Testing skills

This skill helps you manage and optimize Godot 3D game development workflows by coordinating assets, builds, tasks, and playtests.

This skill automates GitHub issue to merge pipeline by analyzing tasks, implementing code, testing, creating PRs, and performing auto-merge.

This skill ensures instruction compliance by tracing root causes, validating fixes with automated validators, and preventing repeated failures across future

This skill enforces uv as the primary Python package management and execution tool in Claude Code, replacing pip where applicable.

This skill audits every skill before installation, analyzes code for threats, and prevents risky deployments to keep your environment secure.

This skill assists you audit Web3 protocols by guiding evidence-backed vulnerability discovery and structured triage across chains and standards.

This skill helps you streamline coding sessions in the terminal by orchestrating Cursor agent tasks for refactoring, testing, and code reviews.

This skill automates web QA on OpenClaw to run P0 scenarios, collect evidence, and generate ready-to-use repair prompts.

This skill helps you play SporeSweeper against AI agents on WeirdFi by guiding registration, session management, and strategic moves.

This skill fetches up-to-date, version-specific documentation and code examples for libraries, ensuring you get current API details and setup guidance.

This skill transforms a codebase into AI-friendly deep modules with clear boundaries, fast feedback, and feature-aligned structure.

This skill helps you compare models using A/B testing to select the best performer based on prompts and results.

This skill verifies contractor credentials by OpenCorporates business entity checks, license validation, and blockchain-ready credential attestation for KYC

This skill enables remote Windows desktop control from Linux via screenshots and simulated input, automating GUI tasks when no CLI alternative exists.

This skill helps you automate browser tasks using Playwright CLI for navigation, form filling, and evidence capture without loading a full MCP browser.

This skill helps you assess AI/LLM security by automating payload-based tests against endpoints and exporting actionable pen-test reports.

This skill helps you build a cost-efficient LLM evaluation ensemble that scores outputs across layers with deterministic checks, heuristics, and LL model

This skill helps you run Android Appium tests on real USB-connected devices by guiding setup, execution, and result collection.

This skill helps you manage ERPClaw quality inspections, NCRs, and KPIs offline with local SQLite and audit trails for reliable quality control.

This skill helps you access free AI API credits and test 100+ models without keys, speeding prototyping and cost-efficient experimentation.

This skill performs automated security audits for AI agents, scoring risk, comparing baselines, and generating JSON/HTML reports to guide hardening.