cap-evolve

In the author's own words, from each skill's SKILL.md.

• arithmetic-answers

  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.

  examples/toy_skill/seed_capability/SKILL.md on GitHub (opens in a new tab)

• agent-optimize

  Free-form optimization algorithm for agent orchestration mode: the conversational agent owns the whole search — proposing capability edits itself, screening them cheaply, gating each on full val, and sealing test once. Use when orchestration_mode is agent and algorithm_skill is agent-optimize. For a deterministic loop use hill-climb, gepa or skillopt instead.

  skills/algorithms/agent-optimize/SKILL.md on GitHub (opens in a new tab)

• evograph

  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 that evograph never applied, and everything else it did (failure clustering, reje…

  skills/algorithms/evograph/SKILL.md on GitHub (opens in a new tab)

• gepa

  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 are expensive and the scorer returns informative per-task feedback, and you wan…

  skills/algorithms/gepa/SKILL.md on GitHub (opens in a new tab)

• hill-climb

  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 --focus all (every failing val task), cyclic (one task at a time), or hardest-first…

  skills/algorithms/hill-climb/SKILL.md on GitHub (opens in a new tab)

• skillopt

  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 current best; acceptance is the val significance gate. Use when a run should anneal f…

  skills/algorithms/skillopt/SKILL.md on GitHub (opens in a new tab)

• mcp-tool

  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 examples, and curating which of the server's tools are exposed to the model. Only those…

  skills/capabilities/mcp-tool/SKILL.md on GitHub (opens in a new tab)

• skill-package

  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 deterministic bundled code. Checks every edit against the skill-creator authoring…

  skills/capabilities/skill-package/SKILL.md on GitHub (opens in a new tab)

• system-prompt

  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 the safe edit classes (rewrite, consolidate, add a sourced rule, reorder, tighten…

  skills/capabilities/system-prompt/SKILL.md on GitHub (opens in a new tab)

• tools

  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, function-calling accuracy, and adding or removing tools.

  skills/capabilities/tools/SKILL.md on GitHub (opens in a new tab)

• wiki

  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 `memory_skill: wiki` in capevolve.yaml (default is `md-files`). Copied into every iteration's working dir as `./guidance/memory-wiki/` when selected; read this before writing anything under the run dir's `wiki/`.

  skills/memory/wiki/SKILL.md on GitHub (opens in a new tab)

• run-optimizer

  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 optimizer for every run; pick the concrete agent with --name (or optimizer_skill in t…

  skills/optimizers/run-optimizer/SKILL.md on GitHub (opens in a new tab)

• orchestrate

  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 stop (budget/stall), and surfaces the honest test number at the end. Reads cape…

  skills/orchestrate/orchestrate/SKILL.md on GitHub (opens in a new tab)

• using-cap-evolve

  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 cases", "get this prompt's accuracy up on my evals" — even when they never say "opti…

  skills/orchestrate/using-cap-evolve/SKILL.md on GitHub (opens in a new tab)

• baseline

  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 seed stops the run before it spends budget.

  skills/phases/baseline/SKILL.md on GitHub (opens in a new tab)

• diagnose

  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 clusters the failures by a (failure-site, violated-expectation) signature, ranked…

  skills/phases/diagnose/SKILL.md on GitHub (opens in a new tab)

• evaluate

  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 when trials > 1. Never touches the test split (that is finalize's sealed job).

  skills/phases/evaluate/SKILL.md on GitHub (opens in a new tab)

• finalize

  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 must be.

  skills/phases/finalize/SKILL.md on GitHub (opens in a new tab)

• gate

  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.

  skills/phases/gate/SKILL.md on GitHub (opens in a new tab)

• implement-and-check

  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 involved skill's check.py, listing exactly what is still stubbed or non-deterministic…

  skills/phases/implement-and-check/SKILL.md on GitHub (opens in a new tab)

• intake

  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 capability against an eval and no project exists yet — "set up a run", "start o…

  skills/phases/intake/SKILL.md on GitHub (opens in a new tab)

• report

  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".

  skills/phases/report/SKILL.md on GitHub (opens in a new tab)

• blackbox

  The Skillberry proxy intervention — put the optimized capability in the Skillberry Store and let the Skillberry Proxy-Agent (SPA) inject it into the agent's LLM calls, so the benchmark never sees skill files. Use when a capevolve.yaml sets `intervention: blackbox`, or when you need to provision, start, deploy to, stop or clean that stack.

  skills/interventions/llm-proxies/blackbox/SKILL.md on GitHub (opens in a new tab)

• my_skill

  No description in the SKILL.md.

  examples/tau2_custom/blackbox/seed_capability/my_skill/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• agentsby wshobson Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi 40.9k stars · 30 skills
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills
• paperclipby paperclipai The open-source app everyone uses to manage agents at work 103k stars · 30 skills
• awesome-claude-skillsby ComposioHQ A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows 77.2k stars
• marketingskillsby coreyhaines31 Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering. 54.9k stars · 30 skills
• distillyby titanwings Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）. 25.7k stars · 1 skill