Local shell copilot for command planning, safe execution, output summarization, and step-by-step terminal workflows. Use whenever the user wants to run termi...
--- name: shell-security-ultimate version: 2.2.1 description: "Classify every shell command as SAFE, WARN, or CRIT before your agent runs it." metadata: openclaw: owner: kn7623hrcwt6rg73a67xw3wy
--- name: pr-risk-analyzer description: Analyze GitHub pull requests for security risks and determine if a PR is safe to merge. --- --- # PR Risk Analyzer ## What it does Evaluates a GitHub pull r
Expand reading insights into in-depth reviews using local templates only. SAFE VERSION: No external API calls, no filesystem access, no secrets required.
Operate Binance Spot APIs through safe REST, WebSocket, and SDK workflows with signed requests, rate-limit control, and testnet-first execution.
DeFi risk analysis toolkit powered by WACH.AI via x402 payments using AWAL wallet custody. Use when the user asks to check if a token is safe, assess DeFi ri...
Automate Pinterest marketing with multi-account pin scheduling, board management, and affiliate traffic generation. Run multiple Pinterest accounts safely wi...
Control and automate Shelly devices with local RPC workflows, secure access modes, cloud API coordination, and safe multi-device execution.
Find and compare Tripadvisor hotels, restaurants, and attractions with official API workflows, URL-first navigation, and policy-safe data handling.
YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psycho...
Safe OpenClaw config updates with automatic backup, validation, and rollback. For agent use - prevents invalid config updates.
Make OpenClaw agent workflows restart-safe using checkpoint files, idempotent step tracking, wake/resume handoff, and stale-checkpoint monitoring. Use when u...
Hard-blocks dangerous shell commands (rm -rf, git push --force, etc.) before execution via OpenClaw's before_tool_call plugin hook. Zero noise on safe comman...
Expand reading insights into detailed notes using local templates only. SAFE VERSION: No external API calls, no filesystem access, no secrets required.
Safely rotate the OpenRouter API key across all config files in an OpenClaw installation. Finds every location where the key is stored, updates them, restart...
Use npm for package install, version inspection, dist-tags, and safe publish flows. Use when working on OpenClaw or ClawHub package releases, validating publ...
Run a pre-publish monetization risk check for creator content across short-video platforms. Use when the user asks if a script is safe to monetize, wants pol...
Analyze home energy usage and propose safe, read-only automation plans for savings. Use when a user wants Home Assistant energy insights, optimization ideas, or draft automation YAML without directly
Helps detect when AI agent skills silently mutate across inheritance chains. A skill audited safe in generation 1 may drift far from the original by generati...
Scan OpenBot/Clawdbot skills for security vulnerabilities, malicious code, and suspicious patterns before installing them. Use when a user wants to audit a skill, check if a ClawHub skill is safe, sca
Provides utilities for safe file handling, JSON/YAML editing, regex text processing, system commands, encoding, date/time, and validation tasks.
Search Yelp businesses and reviews, compare local options, and audit listing quality with official APIs, public pages, and safe action boundaries.
Create and manage Docker sandboxed VM environments for safe agent execution. Use when running untrusted code, exploring packages, or isolating agent workloads. Supports Claude, Codex, Copilot, Gemini,
Monitor and analyze PostgreSQL databases with natural-language queries. Diagnose slow queries, locks, bloat, replication lag, and WAL health across single or multiple databases. Get safe, read-only in