메뉴
Query up-to-date library documentation and code examples using Context7. Provides 2 tools for resolving library IDs and querying documentation.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Create, update, validate, diff, or export DESIGN.md files following the Google Stitch DESIGN.md spec and @google/design.md tooling. Use when the user asks to write/update DESIGN.md, create a design system document, generate design tokens, encode brand/UI guidelines, export a design system, or document UI consistency rules for AI agents. Do NOT use for ordinary UI implementation unless the user asks for DESIGN.md or design-system documentation.
Screens third-party project dependencies for known vulnerabilities and supply-chain risk before installation using a bundled check-deps.py script. Use when user asks to install, add, update, upgrade, or pin packages with npm, pnpm, yarn, bun, pip, uv, poetry, or cargo, or when deciding whether a package version is safe to install. Do NOT use for OS package managers such as apt, brew, yum, apk, or pacman.
Track decisions (AGD) with validation and indexing. Use when making design decisions, recording important choices, discussing trade-offs, or when user mentions AGD or decision record.
End-to-end workflow for developing, debugging, configuring, and shipping pi-coding-agent extensions and pi packages. Use when building or maintaining extensions, skills, prompt templates, themes, settings.json setups, provider integrations, or when updating this skill after pi releases. Do NOT use for general coding questions unrelated to pi extension development.
Fork the current pi session into a new tmux pane. Use when user says /tmux-fork, 'fork to tmux', 'open in new pane', or wants to branch the conversation into a separate tmux pane.
Create and improve Claude Code Skills following official best practices. Use when creating a skill, improving skill descriptions, fixing skill activation issues, or structuring skill directories.
| name | mcp-context7 |
| description | Query up-to-date library documentation and code examples using Context7. Provides 2 tools for resolving library IDs and querying documentation. |
| allowed-tools | Bash, Read |
Query up-to-date documentation and code examples for any programming library or framework using Context7's documentation service.
Version: 2.0.2 (locked 2026-01-20)
This skill works without authentication, but setting an API key is recommended for higher rate limits:
MCP_CONTEXT7_API_KEY: Your Context7 API key (get free key at https://context7.com/dashboard)export MCP_CONTEXT7_API_KEY="ctx7sk_..."
Without API key: Works with lower rate limits (suitable for light usage) With API key: Higher rate limits, free tier is generous for most use cases
Environment variables use the MCP_<SKILL_NAME>_<VAR> naming convention to avoid conflicts.
| Tool | Description |
|---|---|
| resolve-library-id | Resolves a package/product name to a Context7-compatible library ID and returns matching libraries |
| query-docs | Retrieves and queries up-to-date documentation and code examples from Context7 for any programming library or framework |
⚠️ Always check tools/ for exact parameter names before calling.
⚠️ Before calling any tool, read its documentation in tools/ to get the exact parameter names.
# List available tools and their schemas
node ./scripts/mcp-caller.mjs list
# Then check tools/<tool-name>.md for parameter details
Run from this skill directory:
node ./scripts/mcp-caller.mjs call <tool> '<json-args>'
node ./scripts/mcp-caller.mjs resource <uri>
node ./scripts/mcp-caller.mjs prompt <name> '<json-args>'
node ./scripts/mcp-caller.mjs list
For batch operations or complex logic, use the API module:
// example.mjs - Run from this skill directory
import { callTool, listTools } from './scripts/api.mjs';
// First, check available tools and their schemas
const tools = await listTools();
console.log(tools.map(t => ({ name: t.name, params: Object.keys(t.inputSchema?.properties || {}) })));
// Then call with correct parameters (see tools/*.md for details)
const result = await callTool('toolName', { /* check tools/toolName.md for params */ });
// Parallel calls
const results = await Promise.all([
callTool('tool1', { /* params from tools/tool1.md */ }),
callTool('tool2', { /* params from tools/tool2.md */ }),
]);
console.log(JSON.stringify(results, null, 2));
Available API functions:
callTool(name, args) - Call a toollistTools() - List available tools (includes inputSchema with parameter info)readResource(uri) - Read a resourcelistResources() - List resourcesgetPrompt(name, args) - Get a promptlistPrompts() - List promptsclose() - Close connection (optional cleanup)If a tool call fails (e.g., "method not found", parameter changes):
Do not retry failed calls repeatedly - prioritize finding alternatives.
To update this skill with newer MCP server version: