mcp-developer
Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources. Invoke to implement tool handlers, configure resource providers, set up stdio/HTTP/SSE transport layers, validate schemas with Zod or Pydantic, debug protocol compliance issues, or scaffold complete MCP server/client projects using TypeScript or Python SDKs.
90
100%
Does it follow best practices?
Impact
81%
1.15xAverage score across 6 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly defines its scope around MCP server/client development. It provides comprehensive trigger terms covering the full MCP ecosystem, explicitly states when to use it, and lists specific concrete actions. The technical specificity (Zod, Pydantic, stdio/HTTP/SSE) creates a distinct niche that won't overlap with general development skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'implement tool handlers, configure resource providers, set up stdio/HTTP/SSE transport layers, validate schemas with Zod or Pydantic, debug protocol compliance issues, scaffold complete MCP server/client projects'. | 3 / 3 |
Completeness | Clearly answers both what (implement handlers, configure providers, set up transport, validate schemas, debug, scaffold) AND when ('Use when building, debugging, or extending MCP servers or clients') with explicit trigger guidance at the start. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'MCP servers', 'MCP clients', 'tool handlers', 'resource providers', 'stdio/HTTP/SSE transport', 'Zod', 'Pydantic', 'TypeScript', 'Python SDKs', 'protocol compliance'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche around MCP (Model Context Protocol) specifically. The combination of MCP-specific terminology, transport layers, and SDK references makes it unlikely to conflict with general coding or API skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that demonstrates best practices across all dimensions. It provides immediately actionable code examples in both TypeScript and Python, maintains a clear workflow with explicit validation checkpoints and feedback loops, and efficiently organizes content with well-signaled references to detailed documentation. The MUST DO/MUST NOT DO constraints provide clear guardrails without being verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of concepts Claude already knows. Every section serves a purpose with no padding or unnecessary context about what MCP is or how protocols work. | 3 / 3 |
Actionability | Provides fully executable TypeScript and Python code examples that are copy-paste ready, includes specific CLI commands for initialization and testing, and shows concrete expected input/output for tool calls. | 3 / 3 |
Workflow Clarity | The 6-step core workflow is clearly sequenced with an explicit feedback loop in step 5 that covers schema validation failures and malformed responses with specific fix-and-retry guidance. | 3 / 3 |
Progressive Disclosure | Clean structure with a reference table pointing to one-level-deep topic files (protocol, SDKs, tools, resources) with clear 'Load When' guidance. Main content stays focused on quick start while advanced topics are properly delegated. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jeffallan/claude-skills
- Commit
5b76101
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.