Security & Testing Agent Skills

Enforces a strict Red-Green-Refactor cycle to ensure reliable software behavior and high test coverage before writing production code.

Use this skill when the user wants a review or security audit of code or documentation.

Comprehensive checklist for conducting thorough code reviews covering functionality, security, performance, and maintainability

Test authoring guidance

Use PROACTIVELY when auditing code quality, running security scans, assessing technical debt, reviewing code for production readiness…

Instructs AI coding agents to invoke CodeGuard MCP Server security rules before writing or reviewing code.

Comprehensive guide for setting up and configuring CodeQL code scanning via GitHub Actions workflows and the CodeQL CLI.

Ask Codex CLI (gpt-5.6-sol) to run local app verification that needs computer use, browser automation, simulators, screenshots, app…

QA the omo Codex Light edition (lazycodex / packages/omo-codex) itself, in strict isolation so ONLY our plugin is exercised, never the…

Compare screenshots to judge which image is less wrong, not to match a baseline.

Internal downstream skill for ctf-sandbox-orchestrator.

Audit a website, app, or product's codebase for GDPR and EU AI Act compliance, then hand back a ranked list of plain-English fixes.

Inspects storyboards and visual scripts for NSFW, violent, and sensitive content to ensure platform policy compliance.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition…

Conduct a defensible cybersecurity risk assessment using the NIST SP 800-30 Rev 1 methodology: prepare scope and a risk model, identify…

This skill should be used when the user says "configure hooks", "set up quality gates", "add PostToolUse hook", "set up permission hooks"…

A skill with consecutive hyphens in the name.

Build or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services.

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket…

Implement secure authentication in Convex with user management and access control.

Spin up a live local Omnigent server and exercise the GitHub Copilot SDK harness end-to-end — build copilot agents, run real turns…