LLM & Agents

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

Generate retro arcade style infographic prompts for documentation pages

Write focused tests for core user flows and critical paths with clear test names, behavior-focused assertions, mocked external dependencies, and fast execution, deferring edge case testing until explicitly required. Use this skill when creating or modifying test files, writing unit tests, integration tests, or test cases for any feature. Apply when writing test files (test/, __tests__/, spec/, .test.js, .spec.ts, test_*.py), implementing tests for core user workflows, testing critical business logic, mocking external dependencies (databases, APIs, file systems), writing descriptive test names, creating fast-running unit tests, or adding tests at logical completion points of feature development. Use for any task involving test creation, test coverage, test strategy, or test-driven development.

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with any AI model (OpenRouter, Gemini, OpenAI, local models). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, Gemini, OpenAI, Ollama, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

Scans codebases to generate architecture documentation (ARCHITECTURE.md). Use when joining an existing project, understanding codebase structure, exploring project architecture, or preparing for agent-foreman init. Triggers on 'analyze project', 'understand codebase', 'explore architecture', 'scan project structure', 'survey project'.

Creates AI agent task management structure with feature backlog (ai/tasks/), TDD enforcement, and progress tracking. Use when setting up agent-foreman, initializing feature-driven development, creating task backlog, or enabling TDD mode. Triggers on 'init harness', 'setup feature tracking', 'create feature backlog', 'enable strict TDD', 'initialize agent-foreman'.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create section outlines with key points using research-lookup, (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process: (1) create section outlines with key points using research-lookup, (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.

Test llm-mux IR translator - cross-format API translation

Generate TestBox BDD test specs for Wheels models, controllers, and integration tests. Use when creating tests for models (validations, associations), controllers (actions, filters), or integration workflows. Ensures comprehensive test coverage with proper setup/teardown and Wheels testing conventions.

Build llm-mux binary and run locally for development/debugging

Generate TestBox BDD test specs for Wheels models, controllers, and integration tests. Use when creating tests for models (validations, associations), controllers (actions, filters), or integration workflows. Ensures comprehensive test coverage with proper setup/teardown and Wheels testing conventions.

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

Implements UI components from scratch based on design references (Figma, screenshots, mockups) with intelligent validation and adaptive agent switching. Use when user provides a design and wants pixel-perfect UI implementation with design fidelity validation. Triggers automatically when user mentions Figma links, design screenshots, or wants to implement UI from designs.

⚡ PRIMARY TOOL for: 'what's tested', 'find test coverage', 'audit test quality', 'missing tests', 'edge cases', 'test patterns'. Uses claudemem v0.3.0 AST with callers analysis for test discovery. GREP/FIND/GLOB ARE FORBIDDEN.

Plugin release process for MAG Claude Plugins marketplace. Covers version bumping, marketplace.json updates, git tagging, and common mistakes. Use when releasing new plugin versions or troubleshooting update issues.

Reference guide for using PROXY_MODE with external AI models. Use when running multi-model reviews, understanding which agents support PROXY_MODE, or debugging external model integration issues.

XML tag structure patterns for Claude Code agents and commands. Use when designing or implementing agents to ensure proper XML structure following Anthropic best practices.

Integration guide for using detective skills across plugins. Maps agent roles from frontend, bun, and other plugins to appropriate detective skills. Developer agents should use developer-detective, architect agents should use architect-detective, etc.