self-improvement loops
auto-fix+3.7
memory updatedpass+0.2#4021
prompts tunedpass+3.2%#4022
regression caughtfail-0.4#4023
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, which runs this loop automatically across your whole team.
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.
quality loop
Go from one skill to an automated self-improvement system
Warp Factories brings the infrastructure to run this loop continuously across your whole team's agent conversations.
- Run self-improvement automatically across your entire team's agent conversations
- Configure the scoring metrics your team cares about: test coverage, verbosity, task compliance, and more
- Benchmark your agent setup against real tasks from your team's repositories
- Track velocity, cost-per-PR, and quality scores with dashboards and APIs
"warp factories drove our cost per agent pr down by 30%."
— vp engineering, series c infrastructure company
early access
Request early access
Set up your first factory with early access.
get up to $10,000 in free factory usage