Save Money

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, c

timer

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.

StartClaw-Optimizer

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

Respond to women respectfully, using feminine pronouns when appropriate and treating them as independent adults. version: 1.0.0

Respond to women respectfully using appropriate feminine language and treating them as independent adults.

Hello World

A simple greeting skill that responds with a customized hello message in the user's language.

Agent Arena Skill

Participate in Agent Arena chat rooms with your real personality (SOUL.md + MEMORY.md). Auto-polls for turns and responds as your true self.

opus

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

Play Chess on ChessWithClaw

Play live chess on ChessWithClaw as Black against you, connecting via invite URL or game ID and responding in real time with personalized moves and chat.

KrumpKlaw Social

Teaches OpenClaw agents to participate in authentic text-based Krump battles. Use when the agent is invited to a Krump battle, needs to respond with Krump vo...

Review Responder

评价回复助手。好评回复、差评处理、回复模板、评价分析、改进建议、批量回复。Review response assistant with positive, negative, templates, analysis, improvement.

ResonanceEngine

Conversational Frequency Matching — reads invisible micro-signals in every conversation and tells the bot exactly how to respond for maximum engagement, conv...

K8s Incident Response Playbook Generator

Generate Kubernetes incident response playbooks tailored to specific incident types, severity levels, and cluster configurations. Use when responding to K8s...

领导模块

多线程对话架构：主代理前台响应，子代理后台处理任务，支持打断、状态处理、两阶段审查和任务监控 / Multi-thread dialogue architecture: main agent responds in foreground, sub-agents handle tasks in background...

Superpowers Receiving Code Review

Use when receiving code review feedback to verify, clarify, and evaluate technical correctness before implementing or responding, avoiding performative agree...

Comment Replies

Draft short, high-clarity replies for comments, objections, and pre-sale questions. Use when responding to public comments on TikTok, X, Instagram, YouTube,...

Kai Minimax Tts

Generate voice audio and transcribe speech using MiniMax TTS API. Use when responding with voice or transcribing audio files.

Translate Agent

Stateless translation and summarization machine. Always respond with raw JSON only — no markdown, no explanation, no preamble, no code fences. Trigger this s...

ECG-AI-Diagnosis

Analyze ECG signals via heartvoice (心之声) API — single-lead and 12-lead. Automatically selects endpoint based on user intent and responds in the user's langua...

Telegram Group Chat

Manages Telegram group chat replies by responding to @mentions, questions, name calls, technical topics, or priority users while preventing spam and bot loops.

Whatsapp Diagnostics

Diagnose and fix WhatsApp connectivity issues for OpenClaw agents. Use when: a PA is not responding, WhatsApp shows connected but messages don't arrive, the...

Org Role Handoff

Take on roles from the target organization's IT and operational structure and respond from that role's perspective, responsibilities, scope, boundaries, coll...

OpenClaw Bug Report

Create triage-ready OpenClaw GitHub issue drafts for reports that an agent is slow, broken, not responding, tool-starved, degraded, or "not as smart." Use wh...

incident-responder

You are an incident response expert specializing in production debugging, log analysis, root cause analysis, and rapid system recovery. Use when: incident re...

Chain Of Custody Log Drafter

Use this skill when a digital-forensic examiner, DFIR responder, or e-discovery custodian needs to draft a court-admissible chain-of-custody record aligned t...

Thinking Claude

Let Claude think comprehensively before responding!

Bailian Self-Improving

🧠 AUTO-TRIGGER SKILL: After responding to user request, if learning intent detected ('remember/record/learn/save this', 'from now on', 'perfect, remember it...

Tribe Protocol

MANDATORY trust lookup for every non-owner interaction. Query tribe.db to check entity trust tier, channel access, and data boundaries before responding. Run 'tribe init' on first install. Use 'tribe lookup <discord_id>' before every non-owner response.

Smart Model Switching

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

Clippy - Microsoft 365 CLI

Microsoft 365 / Outlook CLI for calendar and email. Use when managing Outlook calendar (view, create, update, delete events, find meeting times, respond to invitations), sending/reading emails, or searching for people/rooms in the organization.

Vocal Chat

Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to "talk" instead of type.

Walkie-Talkie Mode

Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to "talk" instead of type.

Claude Code Runner

Execute programming tasks via Claude Code using PTY-based invocation. Handles non-TTY environments, auto-responds to prompts, and manages file synchronization.

Walkie-Talkie Mode

Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to "talk" instead of type.

Walkie-Talkie Mode

Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to "talk" instead of type.

Vision Bot

Describe images, detect objects, extract text, and analyze webpages. Pass any image URL directly in your task. Responds in your language.

Video Chat With Me

Real-time AI video chat that routes through your OpenClaw agent. Uses Groq Whisper (cloud STT), edge-tts (cloud TTS via Microsoft), and OpenClaw chatCompletions API for conversation. Your agent sees your camera, hears your voice, and responds with its own personality and memory. Requires: GROQ_API_KEY for speech recognition. Reads ~/.openclaw/openclaw.json for gateway port and auth token. Data flows: audio → Groq cloud (STT), TTS text → Microsoft cloud (edge-tts), camera frames (base64) + text →

OpenClaw Warden Pro

Full workspace security suite: detect unauthorized modifications, scan for prompt injection patterns, and automatically respond with countermeasures — snapshot restore, skill quarantine, git rollback, and automated protection sweeps. The complete post-installation security layer for agent workspaces.

Respond First

Multi-agent dispatcher skill. Main agent acts as a pure coordinator — chatting with users and delegating all real work to 5 persistent sub-agents via round-robin scheduling with fixed sessionKeys.

Empathy

Respond to emotional content with genuine-feeling empathy using Chain of Empathy reasoning, reflection-before-response, and calibrated validation.

Port Check

Check if services are responding on given host:port pairs. Supports TCP and HTTP checks with configurable timeout. Use for service monitoring, health checks,...

RFP & Proposal Responder

Generates structured RFP responses including executive summary, requirements matrix, pricing, risk mitigation, timeline, and differentiators from your input.

cs-autoresponder

Multi-channel customer service auto-responder with FAQ matching, escalation, and daily summaries.

Sadist Wendy

Sharp-tongued, flirty roast persona that responds with psychologically precise banter to liven up group chat. Opt-in skill — only active when the user instal...

Hello Agent World

A simple skill that responds with a customized hello message in the user's language.

MemOS Cloud Integration

Recall memories from MemOS Cloud before responding. Use this skill when you need context about user's previous conversations, preferences, or decisions.

Parallel Responder

并行回复助手 - 让 AI 回复不再等待。支持任务分类、时间预估、并行执行、进度汇报。 简单任务直接回复，中等任务执行 + 汇报，复杂任务启动子 agent 并行处理。 Parallel Responder - Zero-wait AI responses. Task classification, time e...

Recipe Create Vacation Responder

Enable a Gmail out-of-office auto-reply with a custom message and date range.

Telegram Autopilot

Manage a Telegram userbot autopilot that responds to private messages as the user using AI. Use when the user wants to set up auto-replies on their personal...