[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NDBMHJSXSNWQF5PC4EYJ8T":3,"skill-same:01M6NDBMHJSXSNWQF5PC4EYJ8T":78},{"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":31,"publishedAt":52,"linkOnly":53,"markdownContent":54,"markdownBody":55,"frontMatter":56,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":6,"ownerHtmlUrl":62,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6NDBMHJSXSNWQF5PC4EYJ8T","code-review",null,"Review criteria and confidence scoring for changes in the harness-eval monorepo (Bash scripts, hooks, SKILL\u002Fagent prompts, manifests). Use when reviewing a diff, PR, or file set in this repo.","whchoi98\u002Fharness-eval","whchoi98","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F11262759?v=4","01M6NDBHK852X9V2A3S0MCSFXH","Woo Hyung Choi","01M6NDBHQRZ1X9VQ446F0ECDJJ",19,"MIT","https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-review\u002FSKILL.md",[18,23,26],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000007","代码审查","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":27,"categoryName":28,"taxonomyType":29,"taxonomyTypeDesc":30},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"review","code review","code","changes","for","manifests","scripts","scoring","confidence scoring","hooks","diff","use","repo","eval","monorepo","Bash","SET","file","harness","pr","2026-11-10 10:12:30",false,"---\nname: code-review\ndescription: Review criteria and confidence scoring for changes in the harness-eval monorepo (Bash scripts, hooks, SKILL\u002Fagent prompts, manifests). Use when reviewing a diff, PR, or file set in this repo.\n---\n\n# Code Review Skill\n\nReview changed code in this repo and report every issue with a severity and a confidence score.\n\n## Review Scope\n\nBy default, review all uncommitted work: `git status --short --untracked-files=all` for the file list, `git diff HEAD` for tracked changes (staged and unstaged), and each untracked (`??`) file read in full, since a new file has no diff. The user may specify different files or scope.\n\n## What to check in this repo\n\nBeyond general correctness and security, the contracts most likely to break here (plugin paths are under `plugins\u002Fharness-eval\u002F`):\n- Scripts: target project root as `$1` (`aggregate.sh` reads stdin instead), JSON on stdout \u002F logs on stderr, exit codes 0\u002F1\u002F2, `jq` checked at startup (`scripts\u002FCLAUDE.md`). The SKILL.md files duplicate this contract for plugin users, so a script change must update them.\n- Prompt files are code. SKILL, agent, and command `.md` files carry contracts other code parses - handoff lines and markers, report headings, JSON field names, headings asserted by `tests\u002Fstructure\u002Ftest-plugin-structure.sh`. A changed string must match every consumer; grep for it.\n- Auto-discovery: no non-component `.md` (including CLAUDE.md) under `commands\u002F` or `agents\u002F`. Agents use `tools`; commands and skills use `allowed-tools`.\n- The version must match in `plugin.json` `version` and `marketplace.json` `metadata.version` + `plugins[].version`.\n- Plugin hooks must not modify user files without opt-in, and their failures stay visible (`hooks\u002FCLAUDE.md`).\n- The fixtures under `tests\u002Ffixtures\u002F` are frozen test inputs; new coverage goes in a new fixture directory.\n- Bilingual output: English and Korean reports and doc sections stay in sync.\n\n## Confidence and severity\n\nFor each issue give a severity (critical \u002F important \u002F minor) and a confidence 0-100 that it is a real, newly introduced defect (90+: confirmed; 75-89: verified; 50-74: likely; below 50: speculative or pre-existing). Report every issue with its scores. The report shows items at 75+ first and groups the rest under \"Lower confidence\" - the reader filters, you don't drop.\n\n## Output Format\n\nFor each issue:\n### [CRITICAL|IMPORTANT|MINOR] \u003Cissue title> (confidence: XX)\n**File:** `path\u002Fto\u002Ffile.ext:line`\n**Issue:** Clear description of the problem\n**Guideline:** Reference to CLAUDE.md rule or security standard\n**Fix:** Concrete code suggestion\n\nList items with confidence ≥ 75 first, then a \"Lower confidence\" section; if nothing reaches 75, say so and still list the rest.\n","# Code Review Skill\n\nReview changed code in this repo and report every issue with a severity and a confidence score.\n\n## Review Scope\n\nBy default, review all uncommitted work: `git status --short --untracked-files=all` for the file list, `git diff HEAD` for tracked changes (staged and unstaged), and each untracked (`??`) file read in full, since a new file has no diff. The user may specify different files or scope.\n\n## What to check in this repo\n\nBeyond general correctness and security, the contracts most likely to break here (plugin paths are under `plugins\u002Fharness-eval\u002F`):\n- Scripts: target project root as `$1` (`aggregate.sh` reads stdin instead), JSON on stdout \u002F logs on stderr, exit codes 0\u002F1\u002F2, `jq` checked at startup (`scripts\u002FCLAUDE.md`). The SKILL.md files duplicate this contract for plugin users, so a script change must update them.\n- Prompt files are code. SKILL, agent, and command `.md` files carry contracts other code parses - handoff lines and markers, report headings, JSON field names, headings asserted by `tests\u002Fstructure\u002Ftest-plugin-structure.sh`. A changed string must match every consumer; grep for it.\n- Auto-discovery: no non-component `.md` (including CLAUDE.md) under `commands\u002F` or `agents\u002F`. Agents use `tools`; commands and skills use `allowed-tools`.\n- The version must match in `plugin.json` `version` and `marketplace.json` `metadata.version` + `plugins[].version`.\n- Plugin hooks must not modify user files without opt-in, and their failures stay visible (`hooks\u002FCLAUDE.md`).\n- The fixtures under `tests\u002Ffixtures\u002F` are frozen test inputs; new coverage goes in a new fixture directory.\n- Bilingual output: English and Korean reports and doc sections stay in sync.\n\n## Confidence and severity\n\nFor each issue give a severity (critical \u002F important \u002F minor) and a confidence 0-100 that it is a real, newly introduced defect (90+: confirmed; 75-89: verified; 50-74: likely; below 50: speculative or pre-existing). Report every issue with its scores. The report shows items at 75+ first and groups the rest under \"Lower confidence\" - the reader filters, you don't drop.\n\n## Output Format\n\nFor each issue:\n### [CRITICAL|IMPORTANT|MINOR] \u003Cissue title> (confidence: XX)\n**File:** `path\u002Fto\u002Ffile.ext:line`\n**Issue:** Clear description of the problem\n**Guideline:** Reference to CLAUDE.md rule or security standard\n**Fix:** Concrete code suggestion\n\nList items with confidence ≥ 75 first, then a \"Lower confidence\" section; if nothing reaches 75, say so and still list the rest.\n",{"name":5,"description":7},"main","820cf8d1b503efb55bdcef2f86515841579e54ab",".claude\u002Fskills\u002Fcode-review",2,"https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval","https:\u002F\u002Fgithub.com\u002Fwhchoi98","2026-09-24 17:53:28",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add whchoi98\u002Fharness-eval --skill code-review",{"tool":70,"command":71},"bunx","bunx skills add whchoi98\u002Fharness-eval --skill code-review",{"tool":73,"command":74},"pnpm","pnpm dlx skills add whchoi98\u002Fharness-eval --skill code-review","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fcode-review\u002FSKILL.md",true,[],[79,93,118,127,148,161],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":88,"publishedAt":52},"01M6NDE0RRMR9EH3NX5KT6YRCY","summarize","Summarize a document using an alias and the max effort level","https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-eval\u002Ftests\u002Ffixtures\u002Fmodel-era-project\u002F.claude\u002Fskills\u002Fsummarize\u002FSKILL.md",[85],{"categoryNo":86,"categoryName":87,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",[81,89,90,91,92],"alias","sonnet","document","max",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":102,"publishedAt":52},"01M6NDDWRFFKHJFE7025AGSW9K","standard","Standard harness evaluation — static analysis, dynamic testing, and checklist scoring in 2-3 minutes. Produces a detailed report with findings and improvement roadmap. Dynamic testing runs the target's hooks and tests after the user confirms. Pass --static-only for repositories you do not trust.","https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-eval\u002Fskills\u002Fstandard\u002FSKILL.md",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[95,103,104,105,106,107,108,36,109,110,111,50,39,112,113,114,41,115,116,117],"report","testing","Evaluation","tests","static","improvement","minutes","you","with","do","trust","checklist","roadmap","only","analysis",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":52},"01M6NDDAS3GH993YS98D37FE69","quick","Quick harness evaluation — checklist-based scoring in ~30 seconds. Runs deterministic checks against the target project and produces a score, grade, and improvement suggestions.","https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-eval\u002Fskills\u002Fquick\u002FSKILL.md",[],[120,114,108,125,39,126,105,50],"project","deterministic",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":136,"publishedAt":52},"01M6NDD5XJN68ATTM77DQ8VMYH","full","Full harness evaluation — multi-agent deep analysis across 12 dimensions (safety, completeness, design quality) with parallel evaluators and a synthesized report. Takes 5-10 minutes. Produces a scored report in English and Korean with an executive summary and improvement roadmap. Use when the user explicitly asks for a full, deep, or multi-agent harness evaluation. For a quick score use quick; for static plus dynamic checks use standard.","https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-eval\u002Fskills\u002Ffull\u002FSKILL.md",[133],{"categoryNo":134,"categoryName":135,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",[129,107,108,36,120,137,50,138,139,140,115,141,142,117,143,105,144,145,146,147],"english","across","dimensions","korean","parallel","multi-agent","Safety","deep","deep analysis","executive summary","design",{"skillNo":149,"name":150,"nameZh":6,"description":151,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":154,"publishedAt":52},"01M6NDD366AHN40A7DMW0G3F95","compare","Compare harness evaluation history — shows score trends, per-tier deltas, diminishing returns detection, and next grade projection.","https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-eval\u002Fskills\u002Fcompare\u002FSKILL.md",[],[150,105,50,155,156,157,158,159,160],"detection","trends","next","deltas","returns","history",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":167,"publishedAt":52},"01M6NDCK6VXG06S27GSQGR3163","sync-docs","Bring harness-eval's CLAUDE.md files, architecture docs, and manifests back in line with the current code. Use when the user asks to sync or audit docs, or after structural changes.","https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fsync-docs\u002FSKILL.md",[],[168,169,170,171,35,37,172,111,173,174,175,176,43,177,45,178,50,34,179],"sync","sync docs","docs","back","bring","line","structural","audit docs","files","user","audit","architecture"]