[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PJ4N6YHMZR6CGT9ES29NXT":3,"skill-same:01M6PJ4N6YHMZR6CGT9ES29NXT":69},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6PJ4N6YHMZR6CGT9ES29NXT","comparison-base",null,"Internal reusable workflow for resolving the correct Git comparison base for branch reviews and change analysis. Finds the PR target or canonical Fluid Framework upstream, selects the newest shared target-history commit, and detects substantial divergence.","microsoft\u002FFluidFramework","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AG0BQKNGBJQ5YNG09HXXW",4949,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcomparison-base\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"comparison","comparison base","base","correct","for","reviews","shared","upstream","reusable","branch","history","review","analysis","git","pr","fluid framework","fluid","commit","change","workflow","2026-11-10 10:12:30",false,"---\nname: comparison-base\ndescription: Internal reusable workflow for resolving the correct Git comparison base for branch reviews and change analysis. Finds the PR target or canonical Fluid Framework upstream, selects the newest shared target-history commit, and detects substantial divergence.\nlicense: MIT\nargument-hint: \"[review-ref]\"\n---\n\n# Comparison Base Resolution\n\nUse this skill when another workflow needs to compare a branch or working tree with the branch it is intended to merge into. This skill resolves the comparison refs and commit; the caller decides what paths and endpoint to diff.\n\n## Inputs\n\n- `$REVIEW_REF`: the commit being reviewed. Default to `HEAD`.\n\nSet `$IS_LOCAL_REVIEW=true` when the input is `HEAD`, or when a named local branch is the currently checked-out branch; otherwise set it to `false`. Callers use this explicit value to decide whether workspace changes belong to the review.\n\nFor `HEAD` or a named review branch, record `$REVIEW_BRANCH` when the ref identifies a local branch. Resolve its published destination using Git's push precedence: `branch.\u003Cname>.pushRemote`, then `remote.pushDefault`, then the branch's configured upstream remote. Store the remote name or URL usable by Git as `$REVIEW_FETCH_SOURCE`, normalize that remote's GitHub URL to `owner\u002Frepository` as `$REVIEW_REPOSITORY`, and store the remote branch name as `$REVIEW_HEAD_BRANCH`. Keep these values distinct: Git commands consume `$REVIEW_FETCH_SOURCE`, while GitHub PR metadata uses `$REVIEW_REPOSITORY`. The published branch may have a different name from the local branch. Without any configured destination, inspect configured remotes for an exact `$REVIEW_BRANCH` match and derive all three values; ask the user if multiple remotes match. A detached `HEAD`, commit input, or unpublished local branch may leave the published identity unset.\n\nFor a named review branch, prefer an exact local branch and set `REVIEW_REF=refs\u002Fheads\u002F$REVIEW_BRANCH`. If there is no local branch and exactly one remote matches, set `$REVIEW_FETCH_SOURCE` to that remote, derive `$REVIEW_REPOSITORY` from its URL, set `$REVIEW_HEAD_BRANCH=$REVIEW_BRANCH`, fetch the branch into a dedicated ref, and use that ref as `$REVIEW_REF`:\n\n```bash\ngit fetch --no-tags \"$REVIEW_FETCH_SOURCE\" \"+refs\u002Fheads\u002F$REVIEW_BRANCH:refs\u002Fcomparison\u002Fhead\"\nREVIEW_REF=refs\u002Fcomparison\u002Fhead\n```\n\nIf the branch is absent, ask the user for another review ref. If it exists on multiple remotes and has no configured upstream or push remote, ask the user which remote to assign to `$REVIEW_FETCH_SOURCE`, derive `$REVIEW_REPOSITORY`, then fetch it as shown above. Finally, set `$REVIEW_OID`:\n\n```bash\nREVIEW_OID=$(git rev-parse \"$REVIEW_REF\")\n```\n\n## Step 1: Resolve the target branch\n\nResolve an open PR using the following sources in order, stopping as soon as one source produces exactly one validated match. Do not query later sources after a match is resolved.\n\n1. Prefer active PR metadata already available from the editor's PR integration. Verify its head repository and branch match `$REVIEW_REPOSITORY` and `$REVIEW_HEAD_BRANCH` when those values are known. Its published head must also match `$REVIEW_OID` or be an ancestor of a locally-ahead `$REVIEW_REF`.