Harness Evolver Skills
Diagnose and improve agent prompts, routing, retrieval, and orchestration.
Includes the six public harness namespace skills from the author’s plugin; repository development helpers are separate.
Use cases
- Diagnose an agent run
- Evaluate a harness change
How to use
Use the author’s plugin setup and keep shared orchestration resources. Preserve harness namespace names while adapting safe installation directories for the host.
Skills
harness:certify
Use when the user wants to verify that the evolved agent's score is stable and reliable. Runs evaluation multiple times and reports mean ± std.
raphaelchristi/harness-evolverharness:deploy
Use when the user is done evolving and wants to finalize, clean up, tag the result, or push the optimized agent.
raphaelchristi/harness-evolverharness:evolve
Use when the user wants to run the optimization loop, improve agent performance, evolve the agent, or iterate on quality. Requires .evolver.json to exist (run harness:setup first).
raphaelchristi/harness-evolverharness:health
Use when the user wants to check dataset quality, diagnose eval issues, or before running evolve. Checks size, difficulty distribution, dead examples, coverage, and splits. Auto-corrects issues found.
raphaelchristi/harness-evolverharness:setup
Use when the user wants to set up the evolver in their project, optimize an LLM agent, improve agent performance, or mentions evolver for the first time in a project without .evolver.json.
raphaelchristi/harness-evolverharness:status
Use when the user asks about evolution progress, current scores, best version, how many iterations ran, or whether the loop is stagnating.
raphaelchristi/harness-evolver