SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.
Tags

code-audit
Perform professional code security audits across 9 languages with configurable quick/standard/deep modes and Docker-backed verification.

specialist-agent
Performs adversarial stress-testing of code to find edge cases, race conditions, security holes, and logical flaws before deployment.

Anthropic Cybersecurity Skills
Use OWASP Threat Dragon to create data-flow diagrams, apply STRIDE/LINDDUN threat classifications, and generate threat-model reports to guide secure design revi

skilllearnbench
Run Trivy in offline mode to scan dependency files (package-lock.json, etc.) for HIGH/CRITICAL vulnerabilities and produce machine-readable JSON results.

skillsemgrep
Run Semgrep-based security scans to detect vulnerabilities, secrets, and OWASP Top 10 issues, and produce a categorized report with remediation suggestions.

claude-skills-generator
Comprehensive administration of Harbor container registries, including vulnerability scanning, image signing, and multi-region replication.

vibe-security-skill
Audits AI-generated codebases for critical security flaws like exposed keys, broken RLS, and insecure payment flows.

codex_skill
Perform security-focused code reviews aligned to OWASP Top 10 and CWE patterns; produces grouped findings, risk summary, and remediation guidance.

prodsec-skills
Analyzes, filters, and aggregates SARIF files from static analysis tools like CodeQL and Semgrep.

prodsec-skills
Identifies error-prone APIs and 'footgun' designs that lead developers toward insecure configurations and implementation mistakes.

claude-skill-registry
Audit codebases against SOC2, GDPR, HIPAA, and PCI-DSS frameworks with automated reports and remediation guidance.