\n2. If no match was resolved and `$REVIEW_REPOSITORY` and `$REVIEW_HEAD_BRANCH` are known, query open PRs by branch. `gh pr list --repo \u003Ccandidate-base-repository> --state open --head \"$REVIEW_HEAD_BRANCH\" --json url,state,baseRefName,headRefName,headRefOid,headRepository` is convenient; query GitHub repositories named by configured remotes, including `microsoft\u002FFluidFramework`, one at a time and stop after a validated match. Validate `headRepository.nameWithOwner` against `$REVIEW_REPOSITORY`. This branch query lets a locally-ahead commit resolve its published PR.\n3. If still unresolved, query the GitHub commit-to-PR API (`repos\u002F{owner}\u002F{repo}\u002Fcommits\u002F$REVIEW_OID\u002Fpulls`) for the same candidate repositories, one at a time, and stop after a validated match. Treat HTTP 404 or 422 as no candidates and continue; locally-ahead or unpublished commits may not exist in the queried repository.\n\nFrom any source, read the PR state and URL, base repository and branch, and head repository, branch, and SHA. Only accept open PRs whose head repository and branch match the known review identity and whose head SHA matches `$REVIEW_OID` or is its ancestor.\n\nDo not rely on bare `gh pr view`, bare `gh repo view`, or an unqualified repository context. These are ambiguous in fork checkouts; pass an explicit PR URL or `--repo owner\u002Frepository`. If multiple open PRs match, ask the user which PR to use.\n\nFor a matching PR, set:\n\n- `$TARGET_SOURCE` to its base repository clone URL\n- `$TARGET_REPOSITORY` to its normalized `owner\u002Frepository` name\n- `$TARGET_BRANCH` to its base branch\n- `$PR_URL` to its HTML URL\n\nIf no PR exists, inspect fetch remotes and select one whose normalized URL points to `https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework` (accept SSH or HTTPS and an optional `.git` suffix). Set `$TARGET_SOURCE` to that remote, `$TARGET_REPOSITORY` to `microsoft\u002FFluidFramework`, and `$TARGET_BRANCH` to `main`. If no such remote exists, use `https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework.git` directly as `$TARGET_SOURCE` and set the other values the same way.\n\nFetch the target branch into a dedicated ref so stale or unrelated tracking branches cannot affect the result:\n\n```bash\ngit fetch --no-tags \"$TARGET_SOURCE\" \"+refs\u002Fheads\u002F$TARGET_BRANCH:refs\u002Fcomparison\u002Ftarget\"\nTARGET_REF=refs\u002Fcomparison\u002Ftarget\n```\n\n## Step 2: Select the comparison commit\n\nFind all best common ancestors of the target and review refs. Fluid Framework squash-merges branches into `main`, so this normally produces exactly one commit. Use `--all` so Git reports criss-cross or other ambiguous histories instead of selecting an arbitrary best ancestor.\n\n```bash\nif BASE_COMMITS=$(git merge-base --all \"$TARGET_REF\" \"$REVIEW_REF\"); then\n  BASE_STATUS=0\nelse\n  BASE_STATUS=$?\nfi\n```\n\nIf `$BASE_STATUS` is nonzero, report the Git failure. If `$BASE_COMMITS` is empty, check `git rev-parse --is-shallow-repository`. For a shallow repository, deepen the target and review histories from their respective fetch sources and retry; unshallow when practical. Only ask the user for a comparison commit after the repository is confirmed complete or deepening cannot recover the shared history.\n\nIf exactly one commit was returned, set `$BASE_COMMIT` to it. If multiple commits were returned, show each commit's short SHA, date, and subject, explain that Git found multiple equally good common ancestors, and ask the user which one to use.\n\nVerify `$BASE_COMMIT` is non-empty and is an ancestor of both `$TARGET_REF` and `$REVIEW_REF` before continuing.\n\n## Step 3: Check divergence\n\nCount all commits reachable from each tip after the selected comparison commit:\n\n```bash\nREVIEW_COMMITS=$(git rev-list --count \"$BASE_COMMIT..$REVIEW_REF\")\nTARGET_COMMITS=$(git rev-list --count \"$BASE_COMMIT..$TARGET_REF\")\n```\n\nRecord the comparison commit's short SHA, date, and subject; both tip dates; and the elapsed time from the comparison commit to each tip.