Testing skills

This skill orchestrates multi-step agent pipelines to build, debug, review, and publish software by chaining outputs across steps.

This skill guides you from wiring to ROS2 and safety in robotics projects, generating hardware plans, code, and debugging strategies.

This skill evaluates and reports AI skills against benchmarks, enabling quality gates and comparable metrics before production deployments.

This skill helps you build, debug, and deploy production-quality OpenClaw Telegram bots, enforcing safeguards, proper MEDIA handling, and Docker deployment.

This skill performs a comprehensive web quality audit with lighthouse-based checks and browser automation validation using PinchTab for real-world testing.

This skill helps manage vaccination records and schedules, perform pre-vaccination safety checks, and generate compliant plans for multi-dose vaccines.

This skill performs post-upgrade verification for OpenClaw, validates config, cron, and channels, and auto-repairs drift.

This skill provisions a disposable MySQL-compatible database instantly for prototyping, enabling quick SQL experimentation and ephemeral demos.

This skill installs, updates, repairs, and verifies the OpenClaw Router plugin locally, ensuring health, CLI access, and accurate stats.

This skill helps you register and manage trustless AI agents on TRON and BSC, track on-chain reputation, and verify identities.

This skill helps you manage and interact with multi-session LLM chats using OpenAI-compatible APIs, offering streaming, history, and per-session customization.

This skill validates the ClawHub publishing workflow by testing metadata, content quality, and upload readiness to ensure reliable skill deployment.

This skill enforces strict AI workflow controls, ensuring tasks follow checkpoints, style, and safety rules across multi-step projects.

This skill provides comprehensive Flutter testing guidance across unit, widget, and integration tests to improve coverage and reliability.

This skill guides you to migrate from pm-sim to polymarket-paper-trader and access all features and tests.

This skill guides you to optimize context management and reduce token costs by routing to specialized sub-skills and patterns.

This skill scans OpenClaw skills for malware and security issues using static analysis and optional sandboxing, delivering a trust score and safety

This skill performs a structured codebase QC audit across languages and generates a standardized PASS/WARN/FAIL report highlighting tests, linting, and docs.

This skill automates multi-agent quant research and backtesting, generating factors, strategies, and evaluations to accelerate profitable trading insights.

This skill installs and wires a coding-focused OpenClaw sub-agent for background coding, testing, and data-analysis tasks.

This skill helps you scaffold Node.js experiments inspired by GameDevBench methodology, enabling rapid setup, evaluation, and iteration of agentic capabilities