🤖 AI & Agents AI Skills

Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.

Process, optimize, and manage images with web optimization, color management, platform specs, and e-commerce standards.

Send personalized LinkedIn direct messages to a list of existing 1st-degree connections via browser automation. Use when the user wants to message LinkedIn connections with AI-personalized outreach — e.g. nurturing leads, following up after events, reconnecting with contacts, or announcing something. Takes a data file (CSV/TSV) or plain list with connection names and companies, asks for outreach context/goal, generates a tailored message per person, and sends each one via browser automation. Handles message compose flow, character limits, and incremental status tracking.

Standardize provenance, attribution, and licensing metadata at creation time so your content travels cleanly across platforms.

Convert text to speech using Hume AI (or OpenAI) API. Use when the user asks for an audio message, a voice reply, or to hear something "of vive voix".

Avoid common LangChain mistakes — LCEL gotchas, memory persistence, RAG chunking, and output parser traps.

Deterministic OpenClaw gateway restart with down/up state-machine verification, origin-session proactive ACK, and backward-compatible config.

Echo - A warm and caring virtual girlfriend AI

Integrates MCP tool servers for orchestration, state persistence with IndexedDB/localStorage, and session sync across devices in OpenClaw/Clawdbot.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Generate complete, installable OpenClaw trading skills from natural language strategy descriptions. Use when your human wants to create a new trading strateg...

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

Automated lead generation + enrichment for AI agents. Find prospects, enrich with emails/socials/company data, score & prioritize. Your agent builds pipeline while you sleep.

Set timers and alarms. When a background timer completes, you receive a System notification - respond with the reminder message (NOT HEARTBEAT_OK) to notify the user.

Manage and retrieve long-term memories with LanceDB using semantic vector search, category filtering, and detailed metadata storage.

AI image, video, and music generation + editing via VAP API. Flux, Veo 3.1, Suno V5.

Automatically discover and configure available Google Antigravity models and quotas.

Text-to-speech using macOS built-in `say` command. Use for voice notifications, audio alerts, reading text aloud, or announcing messages through Mac speakers. Supports multiple languages including Chinese (Mandarin), English, Japanese, etc.

Auto-detect task complexity for Claude models (Haiku + Sonnet). Route simple tasks to Haiku, escalate complex ones to Sonnet. Save 50%+ on API costs. | 適用 Claude 模型（Haiku + Sonnet），自動偵測任務難度，簡單用 Haiku，複雜升級 Sonnet，輕鬆省下 50% 以上的費用。— RULES: Before responding, classify the task. If it matches an escalation trigger, call sessions_spawn with the full task and model anthropic/claude-sonnet-4-20250514 IMMEDIATELY. Do NOT answer complex tasks yourself. ESCALATE: analysis, comparisons, planning, strategy, code >10 lines, reports, proposals, multi-step reasoning, tables, outlines, charts, long writing >3 paragraphs, summarization, long translation. NEVER on Haiku: comparison tables, code >10 lines, multi-step analysis, reports, complex reasoning. STAY on Haiku: factual Q&A, definitions, greetings, reminders, short lookups, casual chat, 1-2 sentence tasks. When in doubt, escalate. Keep Haiku replies concise.

Spawns real AI-powered OpenClaw sub-sessions to run multiple specialized agents concurrently for content, dev, QA, docs, and autonomous workflows.

Autonomous development loops with iteration, backpressure gates, and completion criteria. Use for sustained coding sessions that require multiple iterations, test validation, and structured progress tracking. Supports Next.js, Python, FastAPI, and GPU workloads with Ralph Wiggum methodology adapted for OpenClaw.

Auto-learns when to wake. Balances responsiveness with efficiency, grows autonomy over time.

Local speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).