GitHub collection
skillberry-ai/cap-evolve
Imported from GitHub — is this yours?
22 skills imported from this repository.
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.
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 a
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 be
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 ite
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 consoli
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
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
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
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, para
spa
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: spa`, or when you need to
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
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 tas
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. Report
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 — Inp
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 +
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 sa
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 algorithm
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-evolv
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 someo
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".
swebench-solver
Use when fixing a bug in an open-source repository given a GitHub issue description. Analyzes the problem, locates the relevant code, and produces a minimal unified diff patch.
<skill-name>
<One paragraph. WHAT this skill does and WHEN an agent should reach for it. This is the host's activation signal, so be concrete and self-contained — an agent decides whether to load the skill from this text alone.>