mcp-patterns
Model Context Protocol (MCP) server patterns for building integrations with Claude Code. Triggers on: mcp server, model context protocol, tool handler, mcp resource, mcp tool.
82
75%
Does it follow best practices?
Impact
97%
2.15xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xdarkmatter/claude-mods/mcp-patterns/SKILL.mdQuality
Discovery
62%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description has strong trigger terms and occupies a clear niche, making it distinctive and easy to match on relevant keywords. However, it lacks specificity about what concrete actions the skill enables (e.g., creating servers, defining tools, handling requests) and the 'what it does' portion is vague. Adding concrete capabilities and an explicit 'Use when...' clause would significantly improve it.
Suggestions
Replace 'patterns for building integrations' with specific concrete actions, e.g., 'Creates MCP server implementations, defines tool handlers, configures resources and prompts for Claude Code integrations.'
Add an explicit 'Use when...' clause describing scenarios, e.g., 'Use when the user wants to build an MCP server, create custom tools for Claude, or implement Model Context Protocol resources and handlers.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description says 'patterns for building integrations' which is vague. It does not list concrete actions like 'create tool handlers', 'define resources', or 'implement server endpoints'. The phrase 'patterns for building integrations' is abstract and doesn't tell Claude what specific tasks this skill enables. | 1 / 3 |
Completeness | The 'when' is partially addressed via the 'Triggers on:' clause listing keywords, but there is no explicit 'Use when...' guidance describing scenarios. The 'what' is weak — it only says 'patterns for building integrations' without specifying concrete capabilities. The trigger list partially compensates but doesn't fully replace an explicit 'when' clause. | 2 / 3 |
Trigger Term Quality | The description includes good natural trigger terms: 'mcp server', 'model context protocol', 'tool handler', 'mcp resource', 'mcp tool'. These are terms a developer would naturally use when asking about MCP development, and the explicit 'Triggers on:' clause makes them clear. | 3 / 3 |
Distinctiveness Conflict Risk | MCP server development is a clear, specific niche. The trigger terms like 'mcp server', 'model context protocol', 'mcp tool', and 'mcp resource' are highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
87%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 that provides an excellent quick-start template with executable code, clear configuration examples, and well-organized references to deeper content. Its main weakness is the lack of an explicit step-by-step workflow with validation checkpoints for the end-to-end process of building, testing, and deploying an MCP server. The troubleshooting table partially compensates but doesn't replace a proper sequenced workflow.
Suggestions
Add a numbered workflow section (e.g., '## Getting Started Workflow') that sequences: create project → implement server → test locally → configure in Claude Desktop → verify tool appears, with explicit validation at each step.
Include a minimal test/validation command or script inline (not just referenced) so users can verify their server works before configuring it in Claude Desktop.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what MCP is conceptually or waste tokens on things Claude already knows. Every section provides concrete, useful information without padding. | 3 / 3 |
Actionability | The basic server example is fully executable and copy-paste ready. Configuration examples are concrete JSON. The project layout, common issues table, and troubleshooting guidance are all specific and actionable. | 3 / 3 |
Workflow Clarity | While the content provides clear patterns and a project layout, there's no explicit workflow sequence for building and testing an MCP server. There are no validation checkpoints—e.g., no step saying 'test the server responds' before configuring it in Claude Desktop. For a multi-step process like building an MCP integration, this is a gap. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a concise overview in the main file and clearly signaled one-level-deep references to detailed pattern files (tool-patterns.md, resource-patterns.md, etc.). The quick reference table maps use cases to specific reference files. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
9f4534c
- 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.