Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Enforces test-driven development principles to ensure high-quality code with mandatory 80%+ test coverage across unit, integration, and E2E layers.
Locates and validates source code repositories for Python packages using PyPI metadata and web search.
Analyzes Dependabot security advisories to provide actionable resolution strategies for direct and indirect dependencies.
Verifies mathematical formulas and expressions using Behavior-Driven Development workflows and automated LaTeX extraction.
Analyzes code changes for security vulnerabilities using LLM-powered reasoning and STRIDE threat modeling patterns.
Implements comprehensive ISO 14971 risk management processes throughout the medical device product lifecycle.
Automates deterministic service port assignment using color-based sequences to ensure consistent network discovery across environments.
Generates custom Semgrep rules to detect specific bug patterns and security vulnerabilities across various programming languages.
Transforms security scan findings into actionable, prioritized backlog tasks with automated acceptance criteria and workflow integration.
Audits Algorand smart contracts for security vulnerabilities including rekeying attacks and access control issues.
Conducts comprehensive security audits, threat modeling, and compliance verification to harden software against vulnerabilities.
Manages Glide app access, privacy settings, user authentication methods, and data-level security through Row Owners.
Performs deep binary analysis, decompilation, and malware research using industry-standard tools like Ghidra, IDA Pro, and radare2.
Formalizes and verifies complex mathematical theorems across music theory, color harmony, and distributed systems using Lean 4.
Bridges ElizaOS and OpenClaw plugins to the Goblins Object Capability Network to enforce high-security structural authority.
Automates the testing and evaluation of LLM agents using YAML-defined scenarios and AI-powered judge criteria.
Facilitates interaction, integration, and security auditing for the Ostium Protocol perpetual exchange on Arbitrum.
Validates security patches and fixes to ensure they completely resolve vulnerabilities without introducing new regressions.
Validates AI-generated code and agent outputs using real-time truth scoring and automated rollback systems to maintain high codebase reliability.
Automates a comprehensive six-phase quality assurance workflow to ensure code integrity before pull requests or deployments.
Implements rigorous quality assurance strategies, test plans, and acceptance criteria validation for high-reliability software development.
Traces and validates capability derivation chains using 3x3 expert posets and GF(3) conservation principles.
Conducts comprehensive security audits, scans for vulnerabilities, and manages secret detection across codebases.
Manages and optimizes Rust (Cargo) and Node.js (npm) dependencies to resolve version conflicts and ensure security compliance.
Implements a robust Red-Green-Refactor testing cycle specifically optimized for Rust development and the Miyabi framework.
Automates dependency management for Rust and Node.js projects to ensure security, stability, and version compatibility.
Standardizes testing workflows using Vitest, mock factories, and advanced fake timer patterns for the Tzurot ecosystem.
Orchestrates multi-model LLM consensus through a three-phase deliberation protocol for collaborative decision-making and high-integrity code reviews.
Facilitates collaborative AI reasoning by integrating OpenAI's Codex CLI for second opinions on code architecture, security analysis, and design decisions.
Audits cryptographic implementations for vulnerabilities, weak algorithms, and improper key management using industry-standard security tools.
Scroll for more results...