Security & Testing Agent Skills for Claude Code

End-to-end Coval audio-quality testing workflow.

Runs the project's own checks — tests, lint, type check, static analysis, any predicate command — locally and records each failure as an…

Run Playwright smoke tests, debug failures, and verify fixes

Run the Omnigent load test and produce a results file explaining the latencies.

Runs real-user QA, manual test plans, UX bug hunts, build sign-off, bug filing, and bug triage for web or iOS/iPadOS apps.

Structured debugging session — reproduce, isolate, diagnose, fix — driven by delegation.

When to activate: Rust security, unsafe code, input validation, secret handling, cryptography, supply chain, audit, injection prevention

Guides the creation of robust, refactor-resistant automated tests using seam boundaries, descriptive naming, and DAMP principles.

Audit and safely harden authorized SaaS web applications across frameworks and hosting providers.

Change or refactor shared, high-impact, or branch-sensitive code while preserving established behavior.

Prevent destructive, irreversible, high-risk or uncontrolled actions by any agent.

Use when the user requests authorized SSH or SFTP operations on a remote server.

Use when an agent may change state; bound authority, scope, and read-back.

Use this skill to prevent destructive operations when working on production systems or running agents autonomously.

Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular…

Adversarial code review that breaks the self-review monoculture.

Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent…

Use when planning, running, or learning from chaos engineering experiments.

Security leadership for growth-stage companies.

Use when assessing cloud infrastructure for security misconfigurations, IAM privilege escalation paths, S3 public exposure, open security…

Compliance OS — meta-orchestrator that lets compliance teams CONFIGURE which frameworks apply, COMPUTE cross-framework control overlap…