| name | autoresearch |
| description | Run Karpathy-style autoresearch optimization on any content. Generates 50+ variants, scores with a 5-expert simulated panel, evolves winners through multiple rounds, outputs optimized version + full experiment log. Use when optimizing landing pages, email sequences, ad copy, headlines, form pages, CTA text, or any conversion-focused content. Triggers on "optimize this page", "run autoresearch", "score these variants", "A/B test this copy". |
| when_to_use | Use when pre-launch optimizing conversion-focused content — landing pages, email sequences, ad copy, headlines, form pages, or CTA text — by generating and scoring 50+ variants before shipping. Triggers on "optimize this page", "run autoresearch", "score these variants", or "A/B test this copy".
Not when: you need post-launch real-traffic A/B testing (that requires real analytics, not simulated scoring). Not when the task is designing or analyzing a live GROWTH EXPERIMENT or A/B test program — experiment management, logged data points, statistical significance — use `growth-engine`. Not when the task is auditing a LIVE landing-page URL for conversion (fetch the page, then score it across CRO dimensions like CTA visibility, social proof, trust signals, form friction) rather than generating and optimizing copy variants pre-launch — use `conversion-ops`. Not when you need a general quality gate on existing content — use `content-ops` instead.
|
| compatibility | Requires Bash (Python 3 where scripts are invoked). Works in Claude Code and Codex via install.sh. |
Autoresearch Skill
Karpathy-style optimization loops for any conversion-focused content. No traffic needed. Simulated expert panel. Minutes, not weeks.
The sequence: Run autoresearch FIRST to hit 85+ simulated score. Then deploy. Then validate with real traffic.
What You'll Produce
Every run outputs 3 files:
| File | Purpose |
|---|
{name}-optimized.{ext} | The winning optimized content |
data/{name}-experiments.json | Full experiment log — all variants + all scores |
data/{name}-optimization-report.md | Human-readable summary with winner rationale |
Core rules
- Intake: parse content type from file extension (HTML → landing/form page; markdown → email/ad copy). List all optimizable elements and confirm with user before starting.
- Score every variant against the 5-expert panel in a single batched API call per round — never one call per variant.
- Run up to 3 rounds per element; stop early when top variant hits the minimum score threshold (default: 80).
- Cross-breed only after each element has its own winner — premature cross-breeding creates incoherent combinations.
- Write 3 output files: optimized content, experiments JSON, optimization report.
- Report back: winning score, biggest score jump, top 2 runner-ups, file paths, next step.
User Options
| Option | Default | Description |
|---|
elements | all | Which elements to optimize |
variants_per_round | 10 | How many variants per round |
min_score | 80 | Stop when this score is hit |
rounds | 3 | Max rounds before stopping |
auto_apply | false | Overwrite source file with winners |
content_type | auto-detect | Force a content type if auto-detect is wrong |
Quality Gates
- < 70: Don't ship. Something fundamental is broken.
- 70-79: Marginal. One more round targeting the lowest-scoring dimension.
- 80-84: Good. Shippable. Validate with real traffic.
- 85-89: Strong. Ship with confidence.
- 90+: Rare. Ship immediately.
Anti-Patterns
- Never call the API once per variant. Always batch. A 10-variant round = 1 call.
- Don't over-optimize for one dimension — a 95 clarity + 45 trust is a misleading overall score.
- Don't run more than 5 rounds. If not hitting 80 after 3, the problem is strategic, not tactical.
References
Related skills
- content-ops — quality scoring gate; run after autoresearch optimization
- conversion-ops — audits a LIVE landing-page URL across CRO dimensions; use it instead when scoring a live page rather than optimizing copy variants pre-launch
