cap-evolve
Review Skills in skillberry-ai/cap-evolve, with license, maintenance context, and source paths.
- Skills
- 5
- Repository stars
- 36
- Identity status
- Source-linked
Provenance
Source and identity
- Profile type
- Repository
- Canonical name
- cap-evolve
- Public sources
- 1
- License context
- Apache-2.0
Source entries
Agent Skills from cap-evolve
Repository stars and maintenance signals provide context, but do not automatically become an individual Skill's quality score.
skillberry-ai/cap-evolve
gepa
Runs the real GEPA optimization loop (arXiv:2507.19457) — sample-efficient reflective Pareto search. Use when rollouts are expensive and the scorer gives informative per-task feedback, and you want the most quality per evaluation. Each iteration samples a parent from a per-instance Pareto frontier, evaluates it on a cheap minibatch of train tasks with full traces, builds a reflective dataset over the failures, asks the optimizer for one targeted component edit, re-checks the child on the same mi
skillberry-ai/cap-evolve
intake
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 capability to optimize, which runner/optimizer/algorithm to use, and where the data is; scaffolds .capevolve/project/ (adapter stub, capevolve.yaml, PROJECT.md); and for every NEEDED input that is missing, asks the user (quoting path, how to retrieve it, alternatives) rather than fabricating it.
skillberry-ai/cap-evolve
mcp-tool
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 mis-selects them or fills arguments wrong. Only safe edits are permitted — tool/parameter documentation, in-description examples, and adding or removing tools from the exposed set. The wire schema and tool code are NOT editable here (the server owns them).
skillberry-ai/cap-evolve
system-prompt
Optimize an agent's system prompt or policy text — the instructions that shape its behavior. Use when the thing you want to improve is a prompt/policy file (not tools or a skill package). Covers what is safely editable, how prompt wording changes agent behavior, common failure modes (over-long preambles, conflicting instructions, missing output contracts), and what to measure. Provides concrete materialize/apply/validate handlers for prompt artifacts.
skillberry-ai/cap-evolve
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, or has a confusing/redundant toolset. You may edit tool names, descriptions, parameter docs, in-description examples, the JSON schema/API, the tool code itself, ADD tools (including composite tools that call existing tools), and REMOVE tools — all under an action policy so risky edits can be locked off.
Pinned paths
Every entry links to a specific source path and commit when available.
Repository context
Activity, license, and repository-level popularity are shown as context.
Open the source
Inspect the public repository