Skills
Warp's self-improving agents run a second 'improver' skill on a schedule that rewrites the first skill from PR feedback
Warp describes a two-skill loop: a base skill holding domain instructions, and an outer improver skill that runs on a schedule, pulls accumulated human feedback, compares the agent's suggestions against what humans actually did, and opens PRs editing the base skill. Their operating rules are specific: write principles not rules, always include the rationale so the agent generalizes, keep skills small and reference external files, and weight one senior engineer's detailed PR comment above high-volume cursory signal. Warp reports 10M+ Claude Code sessions internally and 400K+ per week, and calls the improver skill the reusable half of the pattern.
↳ Follow the thread