\n\nIf either count is greater than 50, stop before the caller reads diffs. Warn that the histories have substantial divergence and show:\n\n- selected target repository and branch\n- selected comparison commit (short SHA, date, and subject)\n- review side: commit count, tip date, and elapsed time since the comparison commit\n- target side: commit count, tip date, and elapsed time since the comparison commit\n\nAsk whether to continue with these values, choose another target branch, or choose another comparison commit. When `$TARGET_COMMITS` is nonzero, also offer to merge the target branch into the review branch first. Explain that merging can reduce target-side divergence but modifies the review branch; never perform it without explicit approval.\n\n## Outputs\n\nReturn these values to the caller:\n\n- `$REVIEW_REF`, `$REVIEW_OID`, and `$IS_LOCAL_REVIEW`\n- `$REVIEW_FETCH_SOURCE`, `$REVIEW_REPOSITORY`, and `$REVIEW_HEAD_BRANCH`, when a published review identity was resolved\n- `$TARGET_SOURCE`, `$TARGET_REPOSITORY`, `$TARGET_BRANCH`, and `$TARGET_REF`\n- `$BASE_COMMIT`\n- `$REVIEW_COMMITS` and `$TARGET_COMMITS`\n- `$PR_URL`, if a PR was found\n- recorded commit and elapsed-time metadata\n\nThe caller must use the exact selected `$BASE_COMMIT`; it must not later replace it with a three-dot diff or recompute a merge-base.\n\n## Edge Cases\n\n- Ambiguous PR or named branch: ask the user which one to use.\n- Multiple best common ancestors: show them and ask the user which one to use.\n- Empty base in a shallow repository: deepen both relevant histories and retry before treating them as unrelated.\n- No shared target-history commit: ask the user for a comparison commit.\n- More than 50 commits on either side: present divergence and ask before proceeding.\n","# Comparison Base Resolution\n\nUse this skill when another workflow needs to compare a branch or working tree with the branch it is intended to merge into. This skill resolves the comparison refs and commit; the caller decides what paths and endpoint to diff.\n\n## Inputs\n\n- `$REVIEW_REF`: the commit being reviewed. Default to `HEAD`.\n\nSet `$IS_LOCAL_REVIEW=true` when the input is `HEAD`, or when a named local branch is the currently checked-out branch; otherwise set it to `false`. Callers use this explicit value to decide whether workspace changes belong to the review.\n\nFor `HEAD` or a named review branch, record `$REVIEW_BRANCH` when the ref identifies a local branch. Resolve its published destination using Git's push precedence: `branch.\u003Cname>.pushRemote`, then `remote.pushDefault`, then the branch's configured upstream remote. Store the remote name or URL usable by Git as `$REVIEW_FETCH_SOURCE`, normalize that remote's GitHub URL to `owner\u002Frepository` as `$REVIEW_REPOSITORY`, and store the remote branch name as `$REVIEW_HEAD_BRANCH`. Keep these values distinct: Git commands consume `$REVIEW_FETCH_SOURCE`, while GitHub PR metadata uses `$REVIEW_REPOSITORY`. The published branch may have a different name from the local branch. Without any configured destination, inspect configured remotes for an exact `$REVIEW_BRANCH` match and derive all three values; ask the user if multiple remotes match. A detached `HEAD`, commit input, or unpublished local branch may leave the published identity unset.\n\nFor a named review branch, prefer an exact local branch and set `REVIEW_REF=refs\u002Fheads\u002F$REVIEW_BRANCH`. If there is no local branch and exactly one remote matches, set `$REVIEW_FETCH_SOURCE` to that remote, derive `$REVIEW_REPOSITORY` from its URL, set `$REVIEW_HEAD_BRANCH=$REVIEW_BRANCH`, fetch the branch into a dedicated ref, and use that ref as `$REVIEW_REF`:\n\n```bash\ngit fetch --no-tags \"$REVIEW_FETCH_SOURCE\" \"+refs\u002Fheads\u002F$REVIEW_BRANCH:refs\u002Fcomparison\u002Fhead\"\nREVIEW_REF=refs\u002Fcomparison\u002Fhead\n```\n\nIf the branch is absent, ask the user for another review ref. If it exists on multiple remotes and has no configured upstream or push remote, ask the user which remote to assign to `$REVIEW_FETCH_SOURCE`, derive `$REVIEW_REPOSITORY`, then fetch it as shown above. Finally, set `$REVIEW_OID`:\n\n```bash\nREVIEW_OID=$(git rev-parse \"$REVIEW_REF\")\n```\n\n## Step 1: Resolve the target branch\n\nResolve an open PR using the following sources in order, stopping as soon as one source produces exactly one validated match. Do not query later sources after a match is resolved.