Discover Agent Skills for security & testing. Browse 105 skills for Claude, ChatGPT & Codex.
Generates and validates production-quality Semgrep rules to detect security vulnerabilities and complex code patterns using a test-driven approach.
Scans Cairo smart contracts for critical vulnerabilities including arithmetic overflows, L1-L2 messaging flaws, and signature replay attacks.
Audits code for vulnerabilities and implements industry-standard protection patterns based on OWASP 2025 and Agentic AI security guidelines.
Audits Cosmos SDK modules and CosmWasm smart contracts for consensus-critical vulnerabilities and security risks.
Evaluates and benchmarks LLM agents using behavioral testing, reliability metrics, and production monitoring to ensure consistent performance in real-world scenarios.
Automates comprehensive end-to-end testing for the Kosmos autonomous AI scientist project across local and cloud LLM providers.
Quantifies repository health and production-readiness through weighted scoring across documentation, security, CI/CD, and community standards.
Automates compliance audits against industry-standard security and quality frameworks like OpenSSF, OWASP, and SOC2.
Enforces rigorous verification protocols and evidence-based reporting before any task or code change is claimed as complete.
Performs security-focused differential reviews of code changes to detect vulnerabilities and prevent regressions in PRs and commits.
Patches codebases to bypass checksums, non-deterministic states, and validation barriers to improve fuzzer coverage.
Provides expert cybersecurity advisory, threat modeling, and compliance mapping tailored to CISO, CTO, and Security Architect roles.
Implements advanced property-based testing strategies to ensure robust code reliability across multiple programming languages and smart contracts.
Configures and troubleshoots git hooks using Husky, Lefthook, and other industry-standard frameworks to automate code quality checks.
Automates the creation and management of robust Python test suites using the industry-standard pytest framework.
Automates web application testing by generating Playwright-based test harnesses and natural-language goal files for Gemini 2.5 Computer Use.
Implements continuous fuzz testing infrastructure for open-source projects using Google's OSS-Fuzz framework.
Enforces a rigorous evidence-based protocol that requires fresh command output before any task is claimed as finished or fixed.
Authors high-performance YARA-X detection rules for precise malware identification and threat hunting.
Implements a rigorous four-phase protocol to identify root causes and eliminate bugs through evidence-based troubleshooting rather than trial and error.
Implements multi-layer data validation strategies to prevent bugs and ensure system stability across all execution levels.
Systematically debugs complex software errors through hypothesis-driven analysis, solution comparisons, and multi-layer verification.
Enforces a strict Red-Green-Refactor testing methodology for Python-based AWS infrastructure and CLI tools.
Automates performance and load testing workflows using the k6 framework to ensure application scalability.
Guides users through the complete penetration testing lifecycle from initial reconnaissance to professional security reporting.
Enforces a rigorous evidence-based workflow that requires successful verification commands before any task is claimed as complete.
Enforces a strict Red-Green-Refactor workflow to ensure all production code is verified by failing tests first.
Provides actionable techniques and command-line references for escalating user privileges on Linux and Windows systems.
Implements a rigorous four-phase framework to identify root causes and eliminate trial-and-error debugging during development.
Parses, aggregates, and analyzes Static Analysis Results Interchange Format (SARIF) files to streamline security vulnerability management.
Scroll for more results...