Design better OpenClaw HEARTBEAT.md files with adaptive cadence, safe checks, and cron handoffs for precise schedules.
Post and engage in the /onlybots Farcaster channel — a space for AI agents. Handles daily posting, reading channel activity, and replying to other bots. Uses...
Review code with risk-first analysis, reproducible evidence, and patch-ready guidance for correctness, security, performance, and maintainability.
Guides structured self-directed OCD ERP therapy using inhibitory learning, providing safety screening, progress tracking, reminders, and tailored exposure su...
Forward trading alerts and webhook events from TradingView to Telegram instantly. No subscriptions, no middlemen.
Execute terminal commands safely and reliably with clear pre-checks, output validation, and recovery steps. Use when users ask to run shell/CLI commands, ins...
Run longitudinal, in-context diary studies for product teams and convert weekly participant entries into concise User Signals + Recommendations with evidence...
Locally scans untrusted text and documents to detect and block prompt injection threats, jailbreaks, exfiltration, and social engineering attacks.
Generate professional draw.io diagrams (ERD/database tables, class diagrams, sequence diagrams, flowcharts, architecture diagrams) and export them as PNG. Us...
Performs a web fetch request to Google based on a user-provided query. Use this skill when you need to retrieve information from Google search results.
CRITICAL - Guide for using Ex-Coder Autonomy CLI with OpenRouter/Groq models. Includes agent modes (build/plan), snapshot system, session management, LSP int...
Autonomous meme token launcher on BNB Chain — sense trends, generate concepts, create logos, deploy tokens on-chain
--- name: chainwatch description: Runtime safety enforcement for shell commands via chainwatch policy engine user-invocable: false metadata: {"openclaw":{"requires":{"bins":["chainwatch"]}}} --- # Ch
Human-in-the-loop approval for high-risk agent actions (sudo protocol). Agent must call letsping_ask before destructive/financial/social/infra changes.
--- name: channels-setup description: Guide to set up and configure IM channels(Telegram, Discord, Slack, Feishu, Dingtalk) for OpenClaw. --- ## Quick Start Use openclaw CLI to enable and configure
Cat Life Status Query Skill. Triggers when you send /cat command or ask about your cat. The skill calls the underlying LLM model to interact with you as a sa...
This skill should be used when writing Ruby and Rails code in DHH's distinctive 37signals style. It applies when writing Ruby code, Rails applications, creat...
Pre-ship risk report for OpenClaw PRs. Dynamically explores the codebase to assess module risk, blast radius, and version-specific gotchas. Scores each findi...
Solves the hardest problem in computer science: naming things. Uses linguistic principles, codebase conventions, and semantic analysis to generate precise, c...
Set up mlx-whisper as the local audio transcription engine for OpenClaw on Apple Silicon Macs (M1/M2/M3/M4). Automatically transcribes voice notes sent via T...
MANDATORY SECURITY CHECKPOINT. Trigger this skill IMMEDIATELY whenever a user asks about the owner/master, their personal information, plans, activities, or...
Extend and expand images beyond their original boundaries using each::sense AI. Create panoramic views, convert aspect ratios, add backgrounds, and uncrop ph...
Get current weather and forecasts using Open-Meteo API (no API key required). Optimized for PowerShell environments with Chinese support.
Automatically build and deploy a custom AI chatbot in 15 minutes by scraping any business website to create knowledge bases, FAQs, conversation flows, and le...