\n\n1. Prefer active PR metadata already available from the editor's PR integration. Verify its head repository and branch match `$REVIEW_REPOSITORY` and `$REVIEW_HEAD_BRANCH` when those values are known. Its published head must also match `$REVIEW_OID` or be an ancestor of a locally-ahead `$REVIEW_REF`.\n2. If no match was resolved and `$REVIEW_REPOSITORY` and `$REVIEW_HEAD_BRANCH` are known, query open PRs by branch. `gh pr list --repo \u003Ccandidate-base-repository> --state open --head \"$REVIEW_HEAD_BRANCH\" --json url,state,baseRefName,headRefName,headRefOid,headRepository` is convenient; query GitHub repositories named by configured remotes, including `microsoft\u002FFluidFramework`, one at a time and stop after a validated match. Validate `headRepository.nameWithOwner` against `$REVIEW_REPOSITORY`. This branch query lets a locally-ahead commit resolve its published PR.\n3. If still unresolved, query the GitHub commit-to-PR API (`repos\u002F{owner}\u002F{repo}\u002Fcommits\u002F$REVIEW_OID\u002Fpulls`) for the same candidate repositories, one at a time, and stop after a validated match. Treat HTTP 404 or 422 as no candidates and continue; locally-ahead or unpublished commits may not exist in the queried repository.\n\nFrom any source, read the PR state and URL, base repository and branch, and head repository, branch, and SHA. Only accept open PRs whose head repository and branch match the known review identity and whose head SHA matches `$REVIEW_OID` or is its ancestor.\n\nDo not rely on bare `gh pr view`, bare `gh repo view`, or an unqualified repository context. These are ambiguous in fork checkouts; pass an explicit PR URL or `--repo owner\u002Frepository`. If multiple open PRs match, ask the user which PR to use.\n\nFor a matching PR, set:\n\n- `$TARGET_SOURCE` to its base repository clone URL\n- `$TARGET_REPOSITORY` to its normalized `owner\u002Frepository` name\n- `$TARGET_BRANCH` to its base branch\n- `$PR_URL` to its HTML URL\n\nIf no PR exists, inspect fetch remotes and select one whose normalized URL points to `https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework` (accept SSH or HTTPS and an optional `.git` suffix). Set `$TARGET_SOURCE` to that remote, `$TARGET_REPOSITORY` to `microsoft\u002FFluidFramework`, and `$TARGET_BRANCH` to `main`. If no such remote exists, use `https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework.git` directly as `$TARGET_SOURCE` and set the other values the same way.\n\nFetch the target branch into a dedicated ref so stale or unrelated tracking branches cannot affect the result:\n\n```bash\ngit fetch --no-tags \"$TARGET_SOURCE\" \"+refs\u002Fheads\u002F$TARGET_BRANCH:refs\u002Fcomparison\u002Ftarget\"\nTARGET_REF=refs\u002Fcomparison\u002Ftarget\n```\n\n## Step 2: Select the comparison commit\n\nFind all best common ancestors of the target and review refs. Fluid Framework squash-merges branches into `main`, so this normally produces exactly one commit. Use `--all` so Git reports criss-cross or other ambiguous histories instead of selecting an arbitrary best ancestor.\n\n```bash\nif BASE_COMMITS=$(git merge-base --all \"$TARGET_REF\" \"$REVIEW_REF\"); then\n  BASE_STATUS=0\nelse\n  BASE_STATUS=$?\nfi\n```\n\nIf `$BASE_STATUS` is nonzero, report the Git failure. If `$BASE_COMMITS` is empty, check `git rev-parse --is-shallow-repository`. For a shallow repository, deepen the target and review histories from their respective fetch sources and retry; unshallow when practical. Only ask the user for a comparison commit after the repository is confirmed complete or deepening cannot recover the shared history.\n\nIf exactly one commit was returned, set `$BASE_COMMIT` to it. If multiple commits were returned, show each commit's short SHA, date, and subject, explain that Git found multiple equally good common ancestors, and ask the user which one to use.\n\nVerify `$BASE_COMMIT` is non-empty and is an ancestor of both `$TARGET_REF` and `$REVIEW_REF` before continuing.