Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
This repository also configures its own agents. See what cap-evolve tells them →
Skill Claude CodeCodex
Answers a short arithmetic question with just the number. Use when the user asks to compute a sum, difference, or product and wants only the result back.
Skill Claude Code
Free-form optimization algorithm for agent orchestration mode: the conversational agent owns the whole search — reading a digest, proposing big coherent capability edits against failure-cluster hypotheses, probing only missing cells, promoting or pruning on a posterior, merging complementary branches, and sealing test…
Skill Claude Code
Deprecated agent-mode algorithm (evo-graph port): a weakness-graph search that dispatched one solver agent per failure cluster and reverted a whole round on regression. Do not start new runs with it — its per-weakness fan-out is already agent-optimize's sibling fan-out, done behind the honest val significance gate…
Skill Claude Code
Runs the GEPA optimization loop (arXiv:2507.19457) — sample-efficient reflective Pareto search. A cheap train-minibatch pre-gate decides whether a proposal is worth an expensive val evaluation, and parents are sampled from a per-instance frontier so specialists survive instead of being averaged away. Use when rollouts…
Skill Claude Code
Runs a global hill-climb optimization loop where the parent is always the current best candidate and the val significance gate decides acceptance. Use as the algorithm for most runs — the first run on a new project, binary pass/fail scorers, and small task sets. Pick how each iteration's reflection is focused with…
Skill Claude Code
Runs the SkillOpt single-lineage optimization loop, which organizes a hill-climb into epochs over mini-batches of train tasks under a textual learning rate — an integer edit budget that decays on a constant|linear|cosine schedule — and ends each epoch with one extra gated consolidation step. Parent is always the…
Skill Claude Code
Optimize the tool surface of an EXTERNAL MCP server — one the agent talks to but does not implement. Use when an agent wired to an MCP server mis-selects tools, fills arguments wrong, or is offered a noisy 40-tool set it mostly ignores. Covers MCP tool descriptions, per-parameter documentation, in-description…
Skill Claude Code
Optimize an Agent Skill package itself — its SKILL.md (frontmatter + body), its references, and its bundled scripts. Use when the capability under optimization IS a skill, you want the downstream agent to trigger it correctly and follow it without wasted steps, or you want a step the agent keeps skipping turned into…
Skill Claude Code
Optimize an agent's system prompt, developer message, or policy text — the instructions that shape its behavior. Use when the artifact to improve is a prompt or policy file rather than tools or a skill package: the agent lacks a rule, misses the required output format, or applies the wrong decision criterion. Covers…
Skill Claude Code
Optimize an agent's OWN tool surface (tools it implements, not an external MCP server). Use when the agent mis-selects tools, fills arguments wrong, calls the same tool N times in a row, or has a confusing, redundant, or oversized toolset. Covers tool names and descriptions, parameter docs, tool schemas, handler code…
Skill Claude Code needs its repo
Drives any shell-invokable coding agent (Claude Code, Codex, Gemini CLI, opencode, Cursor, Factory Droid, GitHub Copilot CLI, Kimi, Pi, Antigravity, OpenClaw, IBM Bob, or a fully custom command) as the edit proposer in a cap-evolve run, resolving the named optimizer from optimizers/registry.yaml. Use this as the…
Skill Claude Code
Drive the entire cap-evolve pipeline end to end, autonomously. Use when the user wants the whole optimization run with minimal hand-holding. Sequences intake → implement-and-check → baseline → the chosen algorithm loop → finalize → report, enforces the cap-evolve-check hard gate before spending budget, decides when to…
Skill Claude Code
Front door for cap-evolve: routes an optimization request to the right pipeline phase. Use when someone wants an agent, skill, system prompt, tool surface, or MCP toolset to score higher on an eval, benchmark, or task suite — "optimize my skill", "raise the pass rate on these tasks", "my agent keeps failing these…
Skill Claude Code
Establish the starting point. Use after implement-and-check and before any algorithm. Creates the run directory, freezes the seeded train/val/test split (written once), scores the unmodified seed capability on val, and records it as the candidate every algorithm must beat. Reports the remaining headroom so a saturated…
Skill Claude Code
Extract the learning signal from execution traces — the textual analogue of a gradient. Use between evaluation and proposing edits. Reads a candidate's rollouts and traces, separates good signals to keep from bad signals to fix, builds a reflective dataset (per failing task — Inputs, Generated Outputs, Feedback) and…
Skill Claude Code
Score a candidate on a split with honest, variance-aware evaluation. Use whenever you need a number for a candidate (the algorithm calls it internally; you can also call it directly to inspect). Runs the target via the adapter for each task, scores each rollout, aggregates mean + standard error, and reports pass^k…
Skill Claude Code
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. The run dir enforces the seal — a second finalize raises an error — so the headline number is produced once on data the optimizer never saw, the way an honest benchmark result…
Skill Claude Code
Apply the acceptance decision that keeps optimization honest — always on the val split, by default requiring the improvement to exceed the significance bar (Δ > k·SE) so noise is not mistaken for progress. Use to inspect or reproduce a single accept/reject decision; the algorithms apply it internally every iteration.
Skill Claude Code
Runs the hard gate that has to pass before any optimization budget is spent. Use right after intake. Walks the agent through implementing the 3 required adapter methods plus any defaulted hooks that need overriding (and any selected skill's abstract methods), then runs cap-evolve check on the project plus each…
Skill Claude Code
Starts a cap-evolve optimization run. Interviews the user to decide what capability to optimize, which runner/optimizer/algorithm to use, and where the tasks and the scoring source live, then scaffolds .capevolve/project/ (adapter stub, capevolve.yaml, PROJECT.md). Use when someone asks to optimize or improve an agent…
Skill Claude Code
Summarize a run for a human — baseline val → best val → sealed test, the winning candidate, iterations spent, and pass^k. Use after finalize. Writes report.md and prints a compact JSON summary; the source of truth for "did this optimization actually work, and by how much".
Skill Claude Code
Concrete triggers. What situation in the pipeline calls for it.
Skill Claude Code needs its repo
Cross-iteration memory as a weakness graph (weakness nodes + solution cards), extracted from the deprecated evograph algorithm's run-dir format per its own maintainer note. Select via memoryskill: wiki in capevolve.yaml (default is md-files). Copied into every iteration's working dir as ./guidance/memory-wiki/ when…
Skill Claude CodeCodex
Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: