{
  "markdown": "# skill-picker\n\nA [Claude Code](https://docs.anthropic.com/en/docs/claude-code) plugin that compares AI coding skills head-to-head to find which one works best for your task.\n\n## What it does\n\nRun controlled A/B tests: same model (Claude Code), same tasks, different skills. Each candidate runs in an isolated worktree sub-agent. Output: a markdown comparison report with scores and a winner.\n\n## Install\n\n### Option A: Plugin (recommended)\n\n```\n/plugin marketplace add qhuang20/skill-picker\n/plugin install skill-picker@skill-picker\n```\n\n### Option B: Manual (single skill, no plugin overhead)\n\n```bash\ngit clone https://github.com/qhuang20/skill-picker.git /tmp/skill-picker\nmkdir -p ~/.claude/skills/skill-picker\ncp /tmp/skill-picker/skills/skill-picker/SKILL.md ~/.claude/skills/skill-picker/\nrm -rf /tmp/skill-picker\n```\n\n## Usage\n\nJust tell Claude Code:\n\n- \"compare these two skills\"\n- \"which skill is better for X\"\n- \"skill picker\"\n\nOr invoke directly with `/skill-picker:skill-picker`.\n\n## How it works\n\n1. **Diagnose** — Understand your pain point\n2. **Source candidates** — Find skills to compare (local or web search)\n3. **Establish ground truth** — Define what \"good\" looks like with your input\n4. **Battle** — Run parallel sub-agents, each with a different skill, in isolated worktrees\n5. **Report** — Generate a markdown comparison with scores and a winner\n\n## License\n\nMIT\n",
  "bytes": 1388,
  "sha": "5448c8f31169040e3a1f6f694c8956ca503f97cab79a22a17ab71e8fc0dcf082",
  "repo_slug": "qhuang20/skill-picker",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_qhuang20_skill_picker_skill_picker_29725774/readme"
}