\n\n## Step 3: Check divergence\n\nCount all commits reachable from each tip after the selected comparison commit:\n\n```bash\nREVIEW_COMMITS=$(git rev-list --count \"$BASE_COMMIT..$REVIEW_REF\")\nTARGET_COMMITS=$(git rev-list --count \"$BASE_COMMIT..$TARGET_REF\")\n```\n\nRecord the comparison commit's short SHA, date, and subject; both tip dates; and the elapsed time from the comparison commit to each tip.\n\nIf either count is greater than 50, stop before the caller reads diffs. Warn that the histories have substantial divergence and show:\n\n- selected target repository and branch\n- selected comparison commit (short SHA, date, and subject)\n- review side: commit count, tip date, and elapsed time since the comparison commit\n- target side: commit count, tip date, and elapsed time since the comparison commit\n\nAsk whether to continue with these values, choose another target branch, or choose another comparison commit. When `$TARGET_COMMITS` is nonzero, also offer to merge the target branch into the review branch first. Explain that merging can reduce target-side divergence but modifies the review branch; never perform it without explicit approval.\n\n## Outputs\n\nReturn these values to the caller:\n\n- `$REVIEW_REF`, `$REVIEW_OID`, and `$IS_LOCAL_REVIEW`\n- `$REVIEW_FETCH_SOURCE`, `$REVIEW_REPOSITORY`, and `$REVIEW_HEAD_BRANCH`, when a published review identity was resolved\n- `$TARGET_SOURCE`, `$TARGET_REPOSITORY`, `$TARGET_BRANCH`, and `$TARGET_REF`\n- `$BASE_COMMIT`\n- `$REVIEW_COMMITS` and `$TARGET_COMMITS`\n- `$PR_URL`, if a PR was found\n- recorded commit and elapsed-time metadata\n\nThe caller must use the exact selected `$BASE_COMMIT`; it must not later replace it with a three-dot diff or recompute a merge-base.\n\n## Edge Cases\n\n- Ambiguous PR or named branch: ask the user which one to use.\n- Multiple best common ancestors: show them and ask the user which one to use.\n- Empty base in a shallow repository: deepen both relevant histories and retry before treating them as unrelated.\n- No shared target-history commit: ask the user for a comparison commit.\n- More than 50 commits on either side: present divergence and ask before proceeding.\n",{"name":5,"license":15,"description":7,"argument-hint":44},"[review-ref]","main","8809386f7af487f40be7dcbea5d0e4afc37efd0a",".github\u002Fskills\u002Fcomparison-base",590,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework","https:\u002F\u002Ffluidframework.com","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 08:12:05",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add microsoft\u002FFluidFramework --skill comparison-base",{"tool":61,"command":62},"bunx","bunx skills add microsoft\u002FFluidFramework --skill comparison-base",{"tool":64,"command":65},"pnpm","pnpm dlx skills add microsoft\u002FFluidFramework --skill comparison-base","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcomparison-base\u002FSKILL.md",true,[],[70,91,125,149,167,190],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":39},"01M6PJ5SAHYFZFWDG5Y4RW56EP","trigger-pipelines-for-copilot-pr","Trigger ADO pipelines for a Copilot-created PR by posting \u002Fazp run comments. Use when the user asks to trigger CI pipelines for a specific PR.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ftrigger-pipelines-for-copilot-pr\u002FSKILL.md",[],[33,77,23,78,79,80,81,82,83,84,85,86,87,88,89,90],"trigger pipelines for copilot pr","trigger","copilot","pipelines","ado","posting","run","ci","use","number","URL","comments","user","when",{"skillNo":92,"name":30,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":109,"publishedAt":39},"01M6PJ5M4ZG7E78C4GM4041HEP","Review changes relative to a prior state, such as a diff, pull request, branch, commit, or working-tree changes. Use for change-focused code review and regression analysis. Do not use to assess an existing file, API, design, implementation, or other artifact without a comparison; if the request is ambiguous, ask whether the user wants a change review and what prior state to compare against.