evals on your own work
pass96%
8/13 07:03fail0.4$0.39
8/13 07:02pass0.8$0.53
8/13 07:02pass0.8$0.46
Improve your agent skills
Run /skill-doctor on your own setup to score past agent conversations and get real improvements to your skills. Supports Claude Code, Codex, and Warp.
Powered by the self-improvement system behind Warp Factories.
process
How it works
/skill-doctor runs against your personal coding agent setup to review past conversations and propose merge-ready improvements to your skills.
- 01
Aggregate
Your agent aggregates past conversation transcripts for review (Claude Code, Codex, or Warp).
- 02
Score
Subagents score these conversations against tested rubrics for efficiency, code quality, and skill coverage. See the scorers
- 03
Improve
Your agent reviews these scores to propose improvements to your skills.
"warp factories drove our cost per agent pr down by 30%."
— vp engineering, series c infrastructure company
quality loop
Use Warp Factories for automatic self-improvement
evals, benchmarks, and self-improvement loops drive measurable gains.
benchmarks across models
best1.00x
Claude Fable 5pass1.00x$0.53
GPT-5.6 Solpass0.94x$0.41
Gemini 3.6 Flashfail0.89x$0.32
self-improvement loops
auto-fix+3.7
memory updatedpass+0.2#4021
prompts tunedpass+3.2%#4022
regression caughtfail-0.4#4023
early access
Request early access
Set up your first factory with early access.
get up to $10,000 in free factory usage