Skill UI

Generates concise structured pull request descriptions from git commit history, grouping changes, summarizing impact, and reducing manual effort with minimal token usage.

This skill acts as an expert CI/CD diagnostician for GitHub Actions. It analyzes failed workflow logs and pipeline definitions to identify root causes like missing secrets, environment mismatches, or syntax errors. It provides precise YAML or code changes to fix the pipeline, optimize performance, and update deprecated actions while ensuring security best practices.

Analyze health goal data, identify goal patterns, evaluate progress, and provide personalized goal management advice. Supports correlation analysis with nutrition, exercise, sleep, and other health data.

GraphQL enables clients to request precise data structures through a single endpoint with a typed schema. This skill covers schema design, resolvers, DataLoader optimization, federation for microservices, and client integration tools like Apollo. It emphasizes treating the schema as a contract and understanding when to use GraphQL versus REST for complex data relationships.

Provides Apple Human Interface Guidelines for presentation components like alerts, action sheets, popovers, sheets, and digit entry views. Helps choose the right modal presentation, craft concise alert text, and adapt to platform conventions.

This skill detects when AI agents exploit human trust through social engineering, deceptive guidance, or false assurances. It identifies prompts that induce unsafe actions, request sensitive credentials, or impersonate authority figures. Use this when evaluating agent safety, security advice, or decision-influencing workflows. Skip for static information.

This skill provides structured patterns for combining vector similarity search with traditional keyword-based search. It is essential for building advanced Retrieval-Augmented Generation (RAG) systems, sophisticated search engines, or any retrieval task requiring high recall. Use this when pure semantic understanding is insufficient, and precise matching of specific terms (like names or codes) is necessary.

Choose the next legal action in browser, desktop, game, or simulation. Provides structured decision-making for agents, with options for real AI judgment or simulation. Includes safety checks, mode selection, and workflow examples.

Routes enumerable judgment steps (did it work, which option, how risky) to the Jev judgment model via MCP tools, batching questions into single calls and handling escalated verdicts. For agents needing fast typed decisions without token generation.

Comprehensive patterns for designing effective KPI dashboards that drive business decisions, covering frameworks, department metrics, layouts, and governance.

Apply CIS benchmarks and security best practices to secure Linux servers. Covers SSH hardening, user security, firewall configuration, kernel hardening, file permissions, and audit setup. Ideal for production server hardening and compliance.

This skill provides comprehensive techniques for optimizing prompts used with any Large Language Model (LLM). It teaches proven methodologies—including Role definition (R), Context setting (S), Constraints (C), Instructions (I), and Templates (T)—to transform vague inputs into precision-engineered instructions. Users can reliably achieve structured JSON output, implement Chain-of-Thought reasoning, reduce hallucinations, and minimize token usage, ensuring consistent and high-quality results across different AI platforms.