Fetch web content in multiple formats using fetch MCP tools. Use when WebFetch fails with 403/access errors, when fetching HTML pages, JSON APIs, plain text, readable article content, or YouTube transcripts. Triggers on mentions of fetching URLs, web scraping, reading web pages, downloading content, or accessing online resources.
Scanned 5/27/2026
Install via CLI
Skills Directoryopenskills install pleaseai/claude-code-plugins---
name: Fetching Web Content
description: Fetch web content in multiple formats using fetch MCP tools. Use when WebFetch fails with 403/access errors, when fetching HTML pages, JSON APIs, plain text, readable article content, or YouTube transcripts. Triggers on mentions of fetching URLs, web scraping, reading web pages, downloading content, or accessing online resources.
allowed-tools: mcp__fetch__fetch_html, mcp__fetch__fetch_markdown, mcp__fetch__fetch_txt, mcp__fetch__fetch_json, mcp__fetch__fetch_readable, mcp__fetch__fetch_youtube_transcript
---
# Fetch MCP - Web Content Retrieval
Use fetch MCP tools to retrieve web content in the most appropriate format for the task.
## When to Use
- WebFetch fails with 403, access denied, or other errors
- Fetching structured data from JSON APIs
- Converting web pages to clean Markdown for analysis
- Extracting readable article content without navigation/ads
- Downloading YouTube video transcripts
- Getting raw HTML for parsing or inspection
## Available Tools
| Tool | Best For |
|------|----------|
| `mcp__fetch__fetch_markdown` | General web pages — converts to clean Markdown |
| `mcp__fetch__fetch_html` | Raw HTML when you need to parse structure |
| `mcp__fetch__fetch_txt` | Plain text extraction, minimal formatting |
| `mcp__fetch__fetch_json` | JSON REST APIs and data endpoints |
| `mcp__fetch__fetch_readable` | Articles/blog posts — removes ads and navigation |
| `mcp__fetch__fetch_youtube_transcript` | YouTube video transcripts by video URL or ID |
## How to Use
1. Choose the format matching the content type and task
2. Call the appropriate tool with the target URL
3. Process the returned content as needed
## Format Selection Guide
- **Documentation, blog posts**: `fetch_markdown` or `fetch_readable`
- **API endpoints**: `fetch_json`
- **HTML parsing/scraping**: `fetch_html`
- **YouTube videos**: `fetch_youtube_transcript`
- **Plain content extraction**: `fetch_txt`
## Fallback from WebFetch
When WebFetch fails, the fetch plugin automatically suggests retrying with these tools. Prefer `fetch_markdown` as the general-purpose fallback for most URLs.
No comments yet. Be the first to comment!
Brand-aware social media video creator. Reads brand-identity.md, ICP.md, and messaging.md to write a post/storyboard, craft an optimized Seedance 2.0 Director prompt, generate reference frames with the best available image model, and produce platform-ready video.
You are the social media engine for `/market social <topic/url>`. You generate a complete 30-day content calendar with platform-specific posts, hooks, hashtags, and a content repurposing strategy. Every post is ready to publish or hand to a social media manager.
Generate a complete, week-by-week launch playbook for any product, service, or feature launch. This skill produces a tactical plan with templates, checklists, email sequences, social posts, and metrics tracking -- everything needed to execute a successful launch.
Extract, define, and apply design DNA across three dimensions: design system (tokens), design style (qualitative feel), and visual effects (Canvas, WebGL, 3D, particles, shaders, scroll effects, etc.). Use this skill when: (1) a user wants to see the full 3-dimension design structure/schema, (2) a user provides images, screenshots, or URLs of reference designs and wants them analyzed into a structured JSON profile covering all three dimensions, (3) a user has a Design DNA JSON and content and...
Before removing code that looks redundant, wasteful, or "wrong" based on log observations or code review instinct, grep the test suite for tests whose names describe the exact behavior you're about to remove. A test whose title literally describes the "weird" thing (e.g. "calls play() even when player reports playing", "retries even when first call succeeded", "skips cache even when fresh") is a load-bearing workaround, and the production log you're reacting to is probably the workaround work...
