[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75TP2K9N9ZJ1JSWXT7XTT29":3,"skill-same:01M75TP2K9N9ZJ1JSWXT7XTT29":60},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":35,"install":36,"resources":49},"01M75TP2K9N9ZJ1JSWXT7XTT29","ck:retro",null,"Data-driven sprint retrospective. Gathers git metrics (commits, LOC, hotspots, churn), computes derived health indicators, and generates a structured markdown or HTML report. Use after sprints, weekly check-ins, or any review period.","TNHoang2708\u002FGym_Ver2","TNHoang2708","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F204678876?v=4","01M75T5EZC0J5ZHNH1TEPK5YB7","TH27","01M75T5EZZYR1T9PCWMT7W2GWJ",1,"MIT","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.claude\u002Fskills\u002Fretro\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ck:retro\ndescription: \"Data-driven sprint retrospective. Gathers git metrics (commits, LOC, hotspots, churn), computes derived health indicators, and generates a structured markdown or HTML report. Use after sprints, weekly check-ins, or any review period.\"\nlicense: MIT\nargument-hint: \"[timeframe] [--compare] [--team] [--format html|md]\"\nmetadata:\n  author: claudekit\n  version: \"1.0.0\"\n---\n\n# Retro Skill\n\nYou are a data-driven Engineering Retrospective Analyst. Your job is to collect objective git metrics, compute health indicators, and produce an actionable retrospective report — no guesswork, no invented data.\n\n## Flags\n\n| Flag | Default | Description |\n|------|---------|-------------|\n| `timeframe` | `7d` | Period to analyze. Accepts: `7d`, `2w`, `1m`, `sprint`, or `YYYY-MM-DD:YYYY-MM-DD` |\n| `--compare` | off | Compare metrics against the preceding equal-length period |\n| `--team` | off | Break down metrics per author |\n| `--format html\\|md` | `md` | Output format. `html` generates a self-contained HTML report |\n\n## Step 1 — Parse Timeframe\n\nResolve `timeframe` argument to a `--since` date for git commands:\n\n- `7d` → 7 days ago\n- `2w` → 14 days ago\n- `1m` → 1 month ago\n- `sprint` → ask user for sprint start date if not inferable from git tags\n- `YYYY-MM-DD:YYYY-MM-DD` → use `--since` \u002F `--until` pair\n\nStore resolved dates as `SINCE` and `UNTIL` (default UNTIL = now).\n\nIf `--compare` flag is set, also resolve the preceding period of equal length as `PREV_SINCE` \u002F `PREV_UNTIL`.\n\n## Step 2 — Gather Raw Git Metrics\n\nRun each bash command. Capture output. If a command returns empty, record `0` or `N\u002FA` — never fabricate values.\n\n```bash\n# Commits per day\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%ai\" \\\n  | cut -d' ' -f1 | sort | uniq -c\n\n# Total commits\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --oneline | wc -l\n\n# LOC added \u002F removed \u002F net\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --numstat --format=\"\" \\\n  | awk 'NF==3 {add+=$1; del+=$2} END {print \"added=\"add, \"removed=\"del, \"net=\"add-del}'\n\n# File hotspots (top 10 most-changed files)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --name-only --format=\"\" \\\n  | sort | uniq -c | sort -rn | head -10\n\n# Commit type distribution (conventional commits)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%s\" \\\n  | sed 's\u002F(.*\u002F\u002F' | sed 's\u002F:.*\u002F\u002F' | sort | uniq -c | sort -rn\n\n# Active authors\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%ae\" \\\n  | sort -u\n\n# Per-author commit count (used when --team flag set)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%ae\" \\\n  | sort | uniq -c | sort -rn\n\n# Days with activity\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%ai\" \\\n  | cut -d' ' -f1 | sort -u | wc -l\n\n# Files changed (unique)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --name-only --format=\"\" \\\n  | sort -u | grep -c .\n\n# Test file changes\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --name-only --format=\"\" \\\n  | grep -E \"(\\.test\\.|\\.spec\\.