Security & Testing Agent Skills for Claude Desktop

Run Stryker mutation testing on the source files changed in the current branch (vs origin/master) across vitest packages.

Run Stryker mutation testing on a single source file and return a structured, token-frugal report that's pipeable to a follow-up…

Use when choosing native or multi-LLM handling for init, review, or security requests

Use when validating production readiness for a Navan API integration\

Analyze what a change could break beyond its diff and prove the central safety invariant with executable evidence.

Use when preparing an NDSS artifact for evaluation after conditional acceptance — targeting the Available, Functional, and Reproduced…

Use when designing or auditing the evaluation of an NDSS paper — attack demonstrations, defense evaluations under adaptive adversaries…

Use when making an NDSS paper's results reconstructible — snapshotting live-network observations, pinning testbeds and toolchains…

Use when hardening a plan, spec, design, resume, or codebase before an expensive or hard-to-reverse commitment, or when asked to "red team…

Help users run a local Ethereum dev chain, write integration tests, fork networks, debug transactions, or replace Hardhat/Anvil with…

Capture credentials and sensitive data from network traffic during an authorized assessment, including via layer-2 adversary-in-the-middle.

Stop and detect layer-2 adversary-in-the-middle and credential sniffing on internal networks.

NIS2 Directive (EU 2022/2555) compliance for critical infrastructure entities, covering the 10 minimum security measures.

Enter "offline mode" — for security reasons, do NOT use any tool or command that touches the internet or an external network.

Use when product or application logic may contain contradictory states, mixed date or filter scopes, KPI/card mismatches, misleading…

Use when fixing bugs, refactoring, changing shared state, or reviewing a patch where behavior that already works could regress; triggers…

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.

Use when setting up nono to run Claude Code securely, creating or modifying nono profiles, adding per-session filesystem permissions, or…

Audit an Effect codebase for silent error swallowing -- catchAll patterns that collapse errors into sentinel values (null, [], false…

Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis

OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews