by skillberry-ai · MCP Server · ★ 68
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
git clone https://github.com/skillberry-ai/cap-evolve.git
pip install ./core # package: cap-evolve-core · CLI: cap-evolve · zero runtime depsTaken from the project's README on GitHub.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 68 |
| Forks | 18 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 64/100 |
| Open Issues | 127 |
| Last Updated | 2026-11-04 |
| Created | 2026-06-15 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~17k |
cap-evolve watch capability evolve cap-evolve improves an AI agent's prompts, tools, and skills by learning from failed evaluation traces. You bring the agent and the eval you already have. cap-evolve runs the loop — evaluate → diagnose the failures → propose an edit → keep it only if it beats a held-out split by a significant margin → commit — and reports one honest number.
Looking for a cap-evolve alternative? If you're comparing cap-evolve with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Reusable project context and specialist workflows for the AI tools you already use. Agents, skills, rules and
Turn feature specs into merged PRs with a self-supervising swarm of coding agents — parallel execution, isolat
Automated loop driver, slash commands, council automation, MCP browser bridge, and portfolio governance for Cl
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Imp
An introduction to the world of AI Agents
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: