mcp-developer

Name: mcp-developer
Rating: 67 (1 reviews)
Author: jeffallan

tessl i github:jeffallan/claude-skills --skill mcp-developer

github.com/jeffallan/claude-skills

Use when building MCP servers or clients that connect AI systems with external tools and data sources. Invoke for MCP protocol compliance, TypeScript/Python SDKs, resource providers, tool functions.

Review Score

67%

Validation Score

12/16

Implementation Score

42%

Activation Score

90%

SKILL.md

Review

Evals

Generated

13 days ago

Warnings & errors only

Criteria	Score
metadata_version	'metadata' field is not a dictionary
license_field	'license' field is missing
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata
body_examples	No examples detected (no code fences and no 'Example' wording)

Overall Assessment

This skill has good structural organization and progressive disclosure through its reference table, but critically lacks actionable content. It reads more like a role description than a skill that teaches Claude how to perform specific tasks. The absence of any code examples, concrete commands, or executable guidance significantly limits its utility.

Suggestions

Add concrete code examples for at least one TypeScript and one Python MCP server implementation showing basic tool/resource setup
Replace abstract constraints like 'Implement JSON-RPC 2.0 protocol correctly' with specific patterns or code snippets showing correct implementation
Add validation checkpoints to the workflow with specific commands (e.g., 'Test with: npx @modelcontextprotocol/inspector')
Remove or condense the 'Role Definition' and 'Knowledge Reference' sections which don't provide actionable guidance

Dimension	Score	Reasoning
Conciseness	2/3	The skill is reasonably efficient but includes some unnecessary sections like 'Role Definition' that restates what Claude already knows, and 'Knowledge Reference' which is essentially a keyword list that doesn't add actionable value.
Actionability	1/3	The skill provides no concrete code examples, commands, or executable guidance. It describes what to do at a high level ('Implement JSON-RPC 2.0 protocol correctly') but never shows how. The workflow is abstract and the constraints are vague directives without implementation details.
Workflow Clarity	2/3	The 5-step core workflow provides a reasonable sequence but lacks validation checkpoints, specific commands, or feedback loops. For a protocol implementation skill involving security and compliance, the absence of explicit verification steps is a gap.
Progressive Disclosure	3/3	The skill effectively uses a reference table with clear one-level-deep links to detailed guidance files, organized by topic with clear 'Load When' conditions. This is well-structured progressive disclosure.

Overall Assessment

This is a solid skill description with excellent trigger terms and clear when/what guidance for the MCP domain. The main weakness is that it lacks specific concrete actions (verbs describing what the skill actually does), instead relying on domain terminology. Adding action verbs like 'implement', 'configure', 'debug' would strengthen specificity.

Suggestions

Add concrete action verbs describing what the skill does, e.g., 'Implement MCP servers, configure resource providers, create tool functions, debug protocol compliance issues.'

Dimension	Score	Reasoning
Specificity	2/3	Names the domain (MCP servers/clients, AI systems, external tools) and mentions some technical elements (TypeScript/Python SDKs, resource providers, tool functions), but doesn't list concrete actions like 'create', 'configure', 'debug', or 'implement'.
Completeness	3/3	Explicitly answers both what ('building MCP servers or clients that connect AI systems with external tools and data sources') and when ('Use when building MCP servers or clients', 'Invoke for MCP protocol compliance'). Has clear trigger guidance.
Trigger Term Quality	3/3	Includes strong natural keywords users would say: 'MCP servers', 'MCP clients', 'MCP protocol', 'TypeScript/Python SDKs', 'resource providers', 'tool functions', 'external tools and data sources'. Good coverage of technical terms developers would use.
Distinctiveness Conflict Risk	3/3	MCP (Model Context Protocol) is a specific niche with distinct terminology. The combination of 'MCP protocol', 'resource providers', and 'tool functions' creates a clear, unique trigger profile unlikely to conflict with general coding or API skills.