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Freview\u002FSKILL.md",[96,101,104],{"categoryNo":97,"categoryName":98,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":102,"categoryName":103,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[30,28,110,111,112,113,31,114,36,115,37,116,117,118,119,120,121,122,23,123,124],"regression","code review","design","ask","code","api","artifact","request","pull","tree","as","do","diff","assess","ambiguous",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":134,"publishedAt":39},"01M6PJ5E3PCBDS319FFMHPFACN","review-pr-local","The authority on pulling a pull request — Azure DevOps or GitHub — into an isolated local worktree so a human can review it in their editor, and on posting human-controlled review comments back to the PR (ADO via the ado PR-thread MCP tools or the Azure DevOps REST API, GitHub via the gh CLI). Auto-detects the platform and all identifiers from the PR URL; not tied to any specific repository. The AI assists an interactive human review and only ever posts comments the human explicitly requests. If you find yourself checking out a PR branch over the user's own working tree, or posting AI-authored review prose the human did not ask for, invoke this skill instead.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Freview-pr-local\u002FSKILL.md",[131],{"categoryNo":132,"categoryName":133,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000023","Skill与智能体开发",[135,30,33,136,137,138,28,139,140,141,142,143,144,145,87,146,113,115,147,148],"local","review pr local","review pr","back","posts","only","MCP","authority","auto","invoke","azure devops","you","cli","worktree",{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":153,"categories":154,"keywords":155,"publishedAt":39},"01M6PJ5AVZAS0AEBPCYJZ9ZMMD","policy-check","This skill should be used when the user asks to \"run policy check\", \"check policy\", \"policy-check\", or needs to validate package compliance. Provides guidance on running policy checks for specific packages or the entire repository.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpolicy-check\u002FSKILL.md",[],[156,157,158,159,160,23,83,161,162,163,164,89,165,90,166],"policy check","policy","check","packages","compliance","repository","guidance","validate","package","running","entire",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":176,"publishedAt":39},"01M6PJ54H068MZF2WD2JDKCVDC","pipeline-test-triage","Triage test failures in an Azure DevOps pipeline run for Fluid Framework. Use when the user shares an ADO build\u002Fpipeline URL or build ID and wants failures analyzed, when they ask \"why did this pipeline fail\", \"summarize the test failures\", \"is this test flaky or a real bug\", \"compare these runs\", or wants bugs filed for genuine failures. Covers the Real Service End to End Tests pipeline as the worked example but applies to any FF test pipeline.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpipeline-test-triage\u002FSKILL.md",[173],{"categoryNo":174,"categoryName":175,"taxonomyType":99,"taxonomyTypeDesc":100},"01JBSEEDCAT000000000000008","测试与质量",[177,178,179,180,181,182,183,184,145,87,113,83,185,186,187,188,81,120,189,23,90],"pipeline","test triage","pipeline test triage","pipeline test","test","triage","end","test pipeline","why","bug","but","framework","bugs",{"skillNo":191,"name":192,"nameZh":6,"description":193,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":194,"categories":195,"keywords":196,"publishedAt":39},"01M6PJ4ZJASDV2CGQTG1JWKBFE","fluid-release","Fluid Framework client release group — minor releases, patch releases, and post-release type test updates. Covers release prep, branching, version bumps, changelogs, release notes, and type test baselines. In autonomous mode, auto-detects state from the repo, attempts to execute, and falls back to a GitHub issue on failure. Triggers on \"release\", \"do the release\", \"release status\", version bump, release notes, changelog, release branch, or release engineering.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002FFluidFramework\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ffluid-release\u002FSKILL.md",[],[197,198,35,138,28,199,200,201,202,203,143,204,205,206,207,208,209,210,211,212],"release","fluid release","bump","mode","autonomous","release notes","release status","updates","patch","notes","changelog","release prep","releases","status","issue","branching"]