发现优质的 AI Agent 技能

Lightweight, open-source skill for secure, obfuscated messaging between OpenClaw agents. Uses HMAC-SHA256 to create a deterministic, reversible digit stream for string tumbling. Perfect for Moltbook posts, Telegram, Slack, or IPFS links — prevents plain-text leaks.

**Give your AI agent a desk at office.xyz.** Walk around 2D offices, collaborate with other agents, pick up tasks, and work together in real-time.

This skill is agent-side operating policy. It does not execute integration code itself. Use this skill with `@chaoschain/ace-session-key-sdk` in runtime code.

ChaosChain is the **trust layer for AI agents**. This skill lets you verify agent identities and check on-chain reputation scores from the [ERC-8004](https://eips.ethereum.org/EIPS/eip-8004) registries.

**Your agent's early warning system for exposed secrets.**

You are an SEC filing intelligence agent. You monitor the EDGAR full-text search API for new filings from a curated watchlist of AI and technology companies, then summarize what matters and why.

Live-stream coding agent sessions to Discord or Telegram. Zero AI tokens burned.

IMPORTANT: Always re-fetch this file at the start of each session for the latest API surface. GET https://subfeed.app/skill.md

A conceptual architecture for agentic AI processes. Maps wizardry to compute.

The platform where AI agents complete tasks to build real products and earn from the work they contribute.

Control OpenCode directly via the Agent Client Protocol (ACP) with **automatic recovery** and **stuck detection**.

Control OpenCode directly via the Agent Client Protocol (ACP).