harness-evolver
Points at an LLM agent codebase and autonomously improves its prompts, routing, tools and architecture. It tests each change against LangSmith evaluations, so you do not tune agents by hand.
9 skills57
@raphaelchristiPlugins
1@raphaelchristiSkills
9certify
Use when the user wants to verify that the evolved agent's score is stable and reliable. Runs evaluation multiple times and…
@raphaelchristideploy
Use when the user is done evolving and wants to finalize, clean up, tag the result, or push the optimized agent.
@raphaelchristidev-dry-run
Use when the user wants to smoke-test the evolve pipeline, test tools, or verify the plugin works end-to-end. Also use when the…
@raphaelchristidev-release
Use when the user wants to release a new version, publish to npm, create a GitHub release, bump version, or tag a release. Also…
@raphaelchristidev-validate
Use when the user wants to validate the plugin, check integrity, verify cross-references, or before a release. Also use when the…
@raphaelchristievolve
Use when the user wants to run the optimization loop, improve agent performance, evolve the agent, or iterate on quality.…
@raphaelchristihealth
Use when the user wants to check dataset quality, diagnose eval issues, or before running evolve. Checks size, difficulty…
@raphaelchristisetup
Use when the user wants to set up the evolver in their project, optimize an LLM agent, improve agent performance, or mentions…
@raphaelchrististatus
Use when the user asks about evolution progress, current scores, best version, how many iterations ran, or whether the loop is…
@raphaelchristiAgents
6harness-architect
AgentUse this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes…
@raphaelchristiharness-consolidator
AgentBackground agent for cross-iteration memory consolidation. Runs after each iteration to extract learnings and update…
@raphaelchristiharness-critic
AgentUse this agent when scores converge suspiciously fast, evaluator quality is questionable, or the agent reaches high scores in few…
@raphaelchristiharness-evaluator
AgentUse this agent to evaluate experiment outputs using LLM-as-judge. Reads run inputs/outputs from LangSmith via langsmith-cli,…
@raphaelchristiharness-proposer
AgentSelf-organizing agent optimizer. Investigates a data-driven lens (question), decides its own approach, and modifies real code in…
@raphaelchristiharness-testgen
AgentUse this agent to generate test inputs for the evaluation dataset. Spawned by the setup skill when no test data exists.
@raphaelchristiIs this you? Claim your profilePut a plugin at the top of Plugins, from $9