[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M759G8GARE7DFYKBTV43RPDG":3,"skill-same:01M759G8GARE7DFYKBTV43RPDG":45},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M759G8GARE7DFYKBTV43RPDG","review-changes",null,"Review the current branch diff for correctness, reuse and governance, then adversarially verify each finding and report only the ones that survive refutation. Use when asked to \"review my changes\", \"review this branch\", \"review the diff\", \"review trước khi push\", or before opening a PR — for an unlanded design document use spec-red-team instead.","baodq97\u002Fgovkit","baodq97","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F50482002?v=4","01M759BJ9XC68CW9PQCFK22H1X","Bao Do","01M759BJAY1W696G8A8N841875",0,"MIT","https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit\u002Fblob\u002Fmain\u002Fplugins\u002Fswe-flow\u002Fskills\u002Freview-changes\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: review-changes\ndescription: >-\n  Review the current branch diff for correctness, reuse and governance, then adversarially verify\n  each finding and report only the ones that survive refutation. Use when asked to \"review my\n  changes\", \"review this branch\", \"review the diff\", \"review trước khi push\", or before opening a\n  PR — for an unlanded design document use spec-red-team instead.\ncontext: fork\n---\n\n# \u002Freview-changes\n\nA thin front onto the `.claude\u002Fworkflows\u002Freview-changes.js` orchestration — the review->verify\npipeline that reviews the current branch diff across independent dimensions\n(`correctness`, `reuse`, `governance`), then adversarially verifies each finding, surfacing only\nthe issues that survive refutation. Invoke `review-changes.js` (pass your own `dimensions` via\nargs or take the default three); the pipeline has no barrier — a dimension's findings verify as\nsoon as that dimension's review completes. This wrapper reimplements none of that logic — the\n`.js` stays the single source of truth.\n\n## By-hand fallback — workflows are research-preview and globally disableable\n\nWorkflows are research-preview and globally disableable (`disableWorkflows` \u002F\n`CLAUDE_CODE_DISABLE_WORKFLOWS=1`) and cannot be bundled in a plugin (there is no `workflows`\nfield in `plugin.json`). If `review-changes.js` does not run, drive the SAME order BY HAND: for\neach dimension dispatch `swe-flow:reviewer` over the diff (inspect both the committed branch diff\nand any uncommitted\u002Funtracked changes — untracked files are NOT in `git diff`); for each finding,\ndispatch a second `swe-flow:reviewer` to refute it, defaulting to refuted when it cannot be\nreproduced; keep only the findings that survive. Nothing is lost — the govkit PreToolUse\u002FStop\nhook + CI `govkit verify` gate every governed doc regardless. The workflow is an accelerant, not\nthe source of truth.\n\nThis wrapper dispatches only the subagent `review-changes.js` already dispatches —\n`swe-flow:reviewer` (one per dimension for review, a second per finding for refutation). It\nintroduces no new agent type or skill. It only triages code review: it never flips a governed-doc\n`status:` and never assigns an owner (AGENTS.md § Agent constraints).\n","# \u002Freview-changes\n\nA thin front onto the `.claude\u002Fworkflows\u002Freview-changes.js` orchestration — the review->verify\npipeline that reviews the current branch diff across independent dimensions\n(`correctness`, `reuse`, `governance`), then adversarially verifies each finding, surfacing only\nthe issues that survive refutation. Invoke `review-changes.js` (pass your own `dimensions` via\nargs or take the default three); the pipeline has no barrier — a dimension's findings verify as\nsoon as that dimension's review completes. This wrapper reimplements none of that logic — the\n`.js` stays the single source of truth.\n\n## By-hand fallback — workflows are research-preview and globally disableable\n\nWorkflows are research-preview and globally disableable (`disableWorkflows` \u002F\n`CLAUDE_CODE_DISABLE_WORKFLOWS=1`) and cannot be bundled in a plugin (there is no `workflows`\nfield in `plugin.json`). If `review-changes.js` does not run, drive the SAME order BY HAND: for\neach dimension dispatch `swe-flow:reviewer` over the diff (inspect both the committed branch diff\nand any uncommitted\u002Funtracked changes — untracked files are NOT in `git diff`); for each finding,\ndispatch a second `swe-flow:reviewer` to refute it, defaulting to refuted when it cannot be\nreproduced; keep only the findings that survive. Nothing is lost — the govkit PreToolUse\u002FStop\nhook + CI `govkit verify` gate every governed doc regardless. The workflow is an accelerant, not\nthe source of truth.\n\nThis wrapper dispatches only the subagent `review-changes.js` already dispatches —\n`swe-flow:reviewer` (one per dimension for review, a second per finding for refutation). It\nintroduces no new agent type or skill. It only triages code review: it never flips a governed-doc\n`status:` and never assigns an owner (AGENTS.md § Agent constraints).\n",{"name":5,"context":24,"description":7},"fork","main","850634e254ea6a5034bf2eddad5fe95091713231","plugins\u002Fswe-flow\u002Fskills\u002Freview-changes","https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit","https:\u002F\u002Fgithub.com\u002Fbaodq97","2026-09-07 14:26:00",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add baodq97\u002Fgovkit --skill review-changes",{"tool":37,"command":38},"bunx","bunx skills add baodq97\u002Fgovkit --skill review-changes",{"tool":40,"command":41},"pnpm","pnpm dlx skills add baodq97\u002Fgovkit --skill review-changes","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit\u002Fblob\u002Fmain\u002Fplugins\u002Fswe-flow\u002Fskills\u002Freview-changes\u002FSKILL.md",true,[],[46,53,60,67,74,80],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M759HTCHQJVZ4JWDA2JNPJJZ","trigger-shaped","Use when the user says \"plan a sprint retro\"; drafts retro\u002Fnotes.md for the team.","https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fskill-lint\u002Ftriggering\u002Fskills\u002Ftrigger-shaped\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M759HS3E2T97ZN1ED2Z96WAJ","terse-unguarded","Step 2 — writes docs\u002Fx\u002Foutput.json quietly.","https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fskill-lint\u002Ftriggering\u002Fskills\u002Fterse-unguarded\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M759HPZN28VZHKYFR754CVXT","guarded","Summarizes ledger totals into reports\u002Fmonthly.csv.","https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fskill-lint\u002Ftriggering\u002Fskills\u002Fguarded\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M759HMFQAZAWFVSS3KWPCCW0","open","Draft a spec. Use when asked to \"draft a spec\" or \"write the RFC\".","https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fskill-lint\u002Fdead-hint\u002Fskills\u002Fopen\u002FSKILL.md",[],[],{"skillNo":75,"name":62,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M759HJ3XX74S70PW9AR8NS66","Deploy the thing.","https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit\u002Fblob\u002Fmain\u002Fscripts\u002Ffixtures\u002Fskill-lint\u002Fdead-hint\u002Fskills\u002Fguarded\u002FSKILL.md",[],[],{"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":19},"01M759HCWJN9ACRNC1JW76DR1E","working-discipline","Thinking-checkpoint discipline for substantive implementation, debugging, or autonomous work — 21 trigger-gated items (trigger → mandatory question → evidence to produce) that cut agent error and human escalation. Use before an autonomous or long-running run, when asked to \"work carefully\", \"double-check\", \"làm cẩn thận\", \"reduce errors\", \"be more autonomous\", or after looping twice on the same failing fix. NOT a procedure — checkpoints fire on their triggers and demand evidence, with an N\u002FA escape valve so a strong model pays near-zero overhead.","https:\u002F\u002Fgithub.com\u002Fbaodq97\u002Fgovkit\u002Fblob\u002Fmain\u002Fplugins\u002Fswe-flow\u002Fskills\u002Fworking-discipline\u002FSKILL.md",[],[]]