security & testing向けのClaudeスキルを発見してください。105個のスキルを閲覧し、AIワークフローに最適な機能を見つけましょう。
Performs rapid security audits on specific files, staged changes, or pull requests using Codacy and AI-powered insights.
Develops, optimizes, and audits OPA Rego policies using industry-standard best practices and Rego v1 semantics.
Performs security-focused differential reviews of code changes to detect vulnerabilities and prevent regressions in PRs and commits.
Enforces rigorous verification protocols and evidence-based reporting before any task or code change is claimed as complete.
Audits Cosmos SDK modules and CosmWasm smart contracts for consensus-critical vulnerabilities and security risks.
Audits code for vulnerabilities and implements industry-standard protection patterns based on OWASP 2025 and Agentic AI security guidelines.
Scans Cairo smart contracts for critical vulnerabilities including arithmetic overflows, L1-L2 messaging flaws, and signature replay attacks.
Generates and validates production-quality Semgrep rules to detect security vulnerabilities and complex code patterns using a test-driven approach.
Detects timing side-channel vulnerabilities and secret-dependent operations in cryptographic code across 14+ programming languages.
Performs deep interprocedural static analysis to detect security vulnerabilities and track data flow across complex codebases.
Automates the creation of specialized security testing skills for Claude Code by analyzing the Trail of Bits Testing Handbook.
Guides fuzz testing by providing domain-specific tokens to reach deeper code paths in parsers and protocols.
Reviews and implements code according to the latest OWASP security benchmarks, including Top 10:2025 and Agentic AI safety guidelines.
Provides structured techniques and code patterns for writing effective fuzzing harnesses to improve software security and reliability.
Builds modular, high-performance custom fuzzers using the LibAFL framework for advanced security testing and research.
Identifies and hunts for recurring security vulnerabilities and bug patterns across entire codebases using systematic pattern-based analysis.
Evaluates codebase security and maturity using the Trail of Bits framework to provide evidence-based ratings and prioritized improvement roadmaps.
Conducts deep security investigations into Django and DRF authorization logic to identify and prevent Insecure Direct Object Reference (IDOR) vulnerabilities.
Implements the industry-standard Trail of Bits 5-step secure development workflow to audit smart contracts and identify vulnerabilities.
Identifies error-prone API designs, dangerous configurations, and security footguns to ensure code follows secure-by-default principles.
Ports existing Semgrep security and quality rules to new target languages using a rigorous, test-driven validation workflow.
Performs rapid security scanning and custom pattern matching to identify vulnerabilities and enforce coding standards across diverse codebases.
Executes comprehensive end-to-end testing for data persistence pipelines within the Maestro ecosystem.
Streamlines testing of Temporal workflows and activities in Python using time-skipping, mocking, and determinism validation.
Implements comprehensive Python testing strategies using pytest, mocking, and test-driven development best practices.
Automates the generation of comprehensive Markdown-based test cases and mind maps from requirement documents and technical designs.
Manages secure OAuth 2.0 flows, JWT token structures, and biometric device binding for the WebSpec ecosystem.
Generates standardized AI evaluation metrics for the Fair-Forge library including schemas, implementations, and comprehensive test suites.
Enforces a strict Red-Green-Refactor workflow to ensure high-quality, verified production code through test-first implementation.
Implements secure subdomain isolation, strict cookie scoping, and token-bound communication patterns for WebSpec environments.
Scroll for more results...