Skill UI

A comprehensive, multi-phase security audit tool designed to evaluate AI agent skills before deployment. It detects critical vulnerabilities, including prompt injection, malicious code, excessive permissions, secret exposure, and supply chain risks, ensuring the integrity and safety of your agent environment.

An enterprise-grade agent designed to manage the entire lifecycle of skills within an ecosystem. It handles installation, deep validation (including 10 security checks), registration, and post-installation verification. Features include automatic repair, rollback, dry-run simulation, and a comprehensive status dashboard, ensuring maximum redundancy and system integrity.

This comprehensive index covers 37 advanced engineering skills designed for complex system architecture, platform operations, and reliability. Skills include agent design, RAG implementation, CI/CD, observability, database modeling, and security auditing, supporting the entire development lifecycle for powerful enterprise applications.

Validates SKILL.md files against the agentskills specification and Anthropic best practices, catching structure, semantic, naming, and quality issues in a single read-only pass before publishing or debugging skills.

This skill systematically audits a given project by analyzing its historical memory, rollout summaries, and local skill definitions. It identifies repeated complex workflows, recurring operational patterns, or areas where existing skills are stale. The audit process guides the user to recommend the highest-value skills to either add (if a new pattern emerges) or update (if current skills are outdated or incomplete), ensuring the AI agent operates with the most accurate and context-specific knowledge base for optimal project execution.

Generates a precise, evidence-based installation plan for a project's component catalog (ECC). Instead of loading a full, noisy bundle, this skill analyzes the repository's actual code structure, dependencies, and CI/CD evidence to classify skills, rules, and commands into 'DAILY' (essential) and 'LIBRARY' (referenceable) buckets. It ensures only necessary components are active, optimizing the development environment.

Helps users discover and install open agent skills by translating requests like “how do I do X” into CLI searches, reviewing sources, and guiding safe installs with security warnings and confirmations.

Guides agents through researching Microsoft technologies via Learn MCP docs, then scaffolds hybrid skills that store essential knowledge locally while enabling dynamic lookups for depth.

This meta-skill guides engineers through the entire software development lifecycle, from initial idea refinement and specification to implementation, testing, code review, and deployment. It emphasizes critical best practices like surfacing assumptions, managing ambiguity, enforcing simplicity, and maintaining scope discipline to prevent common failure modes.

This comprehensive guide provides a detailed framework for authoring effective and structured SKILL.md files for AI coding agents. It covers best practices for structuring content, including frontmatter fields, defining natural language triggers, establishing core principles, and incorporating advanced elements like decision trees and verification checklists, ensuring agents receive clear, actionable, and consistent technical guidance.

This is the foundational plumbing layer connecting AI agents to the Power Automate platform via FlowStudio MCP. It provides essential capabilities such as secure authentication setup, robust tool discovery (`list_skills`, `tool_search`), and handling complex, oversized API responses. It serves as the prerequisite layer for specialized workflow skills (e.g., building, debugging, monitoring).

Guides teams through creating a complete GitHub Copilot configuration by outlining required instructions, reusable skills, and agent/workflow files tailored to the chosen tech stack and workflow preferences.