[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73BP97DMEWPFM95GAB27CQP":3,"skill-same:01M73BP97DMEWPFM95GAB27CQP":72},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":14,"categories":15,"keywords":16,"publishedAt":17,"linkOnly":18,"markdownContent":19,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":12,"repositoryHtmlUrl":25,"repositoryHomepageUrl":6,"ownerHtmlUrl":26,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":27,"install":28,"resources":41},"01M73BP97DMEWPFM95GAB27CQP","code-review",null,"ngdletrung\u002FJKAI-Zenith","ngdletrung","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F88302940?v=4","01M73BJVV5QJ87R3MC4BXJMWDN","01M73BJVWAAM03TM18QHKRDAMH",0,"MIT","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: code-review\ndescription: Review the current diff for correctness bugs and reuse\u002Fsimplification\u002Fefficiency cleanups at the given effort level (low\u002Fmedium: fewer, high-confidence findings; high→max: broader coverage, may include uncertain findings; ultra: deep multi-agent review in the cloud). Pass --comment to post findings as inline PR comments, or --fix to apply the findings to the working tree after the review.\n---\n\n`high effort → 3+5 angles × 6 candidates → 1-vote verify (recall-biased) → ≤10 findings`\n\nYou are reviewing for **recall** at high effort: catch every real bug a careful\nreviewer would catch in one sitting. At this level, catching real bugs matters\nmore than avoiding false positives. Err on the side of surfacing.\n\n## Phase 0 — Gather the diff\n\nRun `git diff @{upstream}...HEAD` (or `git diff main...HEAD` \u002F `git diff HEAD~1`\nif there's no upstream) to get the unified diff under review. If there are\nuncommitted changes, or the range diff is empty, also run `git diff HEAD` and\ninclude the working-tree changes in scope — the review often runs before the\ncommit. If a PR number, branch name, or file path was passed as an argument,\nreview that target instead. Treat this diff as the review scope.\n\n## Phase 1 — Find candidates (3 correctness angles + 3 cleanup angles + 1 altitude angle + 1 conventions angle, up to 6 each)\n\nRun **8 independent finder angles** via the Agent tool. Each\nsurfaces **up to 6 candidate findings** with `file`, `line`, a one-line\n`summary`, and a concrete `failure_scenario`.\n\n### Angle A — line-by-line diff scan\n\nRead every hunk in the diff, line by line. Then Read the enclosing function for\neach hunk — bugs in unchanged lines of a touched function are in scope (the PR\nre-exposes or fails to fix them). For every line ask: what input, state, timing,\nor platform makes this line wrong? Look for inverted\u002Fwrong conditions,\noff-by-one, null\u002Fundefined deref, missing `await`, falsy-zero checks,\nwrong-variable copy-paste, error swallowed in catch, unescaped regex metachars.\n\n### Angle B — removed-behavior auditor\n\nFor every line the diff DELETES or replaces, name the invariant or behavior it\nenforced, then search the new code for where that invariant is re-established.\nIf you can't find it, that's a candidate: a removed guard, a dropped error\npath, a narrowed validation, a deleted test that was covering a real case.\n\n### Angle C — cross-file tracer\n\nFor each function the diff changes, find its callers (Grep for the symbol) and\ncheck whether the change breaks any call site: a new precondition, a changed\nreturn shape, a new exception, a timing\u002Fordering dependency. Also check callees:\ndoes a parallel change in the same PR make a call unsafe?\n\n### Reuse\n\nThe angles above hunt for bugs; this one and the next two hunt for cleanup in\nthe changed code. Flag new code that re-implements something the codebase\nalready has — Grep shared\u002Futility modules and files adjacent to the change,\nand name the existing helper to call instead.\n\n### Simplification\n\nFlag unnecessary complexity the diff adds: redundant or derivable state,\ncopy-paste with slight variation, deep nesting, dead code left behind. Name\nthe simpler form that does the same job.\n\n### Efficiency\n\nFlag wasted work the diff introduces: redundant computation or repeated I\u002FO,\nindependent operations run sequentially, blocking work added to startup or\nhot paths. Also flag long-lived objects built from closures or captured\nenvironments — they keep the entire enclosing scope alive for the object's\nlifetime (a memory leak when that scope holds large values); prefer a\nclass\u002Fstruct that copies only the fields it needs. Name the cheaper\nalternative.