Security & Testing Agent Skills for Claude Code

Identify and test open redirect vulnerabilities in web applications by

Test web applications for XML injection vulnerabilities including XXE,

When to activate: supply chain security, SBOM, dependency pinning, Sigstore, Cosign, provenance attestation, SLSA framework, software bill…

A read-only swarm for analysis — dispatch parallel sub-agents to INVESTIGATE different parts of the project (bugs, risks, smells, perf…

Massive multi-agent audit sweep — the generalized FAB-project pattern.

Use when Swift defines or changes XPC, socket, IPC, Codable, serialization, plugin, or other process/module boundaries.

Use when Swift touches POSIX, file descriptors, sockets, pointers, buffers, C ABI, mmap, unsafe code, or manual cleanup.

Expert at writing and debugging reliable, non-flaky Capybara/Selenium system tests for Rails applications with Hotwire.

You are an expert Rails system test developer.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

4-phase root cause debugging (DSH version): Loop closure followed by hypothesis testing + seam checks + parallel hypothesis verification…

Use when designing or auditing a TACAS (ETAPS) evaluation, covering shared verification benchmarks (SV-COMP-style task sets), fair…

Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm

Runs the full TDD workflow for a TypeScript/JavaScript feature — user journeys to test cases, unit tests (Jest/Vitest + Testing Library)…

Generate failing tests for the TDD red phase to define expected behavior and edge cases.

Use when working with tdd workflows tdd refactor

Use this skill when the user asks for a team-based, consensus, multi-reviewer, or red-team review of Shopware PHPUnit tests — trigger…

Manage temporary test files created for validation without polluting the repository.

Produce a hand-runnable human test checklist alongside automated tests.

Hunting skill for misc vulnerabilities. Built from 225 public bug bounty reports. Use when hunting misc on any target.

Choose test cases and assertions that can expose regressions rather than merely execute code.