Menu
Evaluate MCP servers and agent tools with structured test cases and metrics. Use when benchmarking tools or validation suites.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Turn CHANGELOG, git history, and incident dialogue into team rules under .cursorGrowth/team-experience (LLM-only, no parsing). Use for 沉淀规则, 团队经验, 从 changelog 学习, 反复出现的 bug.
Discover and route to project skills under .cursor/skills. Use when matching tasks to skills or listing available skills.
Create algorithmic art and interactive p5.js visualizations. Use when generating generative art, creative coding, or visual experiments.
Design RESTful, GraphQL, and microservice APIs with OpenAPI specs, consistency checks, and security review. Use when designing or reviewing API contracts, endpoints, or API documentation.
Plan and implement API testing with contracts, mocks, and automation. Use when validating endpoints, integration tests, or API quality gates.
Backend architecture, databases, APIs, caching, and deployment patterns. Use for server-side design, implementation, or review.
| name | evaluation |
| description | Evaluate MCP servers and agent tools with structured test cases and metrics. Use when benchmarking tools or validation suites. |
基于 Model Context Protocol 评估规范 | 下载时间: 2026-01-16
/skill-name or when the agent selects this skill from context.references/full-guide.md in this skill directory for full workflows, examples, and checklists (progressive disclosure).scripts/ when present, using paths relative to this skill folder./master skill:evaluation when the project uses the command center..cursor/skills/evaluation/references/full-guide.md.cursor/features/skills/skills/registry.json