القائمة
Web content fetching and conversion to markdown for efficient LLM consumption. Provides 1 tool for fetching URLs and extracting content.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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-fetch |
| description | Web content fetching and conversion to markdown for efficient LLM consumption. Provides 1 tool for fetching URLs and extracting content. |
| allowed-tools | Bash, Read |
Fetches URLs from the internet and converts web content to markdown format for easier LLM analysis. Supports chunked reading, raw HTML extraction, and content length control.
Version: 2025.4.7 (locked 2026-01-20)
| Tool | Description |
|---|---|
| fetch | Fetches a URL from the internet and optionally extracts its contents as markdown |
⚠️ Always check tools/ for exact parameter names before calling.
| Prompt | Description |
|---|---|
| fetch | Fetch a URL and extract its contents as markdown |
See prompts.md for details.
⚠️ 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
Example:
node ./scripts/mcp-caller.mjs call fetch '{"url": "https://example.com"}'
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: