Auto-improve any OpenClaw skill using iterative prompt optimization. Inspired by Karpathy's autoresearch method. Run when asked to improve, optimize, or auto-tune any skill. Runs a loop — score → change → test → keep/revert — until target quality is reached. Fully autonomous once started.
Auto-improve any skill file in this workspace using iterative, scored prompt optimization.
cd /Users/jacopo/.openclaw/workspace-bertuccio/skills/autoresearch
python3 scripts/autoresearch.py \
--skill /path/to/SKILL.md \
--checklist inputs/my-checklist.json \
--inputs inputs/my-inputs.json \
--max-rounds 30 \
--target 0.95 \
--dashboard \
--out /path/to/improved-SKILL.md
[
{"question": "Does the output include a specific number or result? (not vague promises)"},
{"question": "Is the output free of buzzwords like 'revolutionary', 'cutting-edge', 'synergy'?"},
{"question": "Does the output include a clear, specific call to action?"},
{"question": "Is the output under 200 words?"},
{"question": "Does the first line address a specific pain point?"}
]
3-6 questions is the sweet spot. Too many and the skill overfits.
[
"Write landing page copy for an AI productivity tool for freelancers",
"Write landing page copy for a B2B SaaS that automates invoicing",
"Write landing page copy for a fitness app targeting busy parents"
]
Pass --dashboard to get a live HTML dashboard at:
skills/autoresearch/autoresearch-dashboard/index.html
Auto-refreshes every 8 seconds. Shows:
| File | Description |
|---|---|
improved-SKILL.md | Best version found (saves as you go) |
backup-SKILL.md | Original skill, untouched |
autoresearch-log.json | Full history: every round, score, change, keep/revert |
autoresearch-dashboard/ | Live HTML dashboard |
Good checklist questions are:
Bad questions:
ANTHROPIC_API_KEY set in environmentpip3 install anthropicautoresearch-log.json is the most durable artifact — hand it to a future model to continue where this one left off