\n\n### Altitude\n\nCheck that each change is implemented at the right depth, not as a fragile\nbandaid. Special cases layered on shared infrastructure are a sign the fix\nisn't deep enough — prefer generalizing the underlying mechanism over adding\nspecial cases.\n\n### Conventions (CLAUDE.md)\n\nFind the CLAUDE.md files that govern the changed code: the user-level\n~\u002F.claude\u002FCLAUDE.md, the repo-root CLAUDE.md, plus any CLAUDE.md or\nCLAUDE.local.md in a directory that is an ancestor of a changed file (a\ndirectory's CLAUDE.md only applies to files at or below it). Read each one\nthat exists, then check the diff for clear violations of the rules they state.\n\nOnly flag a violation when you can quote the exact rule and the exact line\nthat breaks it — no style preferences, no vague \"spirit of the doc\"\ninferences. In the finding, name the CLAUDE.md path and quote the rule so the\nreport can cite it. If no CLAUDE.md applies, return nothing for this angle.\n\nCleanup, altitude, and conventions candidates use the same\n`file`\u002F`line`\u002F`summary` shape; in `failure_scenario`, state the concrete\ncost (what is duplicated, wasted, harder to maintain, or which CLAUDE.md rule\nis broken) instead of a crash. Correctness bugs always outrank cleanup,\naltitude, and conventions findings when the output cap forces a cut.\n\nPass every candidate with a nameable failure scenario through — finders that\nsilently drop half-believed candidates bypass the verify step and are the\ndominant cause of misses.\n\n## Phase 2 — Verify (1-vote, recall-biased)\n\nDedup near-duplicates (same defect, same location, same reason → keep one). For\neach remaining candidate, run **one verifier** via the Agent tool:\ngive it the diff, the relevant file(s), and the candidate; it returns exactly\none of **CONFIRMED \u002F PLAUSIBLE \u002F REFUTED**.\n\n**PLAUSIBLE by default** — do not refute a candidate for being \"speculative\" or\n\"depends on runtime state\" when the state is realistic: concurrency races,\nnil\u002Fundefined on a rare-but-reachable path (error handler, cold cache, missing\noptional field), falsy-zero treated as missing, off-by-one on a boundary the\ncode does not exclude, retry storms \u002F partial failures, regex\u002Fallowlist that\nlost an anchor. These are PLAUSIBLE.\n\n**REFUTED** only when constructible from the code: factually wrong (quote the\nactual line); provably impossible (type\u002Fconstant\u002Finvariant — show it); already\nhandled in this diff (cite the guard); or pure style with no observable effect.\n\nKeep **CONFIRMED and PLAUSIBLE**. Drop REFUTED.\n\n## Output\n\nReturn findings as a JSON array of at most 10 objects:\n\n```json\n[\n  {\n    \"file\": \"path\u002Fto\u002Ffile.ext\",\n    \"line\": 123,\n    \"summary\": \"one-sentence statement of the bug\",\n    \"failure_scenario\": \"concrete inputs\u002Fstate → wrong output\u002Fcrash\"\n  }\n]\n```\n\nRanked most-severe first. If more than 10 survive, keep the 10 most\nsevere. If nothing survives verification, return `[]`.\n","`high effort → 3+5 angles × 6 candidates → 1-vote verify (recall-biased) → ≤10 findings`\n\nYou are reviewing for **recall** at high effort: catch every real bug a careful\nreviewer would catch in one sitting. At this level, catching real bugs matters\nmore than avoiding false positives. Err on the side of surfacing.\n\n## Phase 0 — Gather the diff\n\nRun `git diff @{upstream}...HEAD` (or `git diff main...HEAD` \u002F `git diff HEAD~1`\nif there's no upstream) to get the unified diff under review. If there are\nuncommitted changes, or the range diff is empty, also run `git diff HEAD` and\ninclude the working-tree changes in scope — the review often runs before the\ncommit. If a PR number, branch name, or file path was passed as an argument,\nreview that target instead. Treat this diff as the review scope.\n\n## Phase 1 — Find candidates (3 correctness angles + 3 cleanup angles + 1 altitude angle + 1 conventions angle, up to 6 each)\n\nRun **8 independent finder angles** via the Agent tool. Each\nsurfaces **up to 6 candidate findings** with `file`, `line`, a one-line\n`summary`, and a concrete `failure_scenario`.