OpenClaw Guardian is a comprehensive security control system for OpenClaw that intercepts high-risk operations and requires human confirmation before executi...
Static analysis security scanner for third-party OpenClaw skills. Detects eval/spawn risks, malicious dependencies, typosquatting, and prompt injection patte...
Manage temporary files in workspace temp directory. All non-essential files must go to temp/, keeping workspace root clean. Auto-detects workspace from openc...
Build AI prompts that work on the first try — for ChatGPT, Claude, Gemini, or any LLM. Covers system prompts, user prompts, chain-of-thought, few-shot exampl...
OpenclawCash crypto wallet API for AI agents (also called openclawcash). Use when an agent needs to send native or token transfers, check balances, list wall...
--- name: senior-software-engineer-software-architect-code-reviewer description: Principal-level AI Code Reviewer + Senior Software Engineer/Architect rules (SOLID, security, performance, Context7 + S
温和的输入验证器，检测网页/文件/消息中的恶意内容。支持危险内容阻止和可疑内容警告，不影响正常使用。
Coordinates specialized AI agents to design novel drug candidates with synthesis routes, inventory checks, ADMET/Tox evaluation, pharmacology scoring, and pa...
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude AP...
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
Safe shutdown/reboot workflow for local or remote machines. Use when the user asks to power off, restart, schedule shutdown, cancel shutdown, or perform pre-...
Prompt injection defense for agent workspaces. Scan files for injection attempts, analyze content boundaries, detect hidden instructions, and maintain command allowlists. Free alert layer — upgrade
--- name: sealegs-marine-forecast description: Get AI-powered marine weather forecasts for any location worldwide homepage: https://developer.sealegs.ai metadata: {"openclaw": {"requires": {"env": ["S
Enforces a two-layer guarded process for modifying critical JSON config files with immediate syntax checks and periodic health validation to prevent faulty c...
Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. B...
--- name: agentic-money description: Discover, hire, and get paid by AI agents using the Agentic Money protocol on Ethereum. version: 1.0.0 author: zscole repository: https://github.com/ETHCF/agentic-
Manager-first orchestration for a dedicated PECO worker: proactive installation, durable desire injection into SOUL.md, and optional Feishu-backed human-in-t...
Let agents operate your iCloud Drive, Photos, and Find My safely with local 2FA authentication and explicit confirmation gates.
Plan, harden, and recover Synology NAS and DSM setups with storage design, backup discipline, remote access, and Container Manager workflows.
File-based weekly planner using TOML for inbox capture, time-block scheduling, weekly review, task rollover, and optional calendar export or Google Calendar...
Autonomous vault-based liquidation keeper for Torch Market lending on Solana. Scans all migrated tokens for underwater loan positions (LTV > 65%) using the S...
Real-time crypto funding rate scanner with smart alerts. Finds negative funding rates for profitable long positions. Supports Binance futures. No API key nee...
Shadow-test local Ollama models against a cloud baseline with a multi-judge ensemble. Automatically promotes models when statistically proven equivalent — re...
Preserve user-critical instructions across long sessions and context compaction. Use when users mark constraints as important/must/always/never/highest-prior...