Discover Agent Skills for security & testing. Browse 105skills for Claude, ChatGPT & Codex.
Enhances the code review process with systematic checklists, constructive feedback patterns, and language-specific best practices to improve code quality.
Builds robust evaluation frameworks and multi-dimensional rubrics to measure AI agent quality, accuracy, and efficiency.
Automates the detection, classification, and resolution of errors encountered during AI-driven development sessions.
Guides the creation of robust Gleam test suites using gleeunit and modern idiomatic assertion patterns.
Performs comprehensive API security assessments using advanced fuzzing, IDOR exploitation, and GraphQL vulnerability discovery techniques.
Configures Claude Code tool permissions and security rules to control access to files, commands, and web tools.
Streamlines .NET test failure analysis by capturing errors and generating focused rerun filters.
Optimizes Clay integrations through automated load testing, Kubernetes auto-scaling, and proactive capacity planning.
Identifies and exploits authentication and session management vulnerabilities in web applications to prevent unauthorized access and account takeovers.
Provides a systematic framework for detecting, exploiting, and remediating Insecure Direct Object Reference (IDOR) vulnerabilities in web applications.
Performs comprehensive network packet capture, filtering, and protocol analysis for troubleshooting and security investigations.
Automates and standardizes the release verification process for Jomonsho projects through tiered linting, type-checking, and multi-level testing.
Provides expert guidance on Ruby testing assertions, expectations, and the creation of custom RSpec matchers.
Provides expert guidance and command-line patterns for network discovery, vulnerability assessment, and security auditing across diverse environments.
Provides a comprehensive command reference for penetration testing tools including network scanning, exploitation, and vulnerability assessment.
Conducts comprehensive security assessments of SSH services including enumeration, credential attacks, and vulnerability exploitation.
Verifies feature implementation through automated browser-based end-to-end testing and acceptance criteria validation.
Conducts comprehensive SQL injection vulnerability assessments to identify, exploit, and remediate database security flaws in web applications.
Provides specialized techniques and command patterns for escalating system privileges from low-level access to root or administrator status.
Automates and validates local web applications using Playwright for end-to-end testing and UI debugging.
Identifies and exploits HTML injection vulnerabilities to secure web applications against content manipulation and phishing attacks.
Executes targeted code fixes for issues identified in prior reviews using parallel subagents and automated verification.
Automates error detection, classification, and recovery to maintain continuous and resilient autonomous coding sessions.
Enforces rigorous, evidence-based verification protocols before allowing any claims of task completion or code success.
Standardizes and automates high-quality unit testing for CUI Java projects using JUnit 5 and specialized generator frameworks.
Performs comprehensive, expert-level assessments of software architecture and code quality to identify technical risks and scaling opportunities.
Automates code verification by suggesting and running context-aware tests, lints, and syntax checks after every modification.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality code through mandatory test-first implementation.
Implements comprehensive input and output safety checks to secure AI agent interactions and protect sensitive data.
Automates local web application testing and debugging using Playwright for comprehensive frontend verification and UI interaction.
Scroll for more results...