Agent Skills Hub

pentest-osint-recon

Automated OSINT reconnaissance agent for mapping external attack surfaces, identifying assets, and uncovering security vulnerabilities.

semgrep-rule-creator

Create, test, and validate custom Semgrep rules for security vulnerabilities and code pattern detection.

eval-harness

Official evaluation framework for AI agent sessions, implementing Evaluation-Driven Development (EDD) principles to ensure reliability.

claude-rag-skills

A suite of professional tools for auditing, evaluating, chunking, and scaffolding production-ready RAG pipelines within Claude Code.

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.

read-only-gh-pr-review

Review backend pull requests with security enforcement and GitHub CLI integration in a strict read-only environment.

report-writing

A professional bug bounty reporting agent that enforces impact-first writing, CVSS 3.1 scoring, and pre-submit validation for platforms like HackerOne, Bugcrowd, and Intigriti.

start

Initiates automated reverse engineering by discovering codebase architecture, layers, and technology stacks to facilitate system modernization or documentation.

web-design-guidelines

Audit UI code for Web Interface Guidelines compliance. Automatically checks accessibility, design standards, and UX best practices.

write-docs

Automate the creation and maintenance of BrowserOS feature documentation using a structured, codebase-aware workflow to generate concise Mintlify MDX pages.

roier-seo

AI-powered Technical SEO auditor that runs Lighthouse/PageSpeed tests and automatically applies code-level fixes for performance, accessibility, and structured data.

vibesafe

Manage Vibesafe units to scan, generate, test, and verify AI-written code with cryptographically-secure hash-locked checkpoints.