Skill UI

This skill performs a full-sweep analysis across all quality dimensions including code decay, architecture, tech debt, and test quality. It applies fixes directly to the codebase, auto-applying safe changes and confirming risky ones before execution. It iterates through reviews, tests, debt, and audits to converge on a clean state, generating a comprehensive Full Sweep Report.

This skill guides authorized security assessments and bug bounty engagements. It covers scope definition, evidence collection, impact validation, and reporting. It enforces mandatory authorization checks before testing to ensure legal compliance and safety. It helps organize the workflow for finding and reporting vulnerabilities responsibly.

An adversarial AI skill designed to hunt down bugs, logic errors, and security flaws in any codebase. Unlike standard reviews, it actively tries to break the code to ensure correctness. It covers logic errors, null safety, edge cases, security vulnerabilities, and more. Use this for deep correctness passes rather than style reviews.

This skill provides language-specific super-code guidelines for C programming. It covers idiomatic practices for memory management, pointers, arrays, error handling, strings, structs, and preprocessor usage. It highlights anti-patterns and best practices to ensure safe, efficient, and maintainable C code within project conventions.

Detects error propagation and chain failures in agent workflows. Identifies vulnerabilities like single-point breakdowns, unbounded retries, and unsafe data propagation to ensure system stability and safety during multi-step operations.

Run an AFP 100-point or AUSTRAC safe-harbour identity check over a document set and report the points attained plus exactly what is missing, so onboarding teams can request only the absent documents and re-run the check.

This skill enables AI agents to control the user's visible browser interface directly. It supports navigation, clicking, typing, and debugging actions within the browser pane. The agent can take screenshots, interact with web tools, and handle login processes. It operates via a live Automation REPL without requiring code mode, ensuring safe and scoped interactions within the current session.

Analyze a repository to detect its tech stack, build tools, and monorepo structure, then generate a reviewed read-only allow list for Claude Code settings.json permissions. Helps set up or audit project permission baselines safely.

Deploy AWS infrastructure using CloudFormation templates, stacks, change sets, nested stacks, and drift detection for safe, repeatable infrastructure as code.

Expert guidance on AWS CloudFormation template optimization, nested stacks, drift detection, and production-ready patterns. Use when writing or reviewing CF templates for maintainability, cost, and safety.

This skill enables non-interactive execution of the Antigravity CLI for coding tasks. It involves setting the working directory, checking CLI availability, and running tasks via JSON output format. Users must handle authentication separately and respect permission settings. It parses JSON status fields to determine success or failure. Safety measures include avoiding interactive modes, not handling credentials, and managing file permissions within the workspace. Use this when delegating coding work to Antigravity.

Run Claude Code non-interactively for coding tasks via the claude -p CLI with JSON output. Covers availability checks, timeouts, read-only tool defaults, and safe handling of missing authentication.