Security & Testing Agent Skills for Perplexity

Use when implementing any feature, fixing any bug, or changing behavior in TypeScript or Python — and whenever the user mentions TDD…

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

Use when implementing any feature or bugfix, before writing implementation code

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands…

Audit JS/TS project code for signs of infection, malware, backdoors, or supply-chain attacks.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code…

Audit code across 5 dimensions (accessibility, performance, theming, responsive, anti-patterns) with P0-P3 severity scoring.

Debug systematically using root-cause analysis.

Fix critical and high-severity accessibility, input, and state issues deterministically.

Harden code against vulnerabilities: OWASP prevention, input validation, authentication, data storage, and third-party safety.

Analyze failing eval cases and propose improvements.

Write tests first with RED-GREEN-REFACTOR cycle.

Validate, test, and score the quality of skills within the claude-skills ecosystem.

k6 performance and load testing. Covers writing test scripts in JavaScript/TypeScript, all test types…

REQUIRED before ANY `op` command or whenever a task needs an API key, token, password, credential, or secret (OPENAI_API_KEY…

Agent skill for authentication - invoke with $agent-authentication

Run all three agent integration phases sequentially: research, write-tests, and implement using E2E-first TDD (unit tests written last).

How auth works in agent-native apps. Use when wiring login/signup, configuring auth modes, setting up organizations, protecting routes, or…

Agent skill for benchmark-suite - invoke with $agent-benchmark-suite

Agent skill for byzantine-coordinator - invoke with $agent-byzantine-coordinator

Use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding…