicate general\narc42, metadata, anchor, Docs-as-Code, or traceability rules here.\n\nThis skill intentionally repeats a few backlog and issue-marking rules from\n`general-semantic-contracts.md` because they are operationally important while\nhandling feature and review work. Keep the general contract as the long-term\nsource of truth when these rules evolve.\n\n## Core Workflow\n\n1. Identify the feature request, Epic issue, UserStory issue, refactoring task,\n   implementation issue, pull request, or review task and read its title,\n   description, acceptance criteria, comments, linked issues, and linked PRs.\n2. Inspect the current architecture documentation before changing code or\n   judging a review. Read the affected arc42 chapter files, ADR index, existing\n   ADRs, quality goals, quality scenarios, risks, building blocks, runtime\n   scenarios, deployment views, and relevant source files.\n3. Classify each feature request before creating or updating backlog issues. If\n   the request is broad enough to coordinate multiple user stories or slices,\n   create or update an Epic. If it is small enough for one reviewable slice,\n   create or update a UserStory. If the size is unclear and the decision affects\n   issue structure, ask a short clarifying question before creating the issue.\n4. Mark Epics and UserStories in the remote project backlog following the type\n   and label taxonomy in `..\u002Freferences\u002Fissue-labels.md`. Use the repository's\n   Epic or UserStory issue type, label, or metadata when available; otherwise\n   prefix the issue title with `[EPIC]` or `[UserStory]`.\n5. Start every Epic and UserStory description with the pattern\n   `As a [Role], I want to [Action], so that [Benefit].`\n6. Assign each UserStory to a matching Epic when one exists. Prefer real\n   sub-issues or parent-child issue relations when the repository supports them;\n   otherwise link the UserStory from the Epic and the Epic from the UserStory.\n7. Mark every requested refactoring in the remote project issue. Use the\n   repository's refactoring issue type, label, or metadata when available; if no\n   dedicated metadata exists, prefix the issue title with `[REFACTORING]`.\n8. For any change that adds or changes observable behaviour, specify that\n   behaviour with `..\u002Fbdd-specification\u002FSKILL.md`. This is the strict default and\n   covers new features, behavioural enhancements, and behaviour-changing bug\n   fixes. Capture the acceptance behaviour as a language-agnostic Gherkin\n   `.feature` spec as early as request or analysis time. The specification and\n   its scenario-to-test bridge are mandatory at the latest when the change is\n   implemented. Relax this only with an explicit human waiver, recorded with its\n   rationale in the issue, pull request, or Q&A document. Pure refactorings add\n   no behaviour and need no new scenarios, but must keep the existing specs and\n   their bridged tests passing.\n9. Record the feature or refactoring at every affected place in the\n   architecture documentation. Prefer a short `Affected Features` or\n   `Affected Refactorings` section or table with stable issue links, status,\n   and explicit `xref` links to related architecture artifacts.\n10. Explicitly mention affected existing ADRs, quality goals, quality scenarios,\n   risks, constraints, components, interfaces, runtime scenarios, and deployment\n   elements in the issue, implementation notes, review output, or architecture\n   changes.\n11. If the feature or refactoring conflicts with an accepted or proposed ADR,\n   quality goal, quality scenario, risk treatment, or constraint, stop treating\n   the conflict as an implementation detail. Use `..\u002Fadr\u002FSKILL.md` to draft a\n   new proposed ADR or update the affected decision trail.\n12. Document new or changed components, runtime scenarios, and deployment\n   changes with a matching PlantUML diagram plus a short textual description.\n   Use C4-PlantUML for building-block diagrams.\n13. Add diagrams to new ADRs when they help readers compare options. If the same\n   diagram or description is also included in the official arc42 structure,\n   author it once and include it with `include::...[tags=...]` instead of\n   copying it.\n14. Add or update quality scenarios and risks only when existing artifacts do\n   not already cover the feature impact. Use `..\u002Fquality-scenario\u002FSKILL.md` and\n   `..\u002Frisk\u002FSKILL.md` for those artifacts.\n15. Run the relevant validators, generators, render checks, tests, or manual\n    checks. Report any unavailable verification and remaining open human\n    decisions.\n16. Before the work is treated as complete, run `..\u002Fconvergence-check\u002FSKILL.md`.\n    Impact analysis establishes what the change touches; the gate asks whether\n    the request, the specification, the architecture record, the implementation\n    and the delivery metadata still agree afterwards.\n\n## Required Reading\n\nRead these files when the feature or review touches the corresponding scope:\n\n- `..\u002F..\u002Fgeneral-semantic-contracts.md` for architecture documentation,\n  Docs-as-Code, metadata, traceability, quality, risks, backlog management, and\n  review rules.\n- `..\u002F..\u002FAGENTS.md` for automated-contributor rules.\n- `..\u002Fbdd-specification\u002FSKILL.md` by default for any new or changed observable\n  behaviour, to specify it as Gherkin and bridge it into tests.\n- `..\u002Fadr\u002FSKILL.md` before creating or changing ADRs, or when a feature\n  conflicts with an existing decision.\n- `..\u002Fquality-scenario\u002FSKILL.md` before creating or changing quality scenarios.\n- `..\u002Frisk\u002FSKILL.md` before creating or changing risks.\n- `..\u002Ftraceability-review\u002FSKILL.md` before changing relation metadata or\n  reviewing traceability.\n- `..\u002Fslice-issues\u002FSKILL.md` when the Epic or UserStory needs child issues or\n  reviewable implementation slices.\n- `..\u002Fimplement-issue-workflow\u002FSKILL.md` when continuing from feature analysis\n  into implementation.\n- `..