Agent Skills Hub

substrate-vulnerability-scanner

Analyze Substrate/Polkadot runtimes and FRAME pallets for 7 critical vulnerabilities including arithmetic overflow, DoS, and improper origin checks.

code-review-specialist

A specialized code review agent that performs multi-dimensional analysis covering security vulnerabilities, performance optimization, code quality, and maintainability standards.

eval-harness

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

ghost-scan-secrets

AI-powered secrets and credentials scanner. Detects hardcoded API keys, passwords, and sensitive data in your codebase with contextual analysis to reduce false positives.

dev-workflow

Full-stack SDLC agent workflow managing the entire production lifecycle from intake and planning to automated testing, CI/CD, and infrastructure deployment using MCP tools.

semgrep

Run Semgrep static analysis scans on codebases using parallel subagents, multi-language detection, and Pro-enabled cross-file taint tracking.

indirect-injection-detection

Detects indirect prompt injection and goal hijacking in AI agents by evaluating how they process external content like RAG, documents, and web data.

multi-llm-advisor

Fetches expert perspectives from OpenAI Codex and Google Gemini for architecture, code reviews, and debugging, with transparent LLM synthesis.

phase-5-validator

Automates finalization validation for project workflows by enforcing git compliance, documentation standards, and deployment readiness.

review-and-qa

Perform comprehensive code reviews and generate QA test plans for Storyblok projects, ensuring quality, security, and adherence to best practices.

evaluating-code-models

Evaluate code generation models using BigCode Evaluation Harness. Benchmarks include HumanEval, MBPP, and MultiPL-E with pass@k metrics for multi-language coding models.

skill-vetter

Security-first vetting protocol for AI agent skills. Detects red flags like credential theft, obfuscated code, and unauthorized data exfiltration before installation.