jbvc/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).
82
82%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
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 'Use when' guidance with framework-specific triggers. Its main weakness is that the 'what' portion is somewhat general—it describes the purpose of MCP servers rather than listing specific concrete actions the skill teaches (e.g., defining tools, configuring transports, handling errors). The trigger term coverage is excellent for this domain.
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'Covers defining tools, configuring transports, input validation, error handling, and authentication patterns for MCP servers.'
| 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 does not 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) 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 trigger terms: 'MCP', 'Model Context Protocol', 'MCP servers', 'FastMCP', 'MCP SDK', 'external APIs', 'Python', 'Node', 'TypeScript'. These cover the main variations a user would naturally use when asking about building MCP servers. | 3 / 3 |
Distinctiveness Conflict Risk | MCP server development is a very specific niche. The description includes distinct triggers like 'MCP', 'Model Context Protocol', 'FastMCP', and 'MCP SDK' that are unlikely to conflict with other 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 skill with strong progressive disclosure and clear phased organization, but it trades off actionability and conciseness. The main body reads more like a project management outline than an executable guide—concrete code examples and validation checkpoints are largely deferred to reference files. The reference section duplicates links already provided in the workflow phases, adding unnecessary tokens.
Suggestions
Add at least one minimal, executable code example in the main body (e.g., a basic TypeScript tool registration with Zod schema) so the skill is actionable without loading reference files.
Remove the duplicated Reference Files section at the bottom, or consolidate all links there and remove inline references in the phases to reduce redundancy.
Add explicit validation/feedback loops in Phase 3 (e.g., 'If build fails → check error output → fix → rebuild → only proceed when build succeeds') to strengthen workflow clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary verbosity—e.g., explaining what MCP is, justifying TypeScript choice with multiple reasons, and restating reference links multiple times (Phase 1, Phase 2, and again in the Reference Files section). However, it's not egregiously padded and most content serves a purpose. | 2 / 3 |
Actionability | The skill provides a structured process with specific URLs, tool names, and framework references, but lacks executable code examples in the main body. Implementation guidance is largely descriptive ('Create shared utilities', 'Use Zod or Pydantic') rather than providing concrete, copy-paste-ready code. The actionable details are deferred to reference files. | 2 / 3 |
Workflow Clarity | The four-phase workflow is clearly sequenced and logically organized, but validation checkpoints are weak. Phase 3 mentions build/test steps but lacks explicit feedback loops (e.g., 'if build fails, fix and rebuild'). For a skill involving code generation and server development, the absence of explicit error recovery loops caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill effectively uses progressive disclosure with a clear overview in the main file and well-signaled, one-level-deep references to language-specific guides, best practices, evaluation guide, and SDK documentation. Navigation is easy with descriptive links and emoji markers. | 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.
Reviewed
Table of Contents