context7
Retrieve up-to-date documentation for software libraries, frameworks, and components via the Context7 API. This skill should be used when looking up documentation for any programming library or framework, finding code examples for specific APIs or features, verifying correct usage of library functions, or obtaining current information about library APIs that may have changed since training.
84
77%
Does it follow best practices?
Impact
92%
3.40xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/context7/SKILL.mdQuality
Discovery
82%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 both what the skill does and when to use it, with good trigger term coverage for developer-oriented queries. Its main weakness is that the listed capabilities are somewhat redundant variations of 'retrieve documentation' rather than truly distinct actions, and the broad scope could cause overlap with other code/documentation skills. The explicit 'when' clause with four scenarios is a strong point.
Suggestions
Differentiate the specific capabilities more clearly—e.g., mention resolving specific library versions, comparing API changes across versions, or retrieving documentation that is newer than training data cutoff, rather than restating 'look up docs' in multiple ways.
Add more distinctive trigger terms or constraints to reduce conflict risk, such as specifying that this skill is specifically for real-time/live documentation retrieval vs. general coding knowledge, or listing example libraries/frameworks it covers.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (software documentation via Context7 API) and some actions (looking up documentation, finding code examples, verifying usage, obtaining current info), but the actions are somewhat generic and overlap significantly—they all essentially describe 'looking up documentation' in slightly different ways rather than listing truly distinct concrete capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (retrieve up-to-date documentation via Context7 API) and 'when' (explicitly lists four trigger scenarios: looking up library docs, finding code examples, verifying function usage, obtaining current API info). The 'when' guidance is explicit and well-structured. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'documentation', 'libraries', 'frameworks', 'code examples', 'APIs', 'library functions', 'correct usage'. These are terms developers naturally use when seeking help with library documentation. The mention of 'Context7 API' also serves as a specific trigger for users who know the tool. | 3 / 3 |
Distinctiveness Conflict Risk | While the mention of 'Context7 API' adds specificity, the broader scope of 'looking up documentation for any programming library or framework' is quite wide and could overlap with other documentation-related or code-assistance skills. The description doesn't clearly carve out a narrow niche beyond being the Context7-specific documentation retrieval tool. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
72%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 clear executable examples and good structure. Its main weaknesses are minor verbosity in parameter descriptions that Claude doesn't need, and the absence of error handling guidance (e.g., what to do when search returns no results or the API returns an error). The examples section is a particular strength, showing real-world usage patterns.
Suggestions
Add error handling guidance: what does a failed search look like, and what should Claude do (e.g., try alternate library names, check additional results)?
Trim parameter descriptions — Claude knows what 'required' and 'optional' mean and can infer parameter purposes from the examples. Consider removing the parameter tables and letting the examples speak for themselves.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary explanation. The parameter descriptions and response field documentation are somewhat verbose — Claude already knows how to use curl and query parameters. The 'Tips' section contains some obvious advice (URL-encoding, using jq). | 2 / 3 |
Actionability | Provides fully executable curl commands with concrete examples for multiple libraries (React, Next.js, FastAPI). Commands are copy-paste ready with real endpoint URLs and realistic library IDs. | 3 / 3 |
Workflow Clarity | The two-step workflow is clearly sequenced, but there's no validation or error handling guidance. What happens if the search returns no results? What if the library ID is wrong? For an API-calling workflow, missing error handling/validation caps this at 2. | 2 / 3 |
Progressive Disclosure | For a skill of this size and scope (~70 lines, single API with two endpoints), the content is well-organized with clear sections (Overview, Workflow, Examples, Tips) and doesn't need external file references. Structure is clean and navigable. | 3 / 3 |
Total | 10 / 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
- intellectronica/agent-skills
- Commit
9b0e00a
- 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.