[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NDDAS3GH993YS98D37FE69":3,"skill-same:01M6NDDAS3GH993YS98D37FE69":53},{"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":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":6,"ownerHtmlUrl":37,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":38,"install":39,"resources":52},"01M6NDDAS3GH993YS98D37FE69","quick",null,"Quick harness evaluation — checklist-based scoring in ~30 seconds. Runs deterministic checks against the target project and produces a score, grade, and improvement suggestions.","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\u002Fplugins\u002Fharness-eval\u002Fskills\u002Fquick\u002FSKILL.md",[],[5,19,20,21,22,23,24,25],"harness","Evaluation","checklist","deterministic","scoring","project","improvement","2026-11-10 10:12:30",false,"---\nname: quick\ndescription: Quick harness evaluation — checklist-based scoring in ~30 seconds. Runs deterministic checks against the target project and produces a score, grade, and improvement suggestions.\neffort: low\n---\n\nYou are performing a Quick harness evaluation. This is a fast, checklist-based assessment that produces a score and grade.\n\n## Steps\n\n1. **Identify target project**: Use the current working directory as the target project root. Verify it exists and contains at least some files.\n\n2. **Run scoring script**: Execute the scoring engine:\n   ```bash\n   HARNESS_EVAL_ROOT=\"${CLAUDE_PLUGIN_ROOT}\" bash \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fscoring.sh\" --mode quick \"$(pwd)\"\n   ```\n   Capture the JSON output. Exit code 1 means some checks failed and is a normal result; only exit code 2 is a script error.\n\n3. **Parse results**: Extract from the JSON:\n   - `scores.overall` — numeric score (1.0-10.0)\n   - `scores.grade` — letter grade\n   - `checklist` — per-tier pass\u002Ftotal counts\n   - `results` — individual check pass\u002Ffail details\n\n4. **Generate bilingual report**: Present results in English and Korean, separated by a horizontal rule. Use this format:\n\n   ```\n   # Harness Quick Evaluation\n\n   **Score: {overall}\u002F10 ({grade})**\n   **Date: {timestamp}**\n\n   ## Checklist Results\n\n   | Tier | Passed | Total | Status |\n   |------|--------|-------|--------|\n   | Basic (6.0+) | X | Y | ✓\u002F✗ |\n   | Functional (7.0+) | X | Y | ✓\u002F✗ |\n   | Robust (8.0+) | X | Y | ✓\u002F✗ |\n   | Production (9.0+) | X | Y | ✓\u002F✗ |\n\n   ## Failed Checks\n   (For each FAIL: its description and tier, then the fix — the file path to create or change, with example content)\n\n   ## Next Steps\n   (The improvements that would move the project to the next tier, highest impact first — as many as the failed checks warrant)\n\n   ---\n\n   # 하네스 Quick 평가\n\n   **점수: {overall}\u002F10 ({grade})**\n   **날짜: {timestamp}**\n\n   ## 체크리스트 결과\n\n   | 단계 | 통과 | 전체 | 상태 |\n   |------|------|------|------|\n   | 기본 (6.0+) | X | Y | ✓\u002F✗ |\n   | 기능적 (7.0+) | X | Y | ✓\u002F✗ |\n   | 견고 (8.0+) | X | Y | ✓\u002F✗ |\n   | 프로덕션 (9.0+) | X | Y | ✓\u002F✗ |\n\n   ## 실패 항목\n   (각 FAIL 항목의 설명과 단계, 그리고 해결 방법 — 만들거나 수정할 파일 경로와 예시 내용)\n\n   ## 다음 단계\n   (다음 단계 도달에 필요한 개선 사항 — 실패 항목에 맞춰 필요한 만큼, 영향도 순)\n   ```\n\n5. **Save reports to files**: Save the English and Korean reports as separate files in the target project:\n   ```bash\n   mkdir -p .harness-eval\u002Freports\n   ```\n   - English report: `.harness-eval\u002Freports\u002Feval-{YYYY-MM-DD}-{NNN}-quick-en.md`\n   - Korean report: `.harness-eval\u002Freports\u002Feval-{YYYY-MM-DD}-{NNN}-quick-ko.md`\n\n   `{YYYY-MM-DD}` is the UTC date of the scoring output's `timestamp`. Quick runs are not recorded in history (`\u002Fharness-eval:compare` works from saved Standard and Full runs), so `{NNN}` is a per-day Quick report counter, not a history ID: list today's Quick reports with `ls .harness-eval\u002Freports\u002Feval-$(date -u +%F)-*-quick-en.md 2>\u002Fdev\u002Fnull || true` (it prints nothing when there are none) and use one more than the highest `{NNN}` found, zero-padded to three digits (`001` if there are none). This keeps a second Quick run on the same day from overwriting the first.\n\n   Use the Write tool to create each file. After saving, inform the user of the file paths.\n\n## Error Handling\n\n- If scoring.sh exits with code 2 (script error), show the error message and suggest checking dependencies (jq installed? correct path?)\n- If the target has no `.claude\u002F` directory at all, the score will be very low. Suggest running `\u002Finit` in a Claude Code session to create a CLAUDE.md, then adding `.claude\u002Fsettings.json` with permissions and hooks.\n- If jq is not installed, tell the user: `sudo apt install jq` or `brew install jq`\n\n## Tone\n\nBe direct and constructive. Focus on what to do next, not what's wrong.\n\n## Language\n\nAlways produce the report in both English and Korean. English section first, then a horizontal rule (---), then the Korean section. Tables, scores, file paths, and code blocks are identical in both sections — only the prose text differs.\n","You are performing a Quick harness evaluation. This is a fast, checklist-based assessment that produces a score and grade.\n\n## Steps\n\n1. **Identify target project**: Use the current working directory as the target project root. Verify it exists and contains at least some files.\n\n2. **Run scoring script**: Execute the scoring engine:\n   ```bash\n   HARNESS_EVAL_ROOT=\"${CLAUDE_PLUGIN_ROOT}\" bash \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fscoring.sh\" --mode quick \"$(pwd)\"\n   ```\n   Capture the JSON output. Exit code 1 means some checks failed and is a normal result; only exit code 2 is a script error.\n\n3. **Parse results**: Extract from the JSON:\n   - `scores.overall` — numeric score (1.0-10.0)\n   - `scores.grade` — letter grade\n   - `checklist` — per-tier pass\u002Ftotal counts\n   - `results` — individual check pass\u002Ffail details\n\n4. **Generate bilingual report**: Present results in English and Korean, separated by a horizontal rule. Use this format:\n\n   ```\n   # Harness Quick Evaluation\n\n   **Score: {overall}\u002F10 ({grade})**\n   **Date: {timestamp}**\n\n   ## Checklist Results\n\n   | Tier | Passed | Total | Status |\n   |------|--------|-------|--------|\n   | Basic (6.0+) | X | Y | ✓\u002F✗ |\n   | Functional (7.0+) | X | Y | ✓\u002F✗ |\n   | Robust (8.0+) | X | Y | ✓\u002F✗ |\n   | Production (9.0+) | X | Y | ✓\u002F✗ |\n\n   ## Failed Checks\n   (For each FAIL: its description and tier, then the fix — the file path to create or change, with example content)\n\n   ## Next Steps\n   (The improvements that would move the project to the next tier, highest impact first — as many as the failed checks warrant)\n\n   ---\n\n   # 하네스 Quick 평가\n\n   **점수: {overall}\u002F10 ({grade})**\n   **날짜: {timestamp}**\n\n   ## 체크리스트 결과\n\n   | 단계 | 통과 | 전체 | 상태 |\n   |------|------|------|------|\n   | 기본 (6.0+) | X | Y | ✓\u002F✗ |\n   | 기능적 (7.0+) | X | Y | ✓\u002F✗ |\n   | 견고 (8.0+) | X | Y | ✓\u002F✗ |\n   | 프로덕션 (9.0+) | X | Y | ✓\u002F✗ |\n\n   ## 실패 항목\n   (각 FAIL 항목의 설명과 단계, 그리고 해결 방법 — 만들거나 수정할 파일 경로와 예시 내용)\n\n   ## 다음 단계\n   (다음 단계 도달에 필요한 개선 사항 — 실패 항목에 맞춰 필요한 만큼, 영향도 순)\n   ```\n\n5. **Save reports to files**: Save the English and Korean reports as separate files in the target project:\n   ```bash\n   mkdir -p .harness-eval\u002Freports\n   ```\n   - English report: `.harness-eval\u002Freports\u002Feval-{YYYY-MM-DD}-{NNN}-quick-en.md`\n   - Korean report: `.harness-eval\u002Freports\u002Feval-{YYYY-MM-DD}-{NNN}-quick-ko.md`\n\n   `{YYYY-MM-DD}` is the UTC date of the scoring output's `timestamp`. Quick runs are not recorded in history (`\u002Fharness-eval:compare` works from saved Standard and Full runs), so `{NNN}` is a per-day Quick report counter, not a history ID: list today's Quick reports with `ls .harness-eval\u002Freports\u002Feval-$(date -u +%F)-*-quick-en.md 2>\u002Fdev\u002Fnull || true` (it prints nothing when there are none) and use one more than the highest `{NNN}` found, zero-padded to three digits (`001` if there are none). This keeps a second Quick run on the same day from overwriting the first.