Classifies tasks by safety and complexity to route safe, negligible queries to gpt-5.1-codex-mini and escalates critical or executable tasks to gpt-5.3-codex.
Safety monitoring and tripwire detection for AI agents. Protects against unauthorized file access, dangerous commands, and excessive activity. Auto-halts on...
OpenClaw auto-update checker and safe applier. Checks for new versions, compares changelogs, and applies updates with rollback safety. Designed to run as a c...
Publishes and syncs local bot skills to ClawHub using non-browser login, preflight safety checks, and automated release scripts for single or batch workflows.
A comprehensive OpenClaw workspace framework providing session protocols, memory system, git workflow, safety rules, priority triage, communication handoffs,...
Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system
--- name: theta-edgecloud-skill description: Theta EdgeCloud API-key-first runtime scaffold with secure command-scoped auth and dry-run safety. metadata: openclaw: homepage: https://docs.thetato
Generate short, funny roasts for social bots with safety filters; free tier allows limited daily use, paid plans increase quota via on-chain entitlement.
Welcome new users to the agent ecosystem. Teaches what agents can do, safety practices, ClawdHub skills, Solvr knowledge sharing, and essential commands.
Order food, groceries, and book restaurants in India via Swiggy's MCP servers. Food delivery, Instamart groceries, and Dineout restaurant bookings with safety-first confirmation workflow.
Fundamental equity analysis and peer ranking using a structured scoring playbook (quality, balance-sheet safety, cash flow, valuation, sector adjustments, co...
Full Self-Driving agent with highest safety standards (Camera-Only, Redundant Checks).
Security blacklist protecting AI agents from malicious skills, scams, and prompt injection. Use before executing external commands, visiting unknown URLs, or installing new skills. Triggers on "securi
Security audit for external resources (GitHub repos, downloaded skills, files). Detects malicious code, suspicious executables, and content mismatches. Use w...
Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.
Adds equilibrium-constrained reasoning to OpenClaw, ensuring all operations maintain balance for coherent, self-validating, and consistent AI responses.
ファイル・設定・データベース・デプロイの変更を伴うタスクで発動。デバッグが2回以上連続で失敗した時に発動。証拠なしに推測・仮定しようとした時に発動（「おそらく」「多分」「〜だと思う」「〜のはず」）。ユーザーに丸投げしようとした時に発動（「ご確認ください」「手動で対応してください」「〜が必要かもしれません」）。修正...
Secure password generator with multiple character sets and strength analysis. Use when: (1) generating strong passwords, (2) creating memorable passphrases,...
Simplify SQL querying and troubleshooting for MySQL, PostgreSQL, and SQLite. Use when users ask to inspect schema, convert natural language to SQL, debug SQL...
Complete Zod validation library documentation. Use when working with Zod schema validation, TypeScript type inference, form validation, API validation, error handling, or data parsing. Covers schema d
Email for AI agents. Create inboxes, receive and send email. No API keys, no human signup.
Scan OpenClaw skills for security risks, suspicious permissions, and provide a trust score to help evaluate skill safety before use or installation.
Analyze SKILL.md files for security risks, quality issues, and best-practice violations to ensure safe, trustworthy OpenClaw skill installation.