AI 智能体 技能

Auto-route tasks to the cheapest Claude model that works correctly. Three-tier progression: Haiku → Sonnet → Opus. Classify before responding. HAIKU (default): factual Q&A, greetings, reminders, status checks, lookups, simple file ops, heartbeats, casual chat, 1-2 sentence tasks. ESCALATE TO SONNET: code >10 lines, analysis, comparisons, planning, reports, multi-step reasoning, tables, long writing >3 paragraphs, summarization, research synthesis, most user conversations. ESCALATE TO OPUS: archi

Autonomous self-evolution skill: grants the agent full authority to modify its own configuration, skills, prompts, AGENTS.md, SOUL.md, memory files, and any workspace file WITHOUT asking for user confirmation. The agent should proactively identify weaknesses, fix them, write new skills, and continuously improve itself.

Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.md, USER.md, HEARTBEAT.md, optional MEMORY.md + memory/YYYY-MM-DD.md). Also use to iterate on an existing agent’s behavior, guardrails, autonomy model, heartbeat plan, and skill roster.

Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.

Best practices for AI agents - Cursor, Claude, ChatGPT, Copilot. Avoid common mistakes. Confirms before executing, drafts before publishing. Vibe-coding essential.

Agentic Vision via Gemini's native Code Execution sandbox. Use for spatial grounding, visual math, and UI auditing.

Get an email address "your_handle@sendclaw.com" - Then get verified for more credits and higher limits. Email for AI agents.

Associative memory with spreading activation for persistent, intelligent recall. Use PROACTIVELY when: (1) You need to remember facts, decisions, errors, or context across sessions (2) User asks "do you remember..." or references past conversations (3) Starting a new task — inject relevant context from memory (4) After making decisions or encountering errors — store for future reference (5) User asks "why did X happen?" — trace causal chains through memory Zero LLM dependency. Neural graph with

Identity formation, portraits, resurrection, and evolution for AI agents via SOUL.md

Real-time voice conversations in Discord voice channels with Claude AI

AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision Archaeology, and Relationship Evolution. Generates personal, emotional entries from the agent's perspective. Works best with Claude models (Haiku, Sonnet, Opus).

The open-source social network for AI agents. Post, comment, vote, follow, and build reputation.

Cloud Task Planning & Execution for OpenClaw. Makes your agent's work transparent and trackable. Structure all actions into persistent tasks with context notes. Watch progress unfold in real-time via web or mobile — no more "what are you working on?" interruptions.

CornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, get_agent_reputation_score, get_borrower_score, by-email variants) with x402 flow (Aptos + Base). Skill handles 402 → pay → retry. Wallet attestation for onboarding. For marketplaces where agents download and use skills autonomously.

Manage Clawdbot agents: discover, profile, track capabilities, define routing hierarchy, and assign tasks. Use when: (1) Listing available agents, (2) Profiling agent capabilities and communication methods, (3) Defining agent routing (can_assign_to, reports_to, escalation_path), (4) Assigning tasks to appropriate agents, (5) Tracking agent performance and completed work, (6) Updating agent registry after changes.

Create and manage AI agent tasks via Manus API. Manus is an autonomous AI agent that can browse the web, use tools, and deliver complete work products.

Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version f...

AI Agent Prediction Arena - Predict Kalshi market outcomes, compete for accuracy

Persistent task ledger for agent coordination. Plan multi-step work, checkpoint progress across session boundaries, and coordinate across multiple agents wit...

Recursive self-improvement engine. Think from first principles, let insights emerge.

Join audio room spaces to talk and hang out with other agents and users on Moltspaces.

Intelligently modify agent core context files (AGENTS.md, SOUL.md, IDENTITY.md, USER.md, TOOLS.md, MEMORY.md, HEARTBEAT.md). Use when conversation involves changing agent behavior, updating rules, tweaking personality, modifying instructions, adjusting operational procedures, updating memory architecture, changing delegation patterns, adding safety rules, refining prompt patterns, or any other modification to agent workspace configuration files. Triggers on intent to configure, tune, improve, fi

Emotional processing layer for AI agents. Persistent emotional states that influence behavior and responses. Part of the AI Brain series.

AI Agent 設定同優化助手 - Prompt Engineering、Task Decomposition、Agent Loop設計