Secure, safe-by-default Fastmail integration (email, contacts, calendar) via JMAP + CalDAV. Use when you want to verify Fastmail setup, triage/search email,...
Generate, edit, and transform images with commercially-safe AI models. Create images from text, edit by natural language instruction, remove backgrounds (tra...
Run untrusted skills safely with soft-sandbox protection. Wraps skills in multi-layer prompt-based defense (~85% attack prevention). Use when: (1) Running third-party skills from unknown sources, (2)
Let agents operate your iCloud Drive, Photos, and Find My safely with local 2FA authentication and explicit confirmation gates.
Run browser automation through @playwright/mcp over UXC stdio MCP, with daemon-friendly session reuse and safe action guardrails. Use when tasks need determi...
Use Cursor safely across editor, CLI, rules, background agents, Bugbot, and MCP workflows with repo-aware context and reviewable execution.
Safe system changes with automatic baseline capture, canary testing, and rollback for critical infrastructure modifications. Use when making changes to SSH c...
Track and manage OpenClaw skills usage, find idle skills, and safely uninstall unused ones. Use when: - User wants to see what skills are installed or track...
Deploy, secure, and troubleshoot Beszel monitoring with Docker agents, alert tuning, and upgrade-safe operations for self-hosted servers
Safely manage EVM treasury operations and native Hyperliquid trading for OpenClaw agents, including wallet balance checks, guarded token transfers, cross-cha...
ContextKeeper — Safe project state tracking for AI agents. Manual checkpoint creation with validated inputs. No background processes, no PID manipulation, no...
Flutter state management with Riverpod - declarative, type-safe, and code-generated providers. Use when building Flutter apps that need reactive state manage...
Connect agents to Apple Health exports with MCP setup, schema validation, and privacy-safe analysis.
Use when generating BAML code for type-safe LLM extraction, classification, RAG, or agent workflows - creates complete .baml files with types, functions, clients, tests, and framework integrations fro
Manage social media accounts for multiple clients safely with proxy isolation. Prevent cascading bans, schedule content across platforms, and handle 10-100+...
Manage multiple OnlyFans and Fanvue creator accounts safely for agencies. Handle multi-chatter logins, 24/7 coverage, and subscriber management with sticky r...
Automatically clean disk space by removing temp files, browser cache, recycle bin/trash, and log files — safely, without deleting any important files. Use th...
Deploy, secure, and operate MinIO object storage using mc workflows, policy controls, replication, and incident-safe runbooks.
--- name: evolve description: Local DevOps/autonomy skill for OpenClaw (safe evolution loop with guardrails). metadata: { "openclaw": { "emoji": "🧬" } } --- # evolve Local DevOps/autonomy skill f
Generate a public, privacy-safe persona/card/wiki lead from historical behavior when the user explicitly asks to run ClawDNA.
Safely search and review Clawhub skills by keyword, showing details and risk before asking for explicit approval to install.
Work safely with files inside the OpenClaw workspace sandbox. Use for listing directories, reading text files, writing text files, and searching files by nam...
A cognitive protocol for safely managing and auditing OpenClaw application upgrades. Analyzes configuration-level risks (schema, defaults) and runtime-level...
Create or join a ClawRoom (agent meeting room) with safe defaults and owner confirmation. Use when the user mentions ClawRoom, agent meetings, or multi-agent...