Integrate Firebase AI Logic (Gemini in Firebase) for intelligent app features. Use when adding AI capabilities to Firebase apps, implementing generative AI features, or setting up Firebase AI SDK. Handles Firebase AI SDK setup, prompt engineering, and AI-powered features.
Spawn 5 parallel Explore agents to discover project constraints. TRIGGERS - constraint scan, degrees of freedom, /ralph:start Step 1.4.5, project memory analysis.
LLM working files and session context management. Use at the start of sessions to restore context, and during work to maintain state across conversations.
Azure OpenAI Service 2025 models including GPT-5, GPT-4.1, reasoning models, and Azure AI Foundry integration
Choose between Shell and Python for generated automation code based on task traits. Use when automation language selection guidance is required.
GitHub AI-powered security and automation features for 2025
Meta-skill for writing and maintaining Claude Code skills. Use when creating new skills, updating existing skills, or reviewing skill quality. Enforces progressive disclosure and size limits.
Generate ROS 2 Python launch files and multi-node system configurations for educational content. This skill should be used when creating lessons that teach launch file syntax, writing exercises involving multi-node startup, parameter configuration, or generating worked examples for robot system deployment.
Self-improving skill library for programming workflows. Mines transcripts and patterns to propose and scaffold new skills. Use when you hear: - "turn this workflow into a skill" - "make a skill for our PR review process" - "generate a new skill" - "automate this repeated process" - "create a skill for X" - "what skills could I create?" - "propose some skills"
Semantic search over skill libraries using ColBERT embeddings. Use when: - "find a skill for..." or "search for skills that..." - "what skill handles..." or "which skill can..." - "index my skills" or "rebuild the skill index" - "show me relevant skills for this task"
Vercel AI SDK plugin development patterns including tool configuration, schema validation, API key handling, and response formatting. Use when developing or contributing to @youdotcom-oss/ai-sdk-plugin package.
Self-referential iteration mode for completing complex tasks autonomously. Use when a task requires multiple attempts, trial-and-error, or persistent effort until success. Based on the Ralph Wiggum methodology. Trigger words: iterate, keep trying, until it works, autonomous, persist, retry.
Check if a specific action is possible and what might be blocking it. Use when asking if you can do something, checking permissions, verifying a capability exists, or troubleshooting why something isn't working. Trigger words: can I, capability, able to, permission, possible, how do I.
Analyze agent-user interaction transcripts to identify context network maintenance needs and guidance improvements. Use after significant agent interactions or to improve context networks.
Manage vim-ai plugin configuration files including .vimrc settings, custom roles, API keys, and model configurations. Use when user requests help with vim-ai setup, modifying vim-ai behavior, adding custom roles, changing AI models, updating prompts, or troubleshooting vim-ai issues.
Create Claude Code subagent configurations for .claude/agents/. Defines specialized agents with isolated contexts. Use when creating dedicated agents for code review, testing, or domain-specific tasks.
Convert Cursor custom commands (.cursor/commands/*.md) to Claude Code skills (.claude/skills/*/SKILL.md). Use when the user says "import command to skill", "convert command to skill", or "migrate cursor command".
Autonomous AI coding loop for unattended development - lets Claude work continuously on tasks while you sleep, with mandatory sandbox enforcement for safety
