--- name: oc_guard description: Safe OpenClaw config planning/apply workflow with bilingual execution receipts. metadata: {"openclaw":{"requires":{"bins":["python3","openclaw","opencode"]}}} --- # oc
Safely run local `gpu` commands via a guarded wrapper (`runner.sh`) with preflight checks and budget/time caps.
Safe, zero-downtime database migration strategies — schema evolution, rollback planning, data migration, tooling, and anti-pattern avoidance for production systems. Use when planning schema changes,
Set up an agent wallet for Uniswap operations. Use when user needs to provision a wallet for an autonomous agent. Supports Privy (development), Turnkey (production), and Safe (maximum security). Confi
Expand reading insights into detailed notes using local templates only. SAFE VERSION: No external API calls, no filesystem access, no secrets required.
Write type-safe TypeScript with proper narrowing, inference patterns, and strict mode best practices.
Advanced editing of OpenClaw JSON5 configs with schema validation, merge patching, env var substitution, and type-safe modifications using jq.
Channel Aavegotchis on Base via Bankr. Checks cooldown, builds calldata, and submits channel txs safely.
Provision a dedicated inbox for your AI agent and manage email safely via thrd.email. Includes instant onboarding, inbound polling, reply/send (idempotent +...
Schedule and run safe daily/weekly updates for Clawdbot + installed skills using the Gateway cron scheduler. Use when setting up "run updates at 04:00" jobs, rotating update reports, running `clawdhub
Expose safe device actions (volume, brightness, open/close apps) for personal automation.
--- name: prts-sandbox description: Isolated Kali Linux sandbox for running pentest tools and risky commands safely. metadata: {"openclaw":{"emoji":"🛡️","requires":{"bins":["bash","curl","jq"]}}}
Control and automate Tuya Smart devices with official cloud APIs, secure request signing, region-aware routing, and safe command execution.
Analyze GitHub pull requests for security risks and determine if a PR is safe to merge.
Use rn-logs to read React Native Metro logs via CDP without MCP overhead. Default output is plain text and safe for non-interactive agent runs.
Run safe read-only queries against MySQL or PostgreSQL for data inspection, reporting, and troubleshooting. Use when the user asks to read tables, inspect schema, count rows, sample data, or export qu
Provides git-powered versioned backups and safe snapshot recovery for workspace files, with automated and manual snapshot options.
Connect to your Shelter financial data. Check safe-to-spend, predict cash crunches, find zombie subscriptions, simulate purchases, get AI coaching, and ask G...
AOI Council — multi-perspective decision synthesis templates (public-safe).
Systematically discover, evaluate, compare, and assess OpenClaw skills to find the right, safe, and high-quality option for your specific task.
Build tai chi practice plans, improve form, and track balance-focused sessions with safe progressions, concise coaching cues, and weekly reviews.
Guides users through safely uninstalling OpenClaw (龙虾). Use when user asks how to remove/uninstall OpenClaw, wants to clean up completely, or mentions paid c...
Analyze SKILL.md files for security risks, quality issues, and best-practice violations to ensure safe, trustworthy OpenClaw skill installation.
Index important directories and perform safe folder operations with proper security checks.