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.

1.15x

Quality

92%

Does it follow best practices?

Impact

81%

1.15x

Average score across 6 eval scenarios

Securityby

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 a specific technical domain (MCP servers/clients), lists concrete actions, and provides explicit trigger guidance. It uses appropriate third-person voice throughout and includes rich, natural trigger terms that developers in this space would use. The description is comprehensive without being unnecessarily verbose.

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 using TypeScript or Python SDKs.	3 / 3
Completeness	Clearly answers both 'what' (implement tool handlers, configure resource providers, set up transport layers, validate schemas, debug protocol issues, scaffold projects) and 'when' ('Use when building, debugging, or extending MCP servers or clients' and 'Invoke to...'). The explicit 'Use when' clause is present at the start.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms a developer would use: 'MCP servers', 'MCP clients', 'tool handlers', 'resource providers', 'stdio', 'HTTP', 'SSE', 'transport layers', 'Zod', 'Pydantic', 'TypeScript', 'Python SDKs', 'protocol compliance'. These are the exact terms users working in this domain would naturally mention.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche around MCP (Model Context Protocol) specifically. The combination of MCP-specific terminology (tool handlers, resource providers, protocol compliance) with specific transport layers and SDK references makes it very unlikely to conflict with general coding or API skills.	3 / 3
	Total	12 / 12 Passed

Implementation

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured MCP skill with strong actionability through complete, executable examples in both TypeScript and Python, clear workflow sequencing with feedback loops, and excellent progressive disclosure via the reference table. The main weakness is moderate verbosity in the constraints section, which lists generic best practices Claude already knows, and the persona description at the top adds no value.

Suggestions

Trim the MUST DO/MUST NOT DO lists to only MCP-specific constraints (e.g., remove generic advice like 'Add authentication' and 'Hardcode credentials' that Claude already knows).

Remove the opening persona sentence ('Senior MCP developer with deep expertise...') as it wastes tokens without adding actionable guidance.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient but includes some unnecessary content. The MUST DO/MUST NOT DO lists contain generic software engineering advice (e.g., 'Add authentication and authorization', 'Hardcode credentials or secrets') that Claude already knows. The opening sentence describing the persona is unnecessary. However, the code examples and reference table are lean.	2 / 3
Actionability	Provides fully executable TypeScript and Python examples with real SDK imports, Zod/Pydantic schema validation, transport setup, and tool/resource registration. The expected tool call flow showing JSON-RPC request/response is a strong concrete addition. Scaffold commands are copy-paste ready.	3 / 3
Workflow Clarity	The core workflow is clearly sequenced with numbered steps. Step 5 (Test) includes an explicit feedback loop: schema validation fails → inspect error → fix → re-run inspector, and malformed response → check transport → fix handler → re-test. This covers the validation checkpoint requirement well for a protocol-compliance context.	3 / 3
Progressive Disclosure	Excellent use of a reference table with clear 'Load When' guidance pointing to one-level-deep reference files for protocol, TypeScript SDK, Python SDK, tools, and resources. The main skill stays as an overview with working examples while deferring detailed guidance to separate files.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: 3d95bb1

Reviewed: 8 days ago

Table of Contents

Discovery Implementation Validation

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.