\n\n### Angle A — line-by-line diff scan\n\nRead every hunk in the diff, line by line. Then Read the enclosing function for\neach hunk — bugs in unchanged lines of a touched function are in scope (the PR\nre-exposes or fails to fix them). For every line ask: what input, state, timing,\nor platform makes this line wrong? Look for inverted\u002Fwrong conditions,\noff-by-one, null\u002Fundefined deref, missing `await`, falsy-zero checks,\nwrong-variable copy-paste, error swallowed in catch, unescaped regex metachars.\n\n### Angle B — removed-behavior auditor\n\nFor every line the diff DELETES or replaces, name the invariant or behavior it\nenforced, then search the new code for where that invariant is re-established.\nIf you can't find it, that's a candidate: a removed guard, a dropped error\npath, a narrowed validation, a deleted test that was covering a real case.\n\n### Angle C — cross-file tracer\n\nFor each function the diff changes, find its callers (Grep for the symbol) and\ncheck whether the change breaks any call site: a new precondition, a changed\nreturn shape, a new exception, a timing\u002Fordering dependency. Also check callees:\ndoes a parallel change in the same PR make a call unsafe?\n\n### Reuse\n\nThe angles above hunt for bugs; this one and the next two hunt for cleanup in\nthe changed code. Flag new code that re-implements something the codebase\nalready has — Grep shared\u002Futility modules and files adjacent to the change,\nand name the existing helper to call instead.\n\n### Simplification\n\nFlag unnecessary complexity the diff adds: redundant or derivable state,\ncopy-paste with slight variation, deep nesting, dead code left behind. Name\nthe simpler form that does the same job.\n\n### Efficiency\n\nFlag wasted work the diff introduces: redundant computation or repeated I\u002FO,\nindependent operations run sequentially, blocking work added to startup or\nhot paths. Also flag long-lived objects built from closures or captured\nenvironments — they keep the entire enclosing scope alive for the object's\nlifetime (a memory leak when that scope holds large values); prefer a\nclass\u002Fstruct that copies only the fields it needs. Name the cheaper\nalternative.\n\n### Altitude\n\nCheck that each change is implemented at the right depth, not as a fragile\nbandaid. Special cases layered on shared infrastructure are a sign the fix\nisn't deep enough — prefer generalizing the underlying mechanism over adding\nspecial cases.\n\n### Conventions (CLAUDE.md)\n\nFind the CLAUDE.md files that govern the changed code: the user-level\n~\u002F.claude\u002FCLAUDE.md, the repo-root CLAUDE.md, plus any CLAUDE.md or\nCLAUDE.local.md in a directory that is an ancestor of a changed file (a\ndirectory's CLAUDE.md only applies to files at or below it). Read each one\nthat exists, then check the diff for clear violations of the rules they state.\n\nOnly flag a violation when you can quote the exact rule and the exact line\nthat breaks it — no style preferences, no vague \"spirit of the doc\"\ninferences. In the finding, name the CLAUDE.md path and quote the rule so the\nreport can cite it. If no CLAUDE.md applies, return nothing for this angle.\n\nCleanup, altitude, and conventions candidates use the same\n`file`\u002F`line`\u002F`summary` shape; in `failure_scenario`, state the concrete\ncost (what is duplicated, wasted, harder to maintain, or which CLAUDE.md rule\nis broken) instead of a crash. Correctness bugs always outrank cleanup,\naltitude, and conventions findings when the output cap forces a cut.\n\nPass every candidate with a nameable failure scenario through — finders that\nsilently drop half-believed candidates bypass the verify step and are the\ndominant cause of misses.\n\n## Phase 2 — Verify (1-vote, recall-biased)\n\nDedup near-duplicates (same defect, same location, same reason → keep one). For\neach remaining candidate, run **one verifier** via the Agent tool:\ngive it the diff, the relevant file(s), and the candidate; it returns exactly\none of **CONFIRMED \u002F PLAUSIBLE \u002F REFUTED**.\n\n**PLAUSIBLE by default** — do not refute a candidate for being \"speculative\" or\n\"depends on runtime state\" when the state is realistic: concurrency races,\nnil\u002Fundefined on a rare-but-reachable path (error handler, cold cache, missing\noptional field), falsy-zero treated as missing, off-by-one on a boundary the\ncode does not exclude, retry storms \u002F partial failures, regex\u002Fallowlist that\nlost an anchor. These are PLAUSIBLE.