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).
91
73%
Does it follow best practices?
Impact
93%
2.21xAverage score across 10 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./examples/mcp-builder/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), provides explicit 'Use when' guidance with framework-specific triggers, and is distinctive enough to avoid conflicts. The main weakness is that the 'what' portion could be more specific about the concrete actions the skill covers (e.g., defining tools, handling resources, configuring transports) rather than staying at a high level.
Suggestions
Add more specific concrete actions the skill covers, e.g., 'defining tools and resources, handling authentication, configuring transports, structuring server code' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description 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 it 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' ('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'. These cover the main variations a user building MCP servers would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | MCP server development is a very specific niche with distinct trigger terms (MCP, Model Context Protocol, FastMCP, MCP SDK). This is unlikely to conflict with general coding skills or other integration-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
57%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 overview skill that excels at progressive disclosure and organizing a complex multi-phase workflow. Its main weaknesses are the lack of executable code examples in the body (deferring almost entirely to reference files) and some verbosity in explaining concepts Claude already understands like API design principles and DRY. The workflow would benefit from explicit validation checkpoints and error recovery steps.
Suggestions
Add at least one minimal executable code example in the main body (e.g., a basic TypeScript tool registration snippet) so the skill is actionable without loading reference files.
Add explicit validation checkpoints with error recovery between phases, e.g., 'If build fails: check type errors with `tsc --noEmit`, fix, and rebuild before proceeding to testing.'
Remove explanations of concepts Claude already knows (e.g., why DRY matters, what async/await is for, why TypeScript has good linting tools) to improve token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably organized but includes some unnecessary explanation (e.g., explaining why TypeScript is recommended with multiple justifications, explaining what MCP is, general software engineering advice like 'DRY principle'). Some sections like 'Understand Modern MCP Design' explain concepts Claude already knows about API design. | 2 / 3 |
Actionability | The skill provides structured guidance and specific tool names (Zod, Pydantic, MCP Inspector) but lacks executable code examples in the main body. Most instructions are descriptive checklists rather than copy-paste ready commands or code snippets. The XML evaluation format example is a good concrete element, but core implementation guidance defers entirely to reference files. | 2 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced and logically ordered, but validation checkpoints are weak. Phase 3 mentions 'run build' and 'verify syntax' but lacks explicit feedback loops for error recovery. There's no 'if this fails, do X' pattern for the build/test steps, and no validation between phases (e.g., verifying API understanding before implementation). | 2 / 3 |
Progressive Disclosure | The skill effectively serves as an overview document with well-signaled, one-level-deep references to language-specific guides, best practices, evaluation guide, and SDK documentation. References are clearly labeled with emoji icons and brief descriptions of what each contains. Navigation is intuitive with references placed contextually where they're needed. | 3 / 3 |
Total | 9 / 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
- douglasvought/wiggle-skills
- Commit
b27906e
- 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.