A community-driven catalogue of 150+ reusable AI agent skills for Claude Code , Antigravity, Cursor Ai , kimi , deepseek ,Mimo — code review, security auditing, architecture review, and more. Install any skill with one npx command.
Skill Claude CodeCodex
Reviews how a feature or system handles PII, data retention, and consent against common privacy-framework principles (GDPR-style). Use when a feature collects, stores, or processes personal data - not a substitute for legal advice.
Skill Claude CodeCodex
Reviews Cross-Origin Resource Sharing configs, CSRF protections, SameSite cookies, and origin security.
Skill Claude CodeCodex
Reviews cipher algorithms, key derivation parameters (Argon2, bcrypt), token signing keys, and TLS settings.
Skill Claude CodeCodex
Formulates redaction rules and masking strategies for PII, secrets, and customer data in logs and staging.
Skill Claude CodeCodex
Triages CVEs and Dependabot/Snyk security alerts to assess real runtime exploitability and reduce alarm fatigue.
Skill Claude CodeCodex
Structures raw incident notes into a blameless postmortem - timeline, root cause, impact, and action items. Use after an incident/outage once the immediate fire is out and it needs to be documented.
Skill Claude CodeCodex
Audits JSON Web Token implementations for algorithm confusion attacks, key rotation, expiration, and replay defense.'.
Skill Claude CodeCodex
Designs Role-Based and Attribute-Based Access Control models, permission bitmasks, and multi-tenant boundary checks.
Skill Claude CodeCodex
Narrowly scans code and config for hardcoded secrets, credentials, API keys, and tokens. Use before a commit/PR, or when auditing a codebase for accidentally-committed secrets.
Skill Claude CodeCodex
Prepares automated audit trails, access review logs, change management records, and infrastructure evidence for SOC 2 audits.
Skill Claude CodeCodex
Performs proactive, pre-implementation threat modeling (STRIDE-style) for a feature or system before it's built. Use when designing something new that touches user data, auth, money, or external input, before writing code.
Skill Claude CodeCodex
Designs chaos engineering experiments like network latency injection and node termination to validate resilience.
Skill Claude CodeCodex
Establishes consumer-driven contract tests using Pact or OpenAPI to prevent breaking changes across services.
Skill Claude CodeCodex
Plans high-value end-to-end critical user journeys with Playwright or Cypress focusing on revenue-critical flows.
Skill Claude CodeCodex
Focuses specifically on unusual inputs, boundary conditions, empty states, and unexpected user behavior that implementations commonly miss. Use to find what a normal test pass would skip over.
Skill Claude CodeCodex
Diagnoses why a test passes sometimes and fails others - timing, shared state, ordering dependence, or external dependencies - and proposes a fix. Use when a test fails intermittently.
Skill Claude CodeCodex
Creates property-based and mutation fuzz testing harnesses (AFL, Atheris, fast-check) to discover unexpected panics and crashes.
Skill Claude CodeCodex
Designs realistic load and performance testing scenarios with k6, Locust, or JMeter for traffic simulations.
Skill Claude CodeCodex
Generates realistic, edge-case-rich mock fixtures and synthetic API payloads without leaking real PII.
Skill Claude CodeCodex
Analyzes test suites to identify surviving mutants, weak assertions, and false confidence in line coverage.
Skill Claude CodeCodex
Audits brittle UI and JSON snapshot tests to eliminate false alarm failures and replace them with resilient semantic assertions.
Skill Claude CodeCodex
Converts requirements into structured manual and automated test cases with clear steps and expected results. Use when you need a test plan/test case document, not code-level unit tests.
Skill Claude CodeCodex
Identifies which behaviors are meaningfully untested and risk-ranks the gaps, rather than reporting line-coverage percentage. Use when deciding where to add tests next.
Skill Claude CodeCodex
Creates meaningful unit, integration, and component tests based on implementation and requirements. Use when code needs test coverage and you want tests that verify behavior, not just tests that pad a coverage number.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: