LLM & Agents

This sop analyzes a codebase and generates comprehensive documentation including structured metadata files that describe the system architecture, components, interfaces, and workflows. It can create targeted documentation files like AGENTS.md (README for AI agents), README.md, CONTRIBUTING.md, or generate a complete documentation ecosystem. The documentation is organized to make it easy for AI assistants to understand the system and help with development tasks.

Rapid ideation skill adapted from obra/superpowers to kick off cortex sessions. Use when defining scope, aligning on goals, or exploring solution space before coding.

This skill should be used when users request help optimizing, improving, or refining their prompts or instructions for AI models. Use this skill when users provide vague, unclear, or poorly structured prompts and need assistance transforming them into clear, effective, and well-structured instructions that AI models can better understand and execute. This skill applies comprehensive prompt engineering best practices to enhance prompt quality, clarity, and effectiveness.

Production-grade mobile app development with Swift (iOS), Kotlin (Android), React Native, and WebView patterns, including UI/UX, navigation, state management, networking, local storage, push notifications, and App Store deployment.

Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes

This skill generates a comprehensive set of Frequently Asked Questions (FAQs) from the course description, course content, learning graphs, concept lists, MicroSims, and glossary terms to help students understand common questions and prepare content for chatbot integration. Use this skill after course description, learning graph, glossary, and at least 30% of chapter content exist.

Universal link validation using lychee for Claude Code sessions. Runs at session end to detect broken links and path policy violations.

Comprehensive guide for creating custom widget modules in Magento 2 that can be inserted into CMS pages and blocks. Covers module structure, widget configuration, templates, JavaScript, CSS, and form submission handling for non-Hyvä themes.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Formats git commit messages following Conventional Commits and respects user's attribution preferences from CLAUDE.md

Prompt engineering framework for Claude Code. Transforms vague requests into precise TCRO-structured prompts. Use when: crafting prompts for code generation, improving prompts not getting results, structuring multi-step workflows, debugging pattern drift. Triggers: optimize prompt, improve prompt, create prompt, prompt engineering, TCRO, prompt template, better prompt.

Structured plan-writing skill adapted from obra/superpowers. Produces actionable plans that map directly to cortex workflows and tasks.

Break LLM name defaults with external entropy. Use when character names cluster around statistical medians (Chen, Patel, Maya, Marcus), when cast has collision risks, or when fantasy cultures need phonologically consistent naming.

Validate and test secrets stored in Doppler. Add API tokens/credentials to Doppler, verify storage and retrieval, test authentication with target services. Use when user mentions "add to Doppler", "store secret", "validate token", or provides API tokens needing secure storage.

Creates event hooks for Claude Code automation with proper configuration, matchers, input/output handling, and security best practices. Covers all 9 hook types (PreToolUse, PostToolUse, UserPromptSubmit, Notification, Stop, SubagentStop, PreCompact, SessionStart, SessionEnd). Use when building automation, creating hooks, setting up event handlers, or when users mention hooks, automation, event handlers, or tool interception.

Prompt patterns for consistent UI generation. Covers precise design intent communication, component specification formats, and iterative refinement patterns for LLM-driven UI development.

Packages and distributes Claude Code plugins with proper structure, documentation, and release management. Creates distribution-ready packages, generates documentation, and sets up automated validation. Use when preparing Claude Code plugins for release, packaging plugins for marketplace distribution, creating plugin documentation, setting up plugin versioning, or publishing plugins to GitHub.

Agno AI agent framework. Use for building multi-agent systems, AgentOS runtime, MCP server integration, and agentic AI development.

Search and download images via Google Custom Search API with LLM-powered selection. This skill should be used when finding images for articles, presentations, research documents, or enriching Obsidian notes with relevant visuals. Supports simple queries, batch processing from JSON config, automatic config generation from terms, and full note enrichment with automatic image insertion below headings.

Replace with description of the skill and when Claude should use it.