\u002Fpr-review\u002FSKILL.md` when the task is a pull request or review task.\n\n## Backlog Issue Rules\n\n- Treat an Epic as the coordination artifact for a feature that is too large for\n  one reviewable slice or naturally contains multiple UserStories.\n- Treat a UserStory as a reviewable slice of user value that can fit into one\n  focused implementation flow.\n- Prefer real Epic and UserStory issue types, labels, or metadata if the remote\n  repository supports them.\n- If no Epic metadata is available, prefix the Epic issue title with `[EPIC]`.\n- If no UserStory metadata is available, prefix the UserStory issue title with\n  `[UserStory]`.\n- Start every Epic and UserStory description with\n  `As a [Role], I want to [Action], so that [Benefit].`\n- Assign a UserStory to an existing matching Epic when one exists. Prefer a real\n  GitHub sub-issue or parent-child relation; use linked issue references only\n  when sub-issues are unavailable.\n- Keep child issues small and independently reviewable. Create sub-issues as\n  real sub-issues for Epics and UserStories when the repository allows it.\n- Do not create duplicate Epics or UserStories. Search open and recently closed\n  issues before creating a new one.\n\n## Refactoring Issue Rules\n\n- Treat refactoring as intentional structural work, not incidental cleanup.\n- Prefer a real refactoring issue type, label, or metadata field if the remote\n  repository supports it.\n- If no refactoring metadata is available, prefix the issue title with\n  `[REFACTORING]`.\n- Keep refactoring issues separate from behavioral feature changes unless a\n  human explicitly accepts a combined scope.\n- Link affected components, ADRs, risks, quality scenarios, tests, and follow-up\n  issues from the refactoring issue.\n\n## Documentation Rules\n\n- Use reviewed repository source files as the source of truth; conversational\n  context and generated prose are advisory until reviewed and committed.\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- Preserve stable IDs and accepted statuses. Mark AI-created or AI-modified\n  architecture content as draft or proposed unless human acceptance is already\n  recorded.\n- Add feature or refactoring references where the work affects the\n  documentation, not only in a central index. A component affected by a feature\n  or refactoring should name that issue near the component description or in an\n  `Affected Features` or `Affected Refactorings` section.\n- Use explicit AsciiDoc anchors and `xref` links for visible references.\n- Do not manually maintain generated include lists. Regenerate derived include\n  fragments when the repository provides a generator.\n- Keep reusable source content in one reviewed source location and include it\n  elsewhere. Use tagged includes for shared descriptions and diagrams:\n\n  ```asciidoc\n  \u002F\u002F tag::feature-auth-runtime[]\n  [plantuml,feature-auth-runtime,svg]\n  ----\n  @startuml\n  ' diagram body\n  @enduml\n  ----\n  \u002F\u002F end::feature-auth-runtime[]\n  ```\n\n  ```asciidoc\n  include::..\u002F06-runtime-view\u002Fdoc-06004-authentication.adoc[tags=feature-auth-runtime]\n  ```\n\n## Review Checklist\n\n- Does the feature, refactoring, or PR change an architecture-significant\n  behavior, boundary, dependency, interface, deployment concern, quality\n  attribute, risk, or operational workflow?\n- Is each Epic, UserStory, or refactoring issue marked with the repository's\n  native metadata, or with `[EPIC]`, `[UserStory]`, or `[REFACTORING]` in the\n  issue title when no metadata exists?\n- Does every Epic and UserStory begin with\n  `As a [Role], I want to [Action], so that [Benefit].`?\n- Is each UserStory assigned to a matching Epic when one exists?\n- Does every behaviour-adding or behaviour-changing change have a Gherkin\n  `.feature` specification bridged to tests per `..\u002Fbdd-specification\u002FSKILL.md`,\n  or an explicitly recorded human waiver?\n- Are affected ADRs and quality goals explicitly named?\n- Is there a conflict that requires a new or changed ADR?\n- Are all affected architecture locations updated with feature references?\n- Are new components, runtime scenarios, and deployment changes documented with\n  PlantUML diagrams and short text?\n- Are shared diagrams and descriptions included by tag instead of copied?\n- Do the Epic and UserStory links cover implementation, documentation, ADRs,\n  risks, quality scenarios, PRs, and real sub-issues where supported?\n- Are validators, generators, tests, and render checks run or explicitly noted\n  as not run?\n- Does the change carry a Convergence Check result, with every finding given a\n  disposition and every blocker its kind, per `..\u002Fconvergence-check\u002FSKILL.md`?\n",{"name":5,"description":7},"main","209607df178aba11b58f76b19e45d58af0d44f52","skills\u002Farchitecture-impact",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 architecture-impact",{"tool":36,"command":37},"bunx","bunx skills add docs-as-code-toolkit\u002Farchitecture-knowledge-toolkit --skill architecture-impact",{"tool":39,"command":40},"pnpm","pnpm dlx skills add docs-as-code-toolkit\u002Farchitecture-knowledge-toolkit --skill architecture-impact","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Farchitecture-impact\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},"01M77S3RY6VQPBNM5JA06GWSCF","traceability-review","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.","https:\u002F\u002Fgithub.com\u002Fdocs-as-code-toolkit\u002Farchitecture-knowledge-toolkit\u002Fblob\u002Fmain\u002Fskills\u002Ftraceability-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},"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":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},"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":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},"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":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},"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":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},"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",[],[]]