skill-distiller

# Skill Distiller Fetches top-rated skills from skills.sh for a task, analyzes them, and synthesizes one token-efficient skill combining the best elements. ## Modes ### Distill `<query>` **1. Search** — Find qualifying skills: ```bash python3 distillery/scripts/distiller.py search "<query1>" "<query2>" ... ``` Returns JSON array of qualifying skills (filtered to `installs >= 100`, top 10, deduplicated). If fewer than 3 qualify, threshold drops to 50. Save this output — it feeds into Step 2. **1b. Triage before fetching** — High install count does not correlate with quality. Before fetching, scan the search results: read skill descriptions and source repo names. Skip sources that are clearly generic checklists, project-specific tools, or domains outside the target skill's scope. Only fetch sources that suggest genuinely new patterns or techniques. **2. Fetch** — Stage sources and compute checksums: ```bash python3 distillery/scripts/distiller.py fetch --skills '<JSON from Step 1>' ``` Handles grouping by source, running `npx skills add`, staging to `distillery/.skill-distiller/sources/`, removing symlinks, and computing SHA-1 checksums. Returns JSON array with `id`, `skillId`, `installs`, `sha1`, and `path` for each staged source. **Fetch fallback:** If `distillery/scripts/distiller.py fetch` fails (subprocess issues with `npx skills add`), run `npx skills add <source_url> -s <skillId> -y --agent claude-code` directly from the project root. The skill will be install...