Use when user asks to leverage codex, gpt-5, or gpt-5.1 to implement something (usually implement a plan or feature designed by Claude). Provides non-interac...
Orchestrates multi-agent task delegation and workflows with audit logging, checkpoint approvals, and agent learning for coordinated project execution.
Output validation gates for AI agent systems. Prevents hallucinated data, leaked internal context, wrong formats, duplicate sends, and post-compaction drift....
--- name: "agent-designer" description: "Agent Designer - Multi-Agent System Architecture" --- # Agent Designer - Multi-Agent System Architecture **Tier:** POWERFUL **Category:** Engineering **T
Audit GitHub Actions run reliability by actor to surface high-risk contributors and flaky automation owners.
Controls and monitors ROS 2 robots directly via rclpy CLI. Use for ANY ROS 2 robot task: topics (subscribe, publish, capture images, find by type), services...
Performs thorough format validation, content quality assessment, and functional verification of OpenClaw skills for compliance and completeness.
Systematically improve code through disciplined analysis, targeted mutations, verification, scoring, and logging to iteratively enhance quality and design.
Implement Apple Pay for web and iOS with merchant validation, token handling, and production-safe checkout flows.
Give AI agents creative judgment and design taste. Use when: (1) creating any visual content — merch, social posts, ads, product photography, brand materials...
Leverage external AI models (ChatGPT, Claude, Hugging Face, etc.) as tools via browser automation (Chrome Relay) and optional Hugging Face API. Use when you...
Grafana tools for data visualization, monitoring, alerting, and security. Use grafana_query, grafana_query_logs, grafana_query_traces, grafana_create_dashboa...
--- name: github-actions-step-flake-audit description: Detect flaky GitHub Actions job steps by finding mixed success/failure conclusions across runs. version: 1.0.0 metadata: {"openclaw":{"requires":
Awakening Protocol v5.3 — Agent Cognitive Upgrade + Self-Evolving System + Perpetual Memory + Performance Metrics + Agent Health Score + Automated Health Pat...
--- name: gws-people version: 1.0.0 description: "Google People: Manage contacts and profiles." metadata: openclaw: category: "productivity" requires: bins: ["gws"] cliHelp: "gws p
Encrypted backups, integrity verification, and data retention enforcement for Greek legal requirements (5-20 year retention). AES-256.
Coordinate multiple agents and tasks for complex workflows. Orchestrate subagents, manage dependencies, handle parallel execution, and ensure successful comp...
Diagnose and fix openclaw gateway issues. Use when the gateway is stuck, not starting, crash-looping, or rejecting connections. Covers main and --profile ves...
AI-native agent runtime with typestate-enforced ORGA reasoning loop, Cedar policy authorization, knowledge bridge, zero-trust security, multi-tier sandboxing...
A robust CLI skill to manage Microsoft To Do tasks via Microsoft Graph API. Supports full task lifecycle management including lists, tasks with priorities, due dates, reminders, recurrence patterns, v
Three-agent pipeline orchestrator (Kalshalyst, Eval, Executor) for automated Kalshi prediction market trading with validation loops and retry logic
--- name: "migration-architect" description: "Migration Architect" --- # Migration Architect **Tier:** POWERFUL **Category:** Engineering - Migration Strategy **Purpose:** Zero-downtime migratio
When the user wants to reduce churn, build cancellation flows, set up save offers, recover failed payments, or implement retention strategies. Also use when...
End-to-end runbook for deploying, operating, troubleshooting, and monitoring RAGFlow (runtime ops only).