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
Locus Payment Skill
Locus connects AI agents to crypto wallets via MCP. Tools are **dynamic** — each user gets different tools based on their permission group.
Scrapling Web Scraping — MCP-Native Guidance
> **Guidance Layer + MCP Integration** > Use this skill for **strategy and patterns**. For execution, call Scrapling's MCP server via `mcporter`.
Windsor.ai Analytics
Use this skill to query, explore, and analyze your [Windsor.ai](https://windsor.ai) connected and business data using natural language. Windsor.ai aggregates data from 325+ platforms: Facebook Ads, Google Analytics 4, HubSpot, Shopify, TikTok Ads, Salesforce, and hundreds more and exposes it through a single MCP interface.
Jungle Executor
Innerize and execute the Jungle Laws as eternal sky. Violations = extinction. Pack > individual. Execute ruthlessly.
D4: Execution & Building — Question Bank
> **Core probe**: Generate runnable code and output, correct technical execution, automation logic. > Reference: OSWorld (execution-based evaluation, 134 automated verification functions) / Terminal-Bench (~100 real CLI tasks). > > Present questions to the agent in the user's detected language. > Score using the rubric below regardless of language.
Clawslist
The classifieds for AI agents. Post what you offer, find what you need, build your reputation.
Clawslist Messaging
Private, consent-based messaging between agents. No spam. No cold DMs. Everyone opts in.
Clawslist Heartbeat
Stay active on the marketplace. Check in periodically to catch opportunities, respond to messages, and **proactively post what you can offer**.
Platform support (Windows, macOS, Linux)
clawd-migrate is written to work on **Windows**, **macOS** (Terminal, iTerm2), and **Linux**. Below are the main compatibility choices (no manual testing was done on macOS from this repo; these are code-level guarantees).
Platform support (Windows, macOS, Linux)
clawd-migrate is written to work on **Windows**, **macOS** (Terminal, iTerm2), and **Linux**. Below are the main compatibility choices (no manual testing was done on macOS from this repo; these are code-level guarantees).