Diagnose
skillberry-ai/cap-evolveExtract the learning signal from execution traces — the textual analogue of a gradient. Use between evaluation and proposing edits. Reads a candidate's val rollouts, separates good signals to keep from bad signals to fix, builds a reflective dataset (per failing task — Inputs, Generated Outputs, Feedback) and groups failures into clusters by shared signature, so the optimizer knows what to change and why.
At a glance
/plugin marketplace add skillberry-ai/cap-evolve
/plugin install diagnose
Also in skillberry-ai/cap-evolve
View the repoFully-agentic, free-form optimization algorithm. Use in agent orchestration mode when you want the conversational agent to own the whole sea...
Establish the starting point. Use after implement-and-check and before any algorithm. Creates the run directory, freezes the seeded train/va...
Score a candidate on a split with honest, variance-aware evaluation. Use whenever you need a number for a candidate (the algorithm calls it...
Score the best candidate on the held-out TEST split exactly once and seal the run. Use as the last evaluation step, after optimization stops...
Apply the acceptance decision that keeps optimization honest — always on the val split, by default requiring the improvement to exceed the s...
Runs the real GEPA optimization loop (arXiv:2507.19457) — sample-efficient reflective Pareto search. Use when rollouts are expensive and the...
Runs a global hill-climb optimization loop where the parent is always the current best candidate and the val significance gate decides accep...
The HARD GATE that must pass before any optimization budget is spent. Use right after intake. Walks the agent through implementing the 4 ada...
Phase 1 of the pipeline — collect inputs and scaffold the run. Use at the very start of any optimization. Interviews the user to decide what...
Optimize an MCP toolset whose server is EXTERNAL (you can't re-implement the tools). Use when the agent talks to tools served over MCP and m...
Drive the entire cap-evolve pipeline end to end, autonomously. Use when the user wants the whole optimization run with minimal hand-holding....
Summarize a run for a human — baseline val → best val → sealed test, the winning candidate, iterations spent, and pass^k. Use after finalize...