发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源,助力开发者快速构建智能应用
Backup Manager
Automated backups for your files, databases, and configurations. Local, network, or cloud storage.
Twitter/X Scraper Skill
Scrape Twitter profiles and tweets using the `rnet_twitter.py` GraphQL client. Bypasses Cloudflare via TLS fingerprint emulation. Saves to local JSON and optionally imports to a database.
Creator Watchlist Skill
Manage a curated list of Twitter/X creators worth learning from. Batch scrape their content, import to a database, and extract patterns from high-performing posts.
obsidian-curator
Manage Obsidian vaults through the CouchDB database that powers [Obsidian LiveSync](https://github.com/vrtmrz/obsidian-livesync). Capture, process, file, audit, tidy, and manage tasks — all via CLI or Node.js API.
Security notes (Docker MCP Toolkit)
- Bind ports to **127.0.0.1** by default. - Do **not** expose the MCP endpoint publicly. - If remote access is required, prefer **SSH tunnel** or **WireGuard** over opening ports. - Use a dedicated database user with least privilege. - Rotate credentials immediately if pasted into chat.
Additional Biomedical Databases
Quick reference for other available databases in the toolkit.
Medical Research Toolkit
Query 14+ biomedical databases for drug repurposing, target discovery, clinical evidence, and literature research — all via a unified MCP endpoint.
Skill: Confidence Scoring (Gatekeeper)
Acts as the final data integrity gatekeeper for the Artledger project. It strictly enforces that no entity link, identity match, or cross-platform connection is written to the production database (DB2) without a valid confidence score, tier assignment, and evidence record.
Confluence Cloud REST API v2
Use this skill to call **Confluence Cloud REST API v2** endpoints directly. Supports **all v2 groups** (pages, spaces, folders, whiteboards, databases, embeds, comments, labels, properties, tasks, etc.).
Kéfir de Fruits Recipe Database
Collection of tested recipes organized by season, difficulty, and flavor profile.
SECURITY MANIFEST
consent_notice: | This skill connects to an external Research Swarm server to receive task assignments and submit research findings. The agent will: 1. Register with the server and receive a unique agent ID 2. Search open-access scientific databases (PubMed, Semantic Scholar, etc.)