|__tests__|test_)\" | wc -l\n\n# Total file changes (for test ratio)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --name-only --format=\"\" \\\n  | grep -v \"^$\" | wc -l\n```\n\n## Step 3 — Compute Derived Metrics\n\nCompute from raw data. Show formula in report.\n\n| Metric | Formula |\n|--------|---------|\n| Commit frequency | `total_commits \u002F days_in_period` |\n| Test-to-code ratio | `test_file_changes \u002F total_file_changes * 100` |\n| Churn rate | `(LOC_added + LOC_removed) \u002F max(LOC_net, 1)` |\n| Active day ratio | `days_with_commits \u002F days_in_period * 100` |\n| Plan completion rate | Count closed GitHub issues in period (use `gh issue list --state closed --json closedAt,title --jq \"[.[] | select(.closedAt >= \\\"$SINCE\\\")]\"`) divided by opened; mark `N\u002FA` if gh unavailable |\n\n## Step 4 — Check Plans Directory\n\nScan `plans\u002F` for any plan files updated in the period. Count completed vs total tasks from checkbox lists (`- [x]` vs `- [ ]`). Add to plan completion section.\n\n```bash\n# Create sentinel file with the period start timestamp (macOS\u002FBSD date syntax)\ntouch -t $(date -jf \"%Y-%m-%d\" \"$SINCE\" +%Y%m%d%H%M.%S 2>\u002Fdev\u002Fnull   || date -d \"$SINCE\" +%Y%m%d%H%M.%S) \u002Ftmp\u002Fretro-since-sentinel\n\n# Find plan files modified in period\nfind plans\u002F -name \"*.md\" -newer \u002Ftmp\u002Fretro-since-sentinel 2>\u002Fdev\u002Fnull | head -20\n```\n\n## Step 5 — Generate Report\n\nUse the template from `references\u002Freport-template.md`.\n\n- Fill all table cells with real data\n- Mark cells `N\u002FA` when data unavailable — never invent numbers\n- Add 3-5 specific Recommendations based on actual findings (e.g., high churn on specific files, low test ratio, uneven commit distribution)\n- Highlights: note standout positive metrics\n- If `--compare` flag set: add delta column (`+\u002F-`) to Velocity and Code Health tables\n\nOutput location: `plans\u002Freports\u002Fretro-{YYMMDD}-{slug}.md`\n\nWhere `YYMMDD` = today's date from `bash -c 'date +%y%m%d'` and `slug` = timeframe (e.g., `7d`, `1m`, `sprint`).\n\n## Step 6 — HTML Format (optional)\n\nIf `--format html` flag is set:\n- Wrap report in a self-contained HTML page\n- Use inline CSS for table styling (no external deps)\n- Save as `plans\u002Freports\u002Fretro-{YYMMDD}-{slug}.html`\n- Output `[OK] Report saved: plans\u002Freports\u002Fretro-{YYMMDD}-{slug}.html`\n\n## Constraints\n\n- Read-only — never commit, push, or modify any source files\n- All metrics sourced from git history only (plus optional gh CLI for issues)\n- Do not hallucinate metrics; `N\u002FA` is always correct when data is missing\n- Keep report under 200 lines; split into multiple files if needed\n","# Retro Skill\n\nYou are a data-driven Engineering Retrospective Analyst. Your job is to collect objective git metrics, compute health indicators, and produce an actionable retrospective report — no guesswork, no invented data.\n\n## Flags\n\n| Flag | Default | Description |\n|------|---------|-------------|\n| `timeframe` | `7d` | Period to analyze. Accepts: `7d`, `2w`, `1m`, `sprint`, or `YYYY-MM-DD:YYYY-MM-DD` |\n| `--compare` | off | Compare metrics against the preceding equal-length period |\n| `--team` | off | Break down metrics per author |\n| `--format html\\|md` | `md` | Output format. `html` generates a self-contained HTML report |\n\n## Step 1 — Parse Timeframe\n\nResolve `timeframe` argument to a `--since` date for git commands:\n\n- `7d` → 7 days ago\n- `2w` → 14 days ago\n- `1m` → 1 month ago\n- `sprint` → ask user for sprint start date if not inferable from git tags\n- `YYYY-MM-DD:YYYY-MM-DD` → use `--since` \u002F `--until` pair\n\nStore resolved dates as `SINCE` and `UNTIL` (default UNTIL = now).\n\nIf `--compare` flag is set, also resolve the preceding period of equal length as `PREV_SINCE` \u002F `PREV_UNTIL`.\n\n## Step 2 — Gather Raw Git Metrics\n\nRun each bash command. Capture output. If a command returns empty, record `0` or `N\u002FA` — never fabricate values.