From episteme
Iteratively improves a copied lab skill candidate against explicit evaluation goals, recording revisions and tradeoffs. Promotes manually only.
How this skill is triggered — by the user, by Claude, or both
Slash command
/episteme:skill-lab-autoresearchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill only for private skill-lab work inside `~/episteme`.
Use this skill only for private skill-lab work inside ~/episteme.
This wrapper is inspired by olelehmann100kMRR/autoresearch-skill, but it is adapted for a private lab workflow where live skills are never edited directly.
Before doing any work, collect or confirm:
target_candidate_path: path to a copied candidate SKILL.md under labs/skills/<skill-name>/candidate/eval_goal: what improvement is being optimizediteration_cap: maximum number of iterationsoutput_dir: path under labs/skills/<skill-name>/runs/If any of these are missing, stop and ask for them.
Refuse the task if target_candidate_path points anywhere inside:
skills/custom/skills/vendor/~/.claude/skills/~/.codex/skills/Refuse the task if output_dir is not inside labs/skills/<skill-name>/runs/.
Refuse any request to overwrite a live skill automatically.
SKILL.md.output_dir.Produce:
Promotion into the live skill set is always manual.
Do not copy changes into skills/house or skills/vendor.
npx claudepluginhub junjslee/episteme --plugin epistemeAutonomously optimizes skill prompts using a mutate/score/keep evolutionary loop with git-based revert. Useful for improving SKILL.md performance over time.
Autonomously optimizes Claude Code skills by iteratively running them on test inputs, scoring against binary evals, reflecting on failures to mutate prompts, and archiving improvements. Invoke via /auto-optimize for skill enhancement or autoresearch.
Iterates on a skill by running it against a behavioral spec with and without proposed changes via parallel-eval harness, then ships the winning version.