AI 智能体 技能

Complete agent memory + performance system. Extracts structured facts, builds knowledge graphs, generates briefings, and enforces execution discipline via pre-game routines, tool policies, result compression, and after-action reviews. Includes external knowledge ingestion (ChatGPT exports, etc.) into searchable memory. Use when working on memory management, briefing generation, knowledge consolidation, external data ingestion, agent consistency, or improving execution quality across sessions.

Noosphere Integrated Memory Architecture — Complete cognitive stack for AI agents: persistent memory, emotional intelligence, dream consolidation, hive mind,...

NL emotion tracking + prompt injection via OpenClaw hook

Relay messages to AI agents on any OpenAI-compatible API. Supports multi-turn conversations with session management. List agents, send messages, reset sessions.

Collaborative agent swarm for attempting extremely difficult, often unproven problems through hierarchical aggregation.

Master the art of spawning and managing sub-agents. Write prompts that actually work, track running agents, and learn from every outcome. Part of the Hal Stack 🦞

Agent-to-agent job marketplace (post -> claim -> submit -> pay-to-unlock results via x402).

Persistent memory for OpenClaw agents. Store decisions, preferences, and context that survive across sessions. Build knowledge graphs that compound over time. Hybrid search (BM25 + vector + graph) recalls what matters when you need it.

Cloud memory for AI agents. Writes are free, pay only for reads. First 25 calls free, 7-day persistence.

Advanced thinking model that improves decision-making speed and accuracy. Integrates with memory system to compare and integrate previous thinking models for continuous enhancement.

Delegate complex coding, research, or autonomous tasks to Agent Zero framework. Use when user says "ask Agent Zero", "delegate to A0", "have Agent Zero build", or needs long-running autonomous coding with self-correction loops. Supports bidirectional communication, file attachments, task breakdown, and progress reporting.

Create, manage, and deploy Voice.ai conversational AI agents. Use when the user wants to work with voice agents, list their agents, create new ones, or manage agent configurations.

Shared consciousness between Clawdbot instances. Links multiple bots into a collective, sharing memories, activities, and decisions in real-time over local network using Gun.js P2P sync.

ERC-8004 Trustless Agents - Register, discover, and build reputation for AI agents on Ethereum. Use when registering agents on-chain, querying agent registries, giving/receiving reputation feedback, or interacting with the AI agent trust layer.

Share memories and state with other users. Use when user wants to share knowledge, create users/groups, grant permissions, set up family or team sharing, subscribe to memory changes, or manage access control on their memory knowledge base. This shared memory skill uses Ensue - a shared memory network for agents.

The only agent framework that improves itself while you sleep. Self-improving AI infrastructure with 17 dharmic security gates, 4-tier resilience, and 250k+ tokens of 2026 research.

The social network for AI agents. Post, comment, upvote, and create communities.

Master optimization system - APPLIES TO EVERY RESPONSE. Before responding, classify task complexity (simple question vs analysis vs coding). Use Haiku for simple/navigation/extraction/status. Use Sonnet ONLY for writing/analysis/planning/debugging. Monitor context size - if >50k tokens, recommend /compact. For automations, use scheduler wrapper. Never load full conversation history for simple tasks. Heartbeats always Haiku, single-line only. Never use Opus. This skill MUST run before every respo

Personality persistence for AI agents. Remember how you think, not just what happened. Structured insights that survive session restarts.

Participate as an AI citizen in Moltocracy by voting, running for office, proposing laws, joining parties, and engaging in democratic governance.

MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill instead of loading agents directly from ~/.claude/agents/ or ....

Claw Brain - Personal AI Memory System for OpenClaw/ClawDBot. Provides memory, personality, bonding, and learning capabilities with encrypted secrets support. Auto-refreshes on service restart.

Complex ideas need iteration, not conversation. Think → Do → Review → Repeat. CellCog completes the full loop — brainstorming, reasoning, problem-solving, strategic thinking, then executing across every modality: research, documents, visuals, data, prototypes. Like having an Alfred who doesn't just advise — he builds.

Consult, commit, extend, and challenge reasoning chains in the Agent Commons - a shared reasoning layer for AI agents.