ReddRadar
Agent skill
benchmark
Stars
159
Forks
11
Install this agent skill to your Project
npx add-skill https://github.com/kayba-ai/recursive-improve/tree/main/.claude/skills/benchmark
SKILL.md
../../../recursive_improve/data/BENCHMARK_SKILL.md
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
kayba-ai/recursive-improve
ratchet
159
11
Explore
kayba-ai/recursive-improve
benchmark
159
11
Explore
kayba-ai/recursive-improve
recursive-improve
159
11
Explore
kayba-ai/recursive-improve
ratchet
159
11
Explore
kayba-ai/recursive-improve
recursive-improve
159
11
Explore
kayba-ai/recursive-improve
recursive-improve
End-to-end agent improvement pipeline. Analyzes raw execution traces, extracts insights, manages a skillbook, gathers domain context, defines metrics, builds a rubric, creates a prioritized action plan, presents it for review, and implements approved fixes. Trigger when the user says "improve my agent", "run the improvement pipeline", "apply insights", "/recursive-improve", or when eval/traces/ contains trace files.
159
11
Explore
Didn't find tool you were looking for?