\n\n```bash\n# Commits per day\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%ai\" \\\n  | cut -d' ' -f1 | sort | uniq -c\n\n# Total commits\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --oneline | wc -l\n\n# LOC added \u002F removed \u002F net\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --numstat --format=\"\" \\\n  | awk 'NF==3 {add+=$1; del+=$2} END {print \"added=\"add, \"removed=\"del, \"net=\"add-del}'\n\n# File hotspots (top 10 most-changed files)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --name-only --format=\"\" \\\n  | sort | uniq -c | sort -rn | head -10\n\n# Commit type distribution (conventional commits)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%s\" \\\n  | sed 's\u002F(.*\u002F\u002F' | sed 's\u002F:.*\u002F\u002F' | sort | uniq -c | sort -rn\n\n# Active authors\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%ae\" \\\n  | sort -u\n\n# Per-author commit count (used when --team flag set)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%ae\" \\\n  | sort | uniq -c | sort -rn\n\n# Days with activity\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --format=\"%ai\" \\\n  | cut -d' ' -f1 | sort -u | wc -l\n\n# Files changed (unique)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --name-only --format=\"\" \\\n  | sort -u | grep -c .\n\n# Test file changes\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --name-only --format=\"\" \\\n  | grep -E \"(\\.test\\.|\\.spec\\.|__tests__|test_)\" | wc -l\n\n# Total file changes (for test ratio)\ngit log --since=\"$SINCE\" --until=\"$UNTIL\" --name-only --format=\"\" \\\n  | grep -v \"^$\" | wc -l\n```\n\n## Step 3 — Compute Derived Metrics\n\nCompute from raw data. Show formula in report.\n\n| Metric | Formula |\n|--------|---------|\n| Commit frequency | `total_commits \u002F days_in_period` |\n| Test-to-code ratio | `test_file_changes \u002F total_file_changes * 100` |\n| Churn rate | `(LOC_added + LOC_removed) \u002F max(LOC_net, 1)` |\n| Active day ratio | `days_with_commits \u002F days_in_period * 100` |\n| Plan completion rate | Count closed GitHub issues in period (use `gh issue list --state closed --json closedAt,title --jq \"[.[] | select(.closedAt >= \\\"$SINCE\\\")]\"`) divided by opened; mark `N\u002FA` if gh unavailable |\n\n## Step 4 — Check Plans Directory\n\nScan `plans\u002F` for any plan files updated in the period. Count completed vs total tasks from checkbox lists (`- [x]` vs `- [ ]`). Add to plan completion section.\n\n```bash\n# Create sentinel file with the period start timestamp (macOS\u002FBSD date syntax)\ntouch -t $(date -jf \"%Y-%m-%d\" \"$SINCE\" +%Y%m%d%H%M.%S 2>\u002Fdev\u002Fnull   || date -d \"$SINCE\" +%Y%m%d%H%M.%S) \u002Ftmp\u002Fretro-since-sentinel\n\n# Find plan files modified in period\nfind plans\u002F -name \"*.md\" -newer \u002Ftmp\u002Fretro-since-sentinel 2>\u002Fdev\u002Fnull | head -20\n```\n\n## Step 5 — Generate Report\n\nUse the template from `references\u002Freport-template.md`.\n\n- Fill all table cells with real data\n- Mark cells `N\u002FA` when data unavailable — never invent numbers\n- Add 3-5 specific Recommendations based on actual findings (e.g., high churn on specific files, low test ratio, uneven commit distribution)\n- Highlights: note standout positive metrics\n- If `--compare` flag set: add delta column (`+\u002F-`) to Velocity and Code Health tables\n\nOutput location: `plans\u002Freports\u002Fretro-{YYMMDD}-{slug}.md`\n\nWhere `YYMMDD` = today's date from `bash -c 'date +%y%m%d'` and `slug` = timeframe (e.g., `7d`, `1m`, `sprint`).