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.

Quality

88%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

This is a solid, actionable MCP development skill with executable code examples in both TypeScript and Python, a clear workflow with feedback loops, and a well-designed reference table for progressive disclosure. Its main weaknesses are some verbosity in the constraints section (generic best practices Claude already knows) and the complete absence of the five referenced bundle files, which undermines the progressive disclosure architecture.

Suggestions

Remove or significantly trim the MUST DO/MUST NOT DO lists — items like 'Add authentication and authorization' and 'Don't hardcode credentials' are generic software engineering practices Claude already knows. Keep only MCP-specific constraints.

Provide the five referenced files (references/protocol.md, typescript-sdk.md, python-sdk.md, tools.md, resources.md) to support the progressive disclosure structure, or remove the reference table if they won't be created.

Remove the opening sentence ('Senior MCP developer with deep expertise...') as it describes a persona rather than providing 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', 'Don't hardcode credentials') that Claude already knows. The opening sentence describing what an MCP developer is adds no value. However, the code examples and workflow are reasonably tight.	2 / 3
Actionability	The skill provides fully executable TypeScript and Python code examples with proper imports, schema validation, transport setup, and resource registration. It includes concrete CLI commands for project initialization and testing, plus an example JSON-RPC request/response flow. The code is copy-paste ready.	3 / 3
Workflow Clarity	The core workflow is clearly sequenced with numbered steps from requirements analysis through deployment. Step 5 (Test) includes an explicit feedback loop: schema validation failure → inspect error → fix → re-run, and malformed response → check transport → fix → re-test. This is well-structured for a multi-step development process.	3 / 3
Progressive Disclosure	The reference table with 'Load When' guidance is well-designed for progressive disclosure, but no bundle files were provided, meaning all five referenced files (references/protocol.md, typescript-sdk.md, python-sdk.md, tools.md, resources.md) are missing. The SKILL.md references paths that don't exist in the bundle, undermining the progressive disclosure structure. The inline content is reasonably organized but the MUST DO/MUST NOT lists could be in a separate reference.	2 / 3
	Total	10 / 12 Passed

Description

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 specific, concrete actions, includes rich trigger terms that developers would naturally use, and explicitly states both what the skill does and when to invoke it. The description is well-structured, concise, and occupies a distinct niche that minimizes conflict risk with other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: implement tool handlers, configure resource providers, set up transport layers (stdio/HTTP/SSE), validate schemas with Zod or Pydantic, debug protocol compliance issues, scaffold complete MCP server/client projects. Very detailed and actionable.	3 / 3
Completeness	Clearly answers both 'what' (implement tool handlers, configure resource providers, validate schemas, debug protocol issues, scaffold projects) and 'when' with an explicit trigger clause: 'Use when building, debugging, or extending MCP servers or clients that connect AI systems with external tools and data sources.'	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', 'Zod', 'Pydantic', 'TypeScript', 'Python', 'SDK', 'protocol compliance'. These are the exact terms users would mention when working in this domain.	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 SDKs and transport layers makes it very unlikely to conflict with general coding or API skills.	3 / 3
	Total	12 / 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: e8be415

Reviewed: 4 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.