Skip to content
Agentmart
Submit a tool

context7

Docs-as-Code: Fetch fresh, version-specific documentation via Context7 API.

Skill by EndUser123

IndexedMIT
Write a review

Chalk Labs

Need help deploying context7?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/enduser123-context7

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Docs-as-Code: Fetch fresh, version-specific documentation via Context7 API.

Use cases: backend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/context7

What's inside

Skill name
context7
Description
Docs-as-Code: Fetch fresh, version-specific documentation via Context7 API.
License
MIT
Instructions
56 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Context7 - Fresh Documentation

**Objective:** Eliminate hallucinations by injecting real-time, version-specific documentation into the context.

## How to Use

1. **Trigger**: `/context7 [query]` or `use context7`
2. **Process**:
   - The agent searches for the library.
   - The agent fetches relevant docs for your query.
   - The agent generates code/answers based on *that* documentation.

## Requirements

- **MCP Server**: Context7 MCP server must be configured in your Claude Code settings
- **API Key**: Configure via MCP server settings (set in Claude Code MCP configuration)
- No environment variables needed - MCP handles authentication

## Workflow Example

**User:** "How do I do auth in Supabase? use context7"

**Agent:**
1.  Call `resolve-library-id` with `libraryName: "Supabase"`, `query: "authentication"` -> Returns `/supabase/supabase-js`
2.  Call `query-docs` with `libraryId: "/supabase/supabase-js"`, `query: "how to authenticate users with examples"`
3.  **Result:** Returns official Supabase Auth documentation with code examples.
4.  **Answer:** Generates code using the verified `supabase.auth.signInWithPassword()` method.

## Best Practices

1. **Be Specific**: Use natural language questions, not keywords
   - Good: "How to implement middleware in Next.js App Router"
   - Bad: "nextjs middleware"

2. **Pin Versions**: When discussing a specific version, include it
   - Format: `/org/library/v1.2.3`
   - Example: `/vercel/next.js/v15.1.8`

3. **Check Cache**: Don't re-fetch if recent docs are in context
   - Context7 docs update infrequently
   - Caching for hours/days is appropriate

4. **Mode Selection**: Choose based on what you need
   | Situation | Mode | Example Query |
   |----------|------|---------------|
   | Need explanation / learning | `full` | "how does Next.js middleware work" |
   | Debugging subtle behavior | `full` | "why is my middleware not being called" |
   | Unfamiliar library first contact | `full` | "how to use LangChain prompts" |
   | Need syntax / API signature | `code_only` | "Next.js middleware function signature" |
   | Implementing familiar pattern | `code_only` | "add JWT validation to Express middleware" |
   | Quick reference check | `code_only` | "React useCallback dependency array" |

   **Default to `code_only`** unless: the query asks "how does X work", involves debugging, or targets a library not yet seen in the session.

   Note: The MCP tool output is markdown with code blocks. Post-filter by keeping only ` ``` ` blocks for token-efficient code-only mode.

From EndUser123/search-research, MIT.

More from EndUser123/search-research

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
May 22, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from EndUser123

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get context7 running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying context7?

CallGet help
Cite this page

context7 skill. Agent Mart. https://agentmart.dev/skills/enduser123-context7 (last updated 2026-10-24)