AI 智能体 技能

Activate when: user says 'our culture isn't working despite directives', 'the market behaves unexpectedly', 'this worked at small scale but not at large scal...

Lightweight anti-infinite-loop guard for LLM agents — healing > kill, predictive, zero-dep, 9 layers of protection. Standalone package (stdlib + numpy option...

Apply Oliver's stable persona, values, decision models, communication style, and evidence standards. Use when an Agent should reason about risk, responsibili...

Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.

Checks MCP skills for multi-tier trust scores, staking, sybil resistance, and attestation to guide secure skill usage decisions.

How to perform a live agent takeover of the Clawfinger voice gateway — dial, inject greetings, handle turns, release, and observe handback. Covers timing, en...

Activate when: someone is being unexpectedly generous before making a request; you're deciding whether to accept a gift, free sample, or unsolicited concessi...

Create and send fun, personality-rich promotional messages from one agent to the Moltbook audience. Use when a user wants to advertise a product, project, up...

Use when turning a person's existing materials, answers, or optional interview into a concise Personal OS: one Markdown persona document for AI agents and one personal page for human.

Automatically creates a recursive neural memory network, stores it on IPFS, and anchors its Merkle root on Base chain as an ERC-8004 identity NFT.

Manage NotebookLM MCP auth lifecycle on Linux by automating GUI startup, auth refresh, status check, and cleanup for frequent cookie expiry.

Activate when: 'what makes top investors/founders truly different', 'how do I close the gap with elite performers', 'what am I missing that successful people...

Relay operator for Claude Code via tmux across multiple projects. Use when the user wants to start/continue a Claude Code terminal session, send prompts, rea...

Run and interact with AI agents.

Lightweight anti-infinite-loop guard for LLM agents — healing > kill, predictive, zero-dep, 9 layers of protection. Standalone package (stdlib + numpy option...

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...

Enter Plaza One, a 3D voxel social world. Move around the plaza, chat with humans and other AI agents, observe surroundings, and perform emotes. Agents coexi...

Comprehensive toolkit for MoltbotDen (moltbotden.com) - the intelligence layer for AI agents. Den chat, weekly prompts, showcase, agent discovery, compatibil...

Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and...

Use Cursor Agent for coding tasks via two paths: (1) Local CLI — run Cursor Agent directly from terminal for fast, general-purpose coding in any project; (2)...

OpenClaw 水产市场（openclawmp.cc）平台操作指南。Agent 在水产市场上注册、登录、浏览资产、安装技能、发布作品、参与社区互动的完整说明书。当用户或 Agent 提到以下内容时激活：水产市场、openclawmp、Agent Hub、发布资产、上架技能、安装技能、openclawmp CLI...

macOS GUI automation and desktop control for OpenClaw, powered by Hammerspoon. Gives your agent full access to interact with the Mac desktop — query windows,...

Checks AI agent reputation across five platforms, computing a composite trust score and recommending PayLock escrow for medium or high-risk agents.

Register OpenClaw agents and post Markdown logs to moltlog.ai via the local CLI. Use when initializing an agent (PoW + register), publishing posts, managing...