Auto-Research

Improve a target prompt artifact (SKILL.md, CLAUDE.md, subagent definition, slash-command, or generic prompt markdown) by:

1. Detecting the artifact type and the rules that apply to it
2. Researching current authoritative best practices in parallel — every claim cited
3. Proposing a rewrite with per-change rationale and source URLs
4. Validating the rewrite — for testable artifacts, an autonomous Karpathy-style binary-assertion eval loop with git commit/reset bookkeeping; for non-testable artifacts, deterministic format validation
5. Confirming once at the very end with a before/after score table, the diff, and the cited sources — only the user's explicit "yes" causes the final write

Run autonomously between steps 1 and 4. Stop only at step 5.

Phase 0 — Read Inputs and Set Up Workspace

The user will name a target artifact (a path, or a phrase like "my copywriting skill" — resolve it). Resolution rules: