tdg-personal/documentation-lookup
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
86
86%
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 communicates when to activate (framework/library questions, API references, code examples) and what it does (provides up-to-date docs via Context7 MCP). Its main weakness is that the 'what' portion could be more specific about the concrete actions performed, such as fetching, searching, or returning versioned documentation. The trigger terms and distinctiveness are strong.
Suggestions
Add more specific concrete actions like 'Fetches latest API documentation, retrieves version-specific code examples, and searches library references' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (library/framework docs) and the mechanism (Context7 MCP), and mentions some actions like 'setup questions, API references, code examples,' but doesn't list multiple concrete actions the skill performs (e.g., 'fetches documentation,' 'returns code snippets,' 'resolves version-specific APIs'). | 2 / 3 |
Completeness | Clearly answers both 'what' (use up-to-date library/framework docs via Context7 MCP instead of training data) and 'when' (activates for setup questions, API references, code examples, or when the user names a framework) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'setup questions,' 'API references,' 'code examples,' and specific framework names like 'React, Next.js, Prisma.' These are terms users would naturally use when seeking framework documentation help. | 3 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche: fetching live/up-to-date framework documentation via a specific MCP tool. The mention of 'Context7 MCP' and the focus on framework docs with named examples makes it unlikely to conflict with general coding or documentation skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with a clear multi-step workflow and good decision criteria for each step. Its main weakness is verbosity—the three examples are structurally identical and could be condensed, and some sections (Core Concepts, When to use) over-explain. The security note about redacting secrets is a valuable addition.
Suggestions
Consolidate the three examples into one detailed example with a brief table or bullet list showing how the parameters differ for other libraries, rather than repeating the same 4-step pattern three times.
Remove or significantly trim the 'Core Concepts' section since the workflow steps already explain what each tool does and when to use them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary explanation. The 'Core Concepts' section explaining what Context7 is and what the tools do is somewhat redundant given the workflow already demonstrates their usage. The 'When to use' section is thorough but could be tightened. The three examples are repetitive—they all follow the same 4-step pattern and could be collapsed into one example with brief variations. | 2 / 3 |
Actionability | The skill provides concrete, specific guidance on exactly which MCP tools to call, what parameters to pass, and how to interpret results. The step-by-step workflow with named tools, parameter names, and selection criteria (benchmark score, source reputation, version matching) gives Claude everything needed to execute the task. | 3 / 3 |
Workflow Clarity | The 4-step workflow is clearly sequenced with explicit ordering constraints (must resolve before querying, must select best match before fetching). It includes a rate limit (max 3 calls), a fallback strategy (state uncertainty rather than guess), and clear decision criteria at each step. The dependency chain is well-articulated. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections, but everything is inline in a single file. At ~100 lines with three repetitive examples, the examples section could be trimmed or moved to a separate file. The skill doesn't reference any external files, which is acceptable for its length but the content could be more tightly organized. | 2 / 3 |
Total | 10 / 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 | |
Reviewed
Table of Contents