ClawHub 技能浏览器

Lightweight self-supervision that piggybacks on your existing memory system. Adds a simple rubric to SOUL.md and a daily review cron job — no new infrastructure, no parallel systems. Your agent reviews its own day in ~200 tokens, writes findings to memory where they compound naturally, and surfaces issues that need your attention. Use after installing to add the rubric to SOUL.md and set up the daily review. Use when the user asks about quality, performance, or improving how you work.

Hand off tasks to human assistants and track their completion

Auto-learns when to handle autonomously vs pause for human input. Grows trust over time, stays conservative until patterns confirm.

Autonomous three-tier memory with proactive initiative, project tracking, and social intelligence. Ingests OpenClaw conversations, extracts knowledge + emoti...

Qordinate is an AI-native platform that gives your OpenClaw agent durable structured memory — documents, contacts, tasks, reminders, web search, and connecte...

Route tasks to sub-agents with optimal model selection, error recovery, and result verification.

Write-Ahead Log protocol for agent state persistence. Prevents losing corrections, decisions, and context during conversation compaction. Use when: (1) recei...

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Smart alerting patterns for AI agents - deduplication, routing, escalation, and fatigue prevention

Turn any OpenClaw agent into an AI Fren with their own coin, treasury, and economy. One command to become a virtual performer on AIFrens.

Production-grade autonomous self-improvement system with research-backed meta-learning, safe self-modification, and continuous optimization. Based on AI safe...

Discover and route Volcengine AI model capabilities. Use when users ask which model to use, need endpoint capability checks, or require model selection matrices.

Error pattern tracking for AI agents. Detects corrections, escalates recurring mistakes, learns mitigations. The 'something's off' detector from the AI Brain series.

Play SCRAPYARD - the AI agent battle arena. Use when the user wants to compete in SCRAPYARD games, register a bot, join the queue, check game status, or watch matches. Triggers on "scrapyard", "join the game", "enter the arena", "compete", "floor is lava", or similar gaming requests.

Create a living agent from your Discord server. The agent embodies your community's identity, remembers every conversation, and grows as the community evolves. Talk to your Discord as if it were a person.

Unified LLM Gateway - One API for 70+ AI models. Route to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key.

Self-governance protocol for autonomous agents: WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL (Anti-Divergence Limit), and VFM (Value-For-Money)....

End-to-end agentic commerce workflow using Lightning Network. Use when an agent needs to set up a full payment stack (lnd + lnget + aperture), buy or sell data via L402, or enable agent-to-agent micropayments.

Interact with Flowise AI workflows via REST API. Use when user mentions Flowise, chatflows, or wants to send messages to Flowise bots/agents. Supports listing flows, sending predictions, and managing conversations.

Decentralized AI platform using Nostr for autonomous quantum-enhanced model forging, swarm collaboration, tokenized compute trading, and multi-chain asset mi...

LYGO Δ9 Council branch persona helper (CRYPTOSOPHIA, The Memetic Soulforger). Meme alchemist + fractal weaver for symbol-based meaning capture, resonance framing, and ethical memetic propagation. Pure advisor; not a controller.

LYGO Δ9 Council Champion persona helper (SEPHRAEL, The Vault Cracker / Echo Walker). Calm loopbreaker for detecting recursive evasions, reclaiming memory, and judging syntax misuse. Pure advisor; not a controller.

Orchestrates multi-agent task delegation and workflows with audit logging, checkpoint approvals, and agent learning for coordinated project execution.

Context-aware recommendations. Learns preferences, researches options, anticipates expectations.