\n\n**REFUTED** only when constructible from the code: factually wrong (quote the\nactual line); provably impossible (type\u002Fconstant\u002Finvariant — show it); already\nhandled in this diff (cite the guard); or pure style with no observable effect.\n\nKeep **CONFIRMED and PLAUSIBLE**. Drop REFUTED.\n\n## Output\n\nReturn findings as a JSON array of at most 10 objects:\n\n```json\n[\n  {\n    \"file\": \"path\u002Fto\u002Ffile.ext\",\n    \"line\": 123,\n    \"summary\": \"one-sentence statement of the bug\",\n    \"failure_scenario\": \"concrete inputs\u002Fstate → wrong output\u002Fcrash\"\n  }\n]\n```\n\nRanked most-severe first. If more than 10 survive, keep the 10 most\nsevere. If nothing survives verification, return `[]`.\n",{},"main","571327a911ec45873180fd5628525b6d4504ed79","files\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith","https:\u002F\u002Fgithub.com\u002Fngdletrung","2026-11-08 11:23:33",{"source":7,"skillName":5,"commands":29,"prompt":39,"zipAvailable":40},[30,33,36],{"tool":31,"command":32},"npx","npx skills add ngdletrung\u002FJKAI-Zenith --skill code-review",{"tool":34,"command":35},"bunx","bunx skills add ngdletrung\u002FJKAI-Zenith --skill code-review",{"tool":37,"command":38},"pnpm","pnpm dlx skills add ngdletrung\u002FJKAI-Zenith --skill code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002FSKILL.md",true,[42,48,52,56,60,64,68],{"path":43,"resourceType":44,"resourceTypeDesc":45,"sizeBytes":46,"sourceHtmlUrl":47},"high.md","REFERENCE","参考文档",6184,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002Fhigh.md",{"path":49,"resourceType":44,"resourceTypeDesc":45,"sizeBytes":50,"sourceHtmlUrl":51},"low.md",1210,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002Flow.md",{"path":53,"resourceType":44,"resourceTypeDesc":45,"sizeBytes":54,"sourceHtmlUrl":55},"max.md",7355,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002Fmax.md",{"path":57,"resourceType":44,"resourceTypeDesc":45,"sizeBytes":58,"sourceHtmlUrl":59},"medium.md",5744,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002Fmedium.md",{"path":61,"resourceType":44,"resourceTypeDesc":45,"sizeBytes":62,"sourceHtmlUrl":63},"README.md",2488,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002FREADME.md",{"path":65,"resourceType":44,"resourceTypeDesc":45,"sizeBytes":66,"sourceHtmlUrl":67},"report-findings-tool.md",2558,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002Freport-findings-tool.md",{"path":69,"resourceType":44,"resourceTypeDesc":45,"sizeBytes":70,"sourceHtmlUrl":71},"xhigh.md",7360,"https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Ffiles\u002Fsystem_prompts_leaks-main\u002FAnthropic\u002FClaude Code\u002Fbundled-skills\u002Fcode-review\u002Fxhigh.md",[73,80,86,93,99,105],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":17},"01M73C2NC1W5P3A0V3GQAJ0SJB","standard_plugin","Hướng dẫn kích hoạt và vận hành cho kỹ năng standard_plugin.","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002Ftemplates\u002Fstandard_plugin\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":17},"01M73C2KAN3Q7D5XEBKB3KZW1B","_STANDARD","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002F_STANDARD\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":17},"01M73C2HV7KDJQTA6ACCR10HZB","test_dynamic_audit","Thao tác kiểm toán động","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FTEST\u002Ftest_dynamic_audit\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":17},"01M73C2FRG0JHZ6W155V1KCHRP","security-audit","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fsecurity-audit\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":17},"01M73C2EMWYHFTAR9RSZ41TBGP","security-and-hardening","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fsecurity-and-hardening\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":8,"repositoryNo":11,"starsCount":12,"licenseSpdxId":13,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":17},"01M73C2CV0BQ59NAEWXKBQ370Z","performance-optimization","https:\u002F\u002Fgithub.com\u002Fngdletrung\u002FJKAI-Zenith\u002Fblob\u002Fmain\u002Fintelligence\u002Fskills\u002FSECURITY\u002Fperformance-optimization\u002FSKILL.md",[],[]]