LLM & Agents

Unit testing patterns and best practices. Use when writing isolated unit tests, implementing AAA pattern, designing test isolation, or setting coverage targets for business logic.

Use when building real-time features with SSE, WebSockets, or streaming APIs. Covers backpressure handling, reconnection strategies, and LLM token streaming patterns.

Zustand state management for React and vanilla JavaScript. Use when creating stores, using selectors, persisting state to localStorage, integrating devtools, or managing global state without Redux complexity. Triggers on zustand, create(), createStore, useStore, persist, devtools, immer middleware.

Comprehensive testing strategies and coverage standards. Use when testing strategy guidance is required.

Multi-agent coordination and synthesis patterns. Use when orchestrating multiple specialized agents, implementing fan-out/fan-in workflows, or synthesizing outputs from parallel agents.

Generate and edit images using AI providers (OpenAI DALL-E, Stability AI, BFL FLUX, Ideogram, FAL, Gemini, Replicate, Clipdrop). Use when user asks to create images, generate artwork, make logos, create visual content, edit photos, remove backgrounds, or modify existing images. Triggers on requests involving pictures, illustrations, graphics, product shots, marketing visuals, or any image creation/editing task.

Use when creating or developing anything, before writing code or implementation plans - refines rough ideas into fully-formed designs through structured Socratic questioning, alternative exploration, and incremental validation. Optimized for git worktree workflows and Claude CLI agent patterns.

Manage the llm-do task tracker stored under tasks/ (backlog, active, completed, recurring) including creating new tasks, updating current state, moving tasks between stages, and applying the standard templates when planning or resuming work.

Provides conventional commits guidance and auto-generates commit messages from git changes. Integrates with /ccpm:commit for automated git commits linked to Linear issues. Auto-activates when users ask about committing, creating git commits, or discussing commit message formats.

Master Orchestrator for autonomous multi-agent coordination. Use when tasks require multiple technology experts, complex workflows (TDD pattern addition, security audits), intelligent routing, or explicit orchestration requests. Coordinates 17 technology experts with real-time progress reporting.

Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.

Integrates SAP Cloud SDK for AI into JavaScript/TypeScript and Java applications. Use when building applications with SAP AI Core, Generative AI Hub, or Orchestration Service. Covers chat completion, embedding, streaming, function calling, content filtering, data masking, document grounding, prompt registry, and LangChain/Spring AI integration. Supports OpenAI GPT-4o, Claude, Gemini, Amazon Nova, and other foundation models via SAP BTP.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Keep project documentation current and optimized for AI agents. Use when user asks to "update docs", "sync documentation", "update CLAUDE.md", "update README", "check documentation freshness", "document recent changes", or "optimize docs for AI".

Use when creating or editing commands, orchestrator prompts, or workflow documentation before deployment - applies RED-GREEN-REFACTOR to test instruction clarity by finding real execution failures, creating test scenarios, and verifying fixes with subagents

Generate and edit images using AI providers (OpenAI DALL-E, Stability AI, BFL FLUX, Ideogram, FAL, Gemini, Replicate, Clipdrop). Use when user asks to create images, generate artwork, make logos, create visual content, edit photos, remove backgrounds, or modify existing images. Triggers on requests involving pictures, illustrations, graphics, product shots, marketing visuals, or any image creation/editing task.

Optimize MATLAB code for better performance through vectorization, memory management, and profiling. Use when user requests optimization, mentions slow code, performance issues, speed improvements, or asks to make code faster or more efficient.

Create comprehensive Claude Code plugins with proper structure, commands, agents, hooks, and marketplace configuration. Use when the user wants to build a new Claude Code plugin or asks how to create/structure a plugin.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.

Automated test fixture generation for Vigil Guard's 8-file test suite. Use for TDD workflow, malicious/benign payload creation, 3-branch detection testing, bypass scenario testing, and maintaining test coverage.