Agent skill
context7
A skill for retrieving the latest library documentation using Context7. Use when the user asks about how to use a library, requests code examples, or instructs to "use context7". Prevents hallucinations based on outdated training data and provides up-to-date API information.
Install this agent skill to your Project
npx add-skill https://github.com/dotneet/claude-code-marketplace/tree/main/research/skills/context7
SKILL.md
Context7
Overview
Context7 is a service that provides LLMs with the latest library documentation. It prevents hallucinations from outdated training data or non-existent APIs, enabling retrieval of version-specific accurate documentation and code examples.
When to Use
Use this skill in the following cases:
- Explicit instruction: When the user instructs "use context7" or "check the latest documentation"
- Library usage questions: When asked about how to use a specific library's API, hooks, or functions
- Code example requests: When asked for code examples using a specific library
- Version-specific information: When library information for a specific version is needed
- Uncertain API information: When your knowledge might be outdated and latest information verification is needed
Workflow
Step 1: Resolve Library ID
First, obtain the Context7 ID for the target library.
API call:
curl "https://context7.com/api/v2/libs/search?libraryName=LIBRARY_NAME&query=CONTEXT_QUERY" \
-H "Authorization: Bearer $CONTEXT7_API_KEY"
Example:
# Search for React library
curl "https://context7.com/api/v2/libs/search?libraryName=react&query=hooks" \
-H "Authorization: Bearer $CONTEXT7_API_KEY"
Criteria for selecting from response:
trustScore: Trust score (higher is better)totalSnippets: Number of available documents (more means richer information)versions: Verify that the required version is included
Step 2: Retrieve Documentation
Use the resolved library ID to retrieve specific documentation.
API call:
curl "https://context7.com/api/v2/context?libraryId=LIBRARY_ID&query=SPECIFIC_QUERY" \
-H "Authorization: Bearer $CONTEXT7_API_KEY"
Example:
# Retrieve information about React's useEffect
curl "https://context7.com/api/v2/context?libraryId=/facebook/react&query=useEffect cleanup function" \
-H "Authorization: Bearer $CONTEXT7_API_KEY"
Query best practices:
- Use specific queries ("useEffect cleanup function" rather than "hooks")
- Be clear about the purpose ("authentication middleware", "form validation", etc.)
Step 3: Respond to User
Respond to the user's question based on the retrieved documentation.
Information to include in the response:
- Retrieved code examples
- API explanations
- Documentation source URLs (for reference)
Examples
Example 1: React Hook Usage
User: "How do I write a cleanup function with React's useEffect?"
Execution steps:
- Library search:
libraryName=react,query=useEffect cleanup - Documentation retrieval:
libraryId=/facebook/react,query=useEffect cleanup function - Respond with the latest code examples and best practices
Example 2: Next.js Routing
User: "Use context7 to show me how to implement authentication middleware with Next.js App Router"
Execution steps:
- Library search:
libraryName=next.js,query=middleware authentication - Documentation retrieval:
libraryId=/vercel/next.js,query=middleware authentication route protection - Respond with the latest App Router compatible middleware implementation
Example 3: Multiple Libraries Combination
User: "How to create a button component using TailwindCSS and shadcn/ui"
Execution steps:
- Resolve IDs for each library
- Retrieve documentation for both
- Respond with a combined implementation example
Error Handling
| Error | Solution |
|---|---|
| 404 (Not Found) | Search again with a different library name (e.g., "nextjs" → "next.js") |
| 429 (Rate Limit) | Wait a moment and retry |
| Empty response | Retry with a more general query |
Resources
For detailed API specifications, see references/api_reference.md.
- Endpoint details
- Response field descriptions
- Rate limit information
- Error code list
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
prompt-improver
A skill for improving prompts by applying general LLM/agent best practices. When the user provides a prompt, this skill outputs an improved version, identifies missing information, and provides specific improvement points. Use when the user asks to "improve this prompt", "review this prompt", or "make this prompt better".
suggest-agent-rules
Suggest agent rules analyzing the session history and the current repository.
perplexity-search
A skill for performing web searches, research, and reasoning using the Perplexity API. Handles real-time web information retrieval, deep research analysis, and advanced reasoning tasks. Use when the user asks for web searches, research, or says things like "look up", "search for", "latest information", "research", or "analyze".
code-modularization-evaluator
Evaluate and improve code modularization using the Balanced Coupling Model. Analyzes coupling strength, connascence types, and distance to identify refactoring opportunities and architectural improvements. Use when reviewing code architecture, refactoring modules, or designing new systems.
typescript-react-reviewer
Expert code reviewer for TypeScript + React 19 applications. Use when reviewing React code, identifying anti-patterns, evaluating state management, or assessing code maintainability. Triggers: code review requests, PR reviews, React architecture evaluation, identifying code smells, TypeScript type safety checks, useEffect abuse detection, state management review.
google-calendar
Accesses the Google Calendar and Tasks API. Use this skill to view or manage calendars, events, schedules, or Google tasks.
Didn't find tool you were looking for?