MCP App StoreMCP App Store
from media-extract-skill16
Extracts and analyses media (YouTube, web articles, local audio/video, transcripts). Produces structured summaries, chapters, quotes, code examples and visual a
Media Extract is a utility skill that ingests content from YouTube, web pages, local files (video, audio, PDF, text) or pasted transcripts and returns structured, parseable outputs: summaries, chapter timestamps, golden nuggets, quotes, command/code examples, and visual analysis via Gemini. It can download videos using yt-dlp, clean meeting transcripts (remove timestamps and filler words), and enrich outputs with metadata (channel, publish date, duration, views, likes, engagement). The skill focuses on consistent, machine-friendly formats so downstream skills can consume the results programmatically.
Use this skill when a user shares a YouTube link, posts an article URL, uploads or points to a local media file, pastes a transcript, or asks explicitly to "clean this transcript", "remove timestamps", or to "analyze this video/article". Also useful for batch processing playlists or folders of videos and for extracting code shown visually on-screen.
Best suited for agents with file and web access and Gemini integration (e.g., Claude with file+tooling, agents using Gemini visual models, or other assistant runtimes that can run local scripts and call external APIs).
Media-extract is a universal media extraction skill handling YouTube, web articles, local video/audio, and transcripts. It routes input by type (URL, file, pasted text) to appropriate workflows (summary, visual analysis, cleaning, etc.). The Python script (extract.py) is well-structured with clean error handling but requires google-genai which wasn't installed, causing it to exit with a helpful error message. No security concerns found — .env loading is safe, no hardcoded credentials, no destructive defaults, no exfiltration patterns.
google-genaiWell-designed skill with clear intent routing and good progressive disclosure via references/workflows/. The SKILL.md is comprehensive with proper XML tags for structure. Script failed to run only due to missing google-genai dependency, not a code bug. The .env loading implementation is manual but secure (uses os.environ.setdefault, skips comments). Minor deduction for no type hints and print-based logging instead of proper logging module.
Markdrop
Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.
Skyvern — AI Browser Automation
Cloud-first AI browser automation platform and SDKs for extracting data, filling forms, downloading files, and running multi-step web workflows from agents or c
hmem — Setup
Interactive installer and setup guide for hmem (persistent memory MCP server); automates .mcp.json config, memory dir, and adds agent hooks for Claude Code, Gem
Executing Plans
Execute a written implementation plan in safe, review-checked batches: load, review, run tasks in small batches with verification and checkpoints for feedback.
Task Delegation Assistant
Helps the agent clarify, break down, schedule, and track delegated tasks using memory and routines; creates plans with steps, due dates and monitoring routines.
Reflect Codex Sessions
Generate reflective summaries of past Codex session histories (summaries, patterns, open loops, decisions) via a CLI that scans cached ~/.codex/sessions and pro
XHS CLI (Xiaohongshu Terminal)
Command-line tool to search, read, and interact with Xiaohongshu (小红书) posts and profiles — supports search, reading, likes, favorites, comments, and posting fr
Avenir-Web
Run and improve Avenir-Web autonomous web tasks: choose run mode, validate and refine instructions, execute single or batch runs, and analyze outputs to propose