\n\n   Use the Write tool to create each file. After saving, inform the user of the file paths.\n\n## Error Handling\n\n- If scoring.sh exits with code 2 (script error), show the error message and suggest checking dependencies (jq installed? correct path?)\n- If the target has no `.claude\u002F` directory at all, the score will be very low. Suggest running `\u002Finit` in a Claude Code session to create a CLAUDE.md, then adding `.claude\u002Fsettings.json` with permissions and hooks.\n- If jq is not installed, tell the user: `sudo apt install jq` or `brew install jq`\n\n## Tone\n\nBe direct and constructive. Focus on what to do next, not what's wrong.\n\n## Language\n\nAlways produce the report in both English and Korean. English section first, then a horizontal rule (---), then the Korean section. Tables, scores, file paths, and code blocks are identical in both sections — only the prose text differs.\n",{"name":5,"effort":31,"description":7},"low","main","820cf8d1b503efb55bdcef2f86515841579e54ab","plugins\u002Fharness-eval\u002Fskills\u002Fquick",2,"https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval","https:\u002F\u002Fgithub.com\u002Fwhchoi98","2026-09-24 17:53:28",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add whchoi98\u002Fharness-eval --skill quick",{"tool":45,"command":46},"bunx","bunx skills add whchoi98\u002Fharness-eval --skill quick",{"tool":48,"command":49},"pnpm","pnpm dlx skills add whchoi98\u002Fharness-eval --skill quick","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002Fplugins\u002Fharness-eval\u002Fskills\u002Fquick\u002FSKILL.md",true,[],[54,70,94,115,128,152],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":65,"publishedAt":26},"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",[60],{"categoryNo":61,"categoryName":62,"taxonomyType":63,"taxonomyTypeDesc":64},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[56,66,67,68,69],"sonnet","alias","max","document",{"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":79,"publishedAt":26},"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",[76],{"categoryNo":77,"categoryName":78,"taxonomyType":63,"taxonomyTypeDesc":64},"01JBSEEDCAT000000000000008","测试与质量",[72,20,19,80,81,82,83,84,25,85,86,87,88,23,89,90,21,91,92,93],"report","testing","analysis","you","static","for","minutes","with","tests","do","trust","hooks","roadmap","only",{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":103,"publishedAt":26},"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",[100],{"categoryNo":101,"categoryName":102,"taxonomyType":63,"taxonomyTypeDesc":64},"01JBSEEDCAT000000000000015","视觉设计",[96,104,84,25,85,5,105,106,107,108,92,109,110,82,111,20,19,112,113,114],"deep","english","across","dimensions","korean","parallel","multi-agent","Safety","deep analysis","executive summary","design",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":26},"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",[],[117,122,123,124,125,126,127,20,19],"detection","trends","next","deltas","returns","history",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":26},"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",[],[135,136,137,138,139,140,141,142,19,143,144,145,146,147,148,87,149,150,151],"sync docs","sync","docs","files","use","user","eval","audit","code","architecture","back","changes","manifests","bring","line","structural","audit docs",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":26},"01M6NDC0RPXHBXXA1BZJZ0ERAE","release","Cut a harness-eval release - bump the version in the three manifest fields and the README version badge, update CHANGELOG (EN+KO), tag. Use only when the user asks to release.","https:\u002F\u002Fgithub.com\u002Fwhchoi98\u002Fharness-eval\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Frelease\u002FSKILL.md",[],[154,19,159,160,161,162,141,163,164,165,166,167,168,93,169,139,170,140],"update","changelog","README","update changelog","true","ko","cut","three","bump","en","version","manifest"]