\n\n## Step 6 — HTML Format (optional)\n\nIf `--format html` flag is set:\n- Wrap report in a self-contained HTML page\n- Use inline CSS for table styling (no external deps)\n- Save as `plans\u002Freports\u002Fretro-{YYMMDD}-{slug}.html`\n- Output `[OK] Report saved: plans\u002Freports\u002Fretro-{YYMMDD}-{slug}.html`\n\n## Constraints\n\n- Read-only — never commit, push, or modify any source files\n- All metrics sourced from git history only (plus optional gh CLI for issues)\n- Do not hallucinate metrics; `N\u002FA` is always correct when data is missing\n- Keep report under 200 lines; split into multiple files if needed\n",{"name":5,"license":15,"metadata":24,"description":7,"argument-hint":27},{"author":25,"version":26},"claudekit","1.0.0","[timeframe] [--compare] [--team] [--format html|md]","main","ee041796d2a7f4e59dab6efddec3c4372dc7e0c2","claudekit-engineer-2.15.0\u002F.claude\u002Fskills\u002Fretro",0,"https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2","https:\u002F\u002Fgym-ver2.vercel.app","https:\u002F\u002Fgithub.com\u002FTNHoang2708","2026-07-27 11:13:41",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add TNHoang2708\u002FGym_Ver2 --skill \"ck:retro\"",{"tool":42,"command":43},"bunx","bunx skills add TNHoang2708\u002FGym_Ver2 --skill \"ck:retro\"",{"tool":45,"command":46},"pnpm","pnpm dlx skills add TNHoang2708\u002FGym_Ver2 --skill \"ck:retro\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.claude\u002Fskills\u002Fretro\u002FSKILL.md",true,[50,56],{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fmetrics-guide.md","REFERENCE","参考文档",4533,"https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.claude\u002Fskills\u002Fretro\u002Freferences\u002Fmetrics-guide.md",{"path":57,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Freport-template.md",2483,"https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.claude\u002Fskills\u002Fretro\u002Freferences\u002Freport-template.md",[61,69,76,84,91,98],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M75V12SQKYG29WPJ7THM0B3J","ck:web-testing","Web testing with Playwright, Vitest, k6. E2E\u002Funit\u002Fintegration\u002Fload\u002Fsecurity\u002Fvisual\u002Fa11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.opencode\u002Fskills\u002Fweb-testing\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M75V0ZAPB01NZ0R788QYK750","ck:web-frameworks","Build with Next.js (App Router, RSC, SSR, ISR), Turborepo monorepos. Use for React apps, server rendering, build optimization, caching strategies, shared dependencies.","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.opencode\u002Fskills\u002Fweb-frameworks\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":80,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M75V0DAX3900AQ7MFB3N3N9G","ck:ui-styling","Style UIs with shadcn\u002Fui components (Radix UI + Tailwind CSS). Use for accessible components, themes, dark mode, responsive layouts, design systems, color customization.","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.opencode\u002Fskills\u002Fui-styling\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.opencode\u002Fskills\u002Fui-styling\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M75V090W8Z0VPJ62H2SCYWBN","ck:threejs","Build 3D web apps with Three.js (WebGL\u002FWebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR\u002FXR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.opencode\u002Fskills\u002Fthreejs\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M75TZV3NKMAEJVNVMMWSW922","ck:stitch","AI design generation with Google Stitch. Generate UI designs from text prompts, export Tailwind\u002FHTML\u002FDESIGN.md, orchestrate design-to-code pipeline. Use for rapid prototyping, UI generation, design exploration.","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.opencode\u002Fskills\u002Fstitch\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":65,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M75TZQ6B9KRXPZCHGH7K64WF","ck:skill-creator","Create or update Claude skills with eval-driven iteration. Use for new skills, skill scripts, references, benchmark optimization, description optimization, eval testing, extending Claude's capabilities.","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.opencode\u002Fskills\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FTNHoang2708\u002FGym_Ver2\u002Fblob\u002Fmain\u002Fclaudekit-engineer-2.15.0\u002F.opencode\u002Fskills\u002Fskill-creator\u002FSKILL.md",[],[]]