by fastxyz · MCP Server · ★ 85
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
/plugin marketplace add fastxyz/skill-optimizer
/plugin install skill-optimizer@skill-optimizer
Taken from the project's README on GitHub.
None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 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 | 85 |
| Forks | 14 |
| Language | TypeScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 72/100 |
| Open Issues | 15 |
| Last Updated | 2026-05-28 |
| Created | 2026-03-06 |
| Platforms | cli, mcp, node |
| Est. Tokens | ~150k |
skill-optimizer Docker workbench and Agent Skill for running deterministic evals against agent skills. Use this repo in two ways: Install the skill/plugin into your agent so it can author and debug eval suites. Run the local CLI to execute cases and suites in Docker against OpenRouter models. Installation Installation differs by agent.
These tools work well together with skill-optimizer for enhanced workflows:
Looking for a skill-optimizer alternative? If you're comparing skill-optimizer 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.
C++ MCP SDK - build Model Context Protocol (MCP) servers and clients in C++ / CPP. Enterprise-grade security,
An LLM trading agent that shows its work: the chart, the prompt, the memory it retrieved, and every loss. Pape
Litefuse - Agent Observability and Evaluation Platform
A small, powerful, open-source CLI coding agent that works with open models.
All-in-one MCP server that can connect your AI agents to any native endpoint, powered by UTCP
We handle what engineers and IDEs won't: generating and maintaining technical documentation for your codebase,
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 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: