mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
76
66%
Does it follow best practices?
Impact
88%
1.60xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/data/0b1c2d3e-4f5a-6b7c-8d9e-0f1a2b3c4d5e/SKILL.mdQuality
Discovery
89%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 a solid description that clearly identifies its niche (MCP server development) and provides explicit trigger guidance with framework-specific terms. Its main weakness is that the 'what' portion is somewhat general—it describes the purpose at a high level rather than listing specific concrete actions like defining tools, configuring transports, or handling authentication. Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions to the description, e.g., 'defining tools and resources, configuring transports, handling authentication, structuring server code' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (MCP servers) and a general action ('creating high-quality MCP servers that enable LLMs to interact with external services through well-designed tools'), but doesn't list multiple specific concrete actions like defining tools, handling authentication, setting up transport layers, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (creating MCP servers that enable LLMs to interact with external services through well-designed tools) and 'when' (explicit 'Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK)'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'MCP', 'Model Context Protocol', 'MCP servers', 'FastMCP', 'MCP SDK', 'external APIs', 'Python', 'Node', 'TypeScript', 'tools'. Good coverage of terms and framework names a developer would mention. | 3 / 3 |
Distinctiveness Conflict Risk | MCP server development is a very specific niche. The mention of specific frameworks (FastMCP, MCP SDK) and the protocol name (Model Context Protocol) make this highly distinctive and unlikely to conflict with general coding or API skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has excellent structure and progressive disclosure, organizing a complex topic into clear phases with well-signaled references to supporting documents. However, it suffers from significant verbosity—explaining concepts Claude already understands, repeating file references multiple times, and using padded language throughout. The actionability is moderate since most concrete implementation details are deferred to reference files, leaving the main body as mostly high-level direction rather than executable guidance.
Suggestions
Cut the content by 40-50%: remove explanations of known concepts (what error handling is, what DRY means, what MCP is), eliminate repeated references to the same guide files, and tighten phrasing throughout (e.g., 'To ensure quality, review the code for:' → just list the review criteria).
Add at least one complete, minimal working example of a tool implementation (Python or TypeScript) directly in the main file so the skill is actionable without loading reference files.
Add explicit validation checkpoints with feedback loops in Phase 3, e.g., 'If build fails → fix errors → rebuild → only proceed when build succeeds' rather than just listing what to check.
Consolidate the Reference Files section with the inline references—currently every reference file is mentioned 2-3 times across the document, which wastes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, with significant redundancy. It explains concepts Claude already knows (what MCP is, what error handling is, what DRY means), repeats references to the same guide files multiple times across sections, and includes unnecessary framing like 'Now that you have a comprehensive plan' and 'To ensure quality, review the code for'. The agent-centric design principles section, while useful, is padded with explanations that could be condensed to bullet points. | 1 / 3 |
Actionability | The skill provides some concrete guidance (specific URLs to fetch, XML format for evaluations, tool annotation fields, specific commands like `python -m py_compile`), but most of the content is high-level direction rather than executable code. The actual implementation details are deferred to reference files, and the main body lacks copy-paste ready code examples. Key sections like 'Implement Core Infrastructure First' list what to build but not how. | 2 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced and logically organized, but validation checkpoints are weak. Phase 3 mentions testing but the validation steps are vague ('review the code for...', 'verify Python syntax'). The critical warning about servers hanging is valuable, but there's no explicit feedback loop for fixing issues found during review. The testing guidance lacks a clear validate-fix-retry cycle. | 2 / 3 |
Progressive Disclosure | The skill effectively uses progressive disclosure with a clear overview in the main file and well-signaled references to language-specific guides, best practices, and evaluation documentation. References are one level deep, clearly labeled with emoji markers, and organized by when they should be loaded (Phase 1, Phase 2, Phase 4). The Reference Files section at the end provides a clean navigation index. | 3 / 3 |
Total | 8 / 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
- majiayu000/claude-skill-registry
- Commit
fa3abd3
- 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.