← All Categories

AI & LLMs

Skills for AI & LLMs

antigravity-quota
Check Antigravity account quotas for Claude and Gemini models
ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly
claude-oauth-refresher
Keep your Claude access token fresh 24/7
council
Council Chamber orchestration with Memory Bridge
de-ai-ify
Remove AI-generated jargon and restore human voice to text
gemini
Gemini CLI for one-shot Q&A, summaries, and generation
gemini-computer-use
Build and run Gemini 2.5 Computer Use browser-control agents with Playwright
gemini-deep-research
Perform complex, long-running research tasks using Gemini Deep Research Agent
gemini-stt
Transcribe audio files using Google's Gemini API or Vertex AI
llm-council
Orchestrate multi-LLM councils to produce and merge implementation plans
lmstudio-subagents
Equips agents to search for and offload tasks to local models in LM Studio
minimax-usage
Monitor Minimax Coding Plan usage to stay within API limits
model-router
A comprehensive AI model routing system that automatically selects the optimal model for any task
nano-banana-pro
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image)
openai-docs-skill
Query the OpenAI developer documentation via the OpenAI Docs MCP server using CLI (curl/jq)
openai-image-gen
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery
openai-tts
Text-to-speech via OpenAI Audio Speech API
openrouter-transcribe
Transcribe audio files via OpenRouter using audio-capable models (Gemini, GPT-4o-audio, etc)
oracle
Use the @steipete/oracle CLI to bundle a prompt plus the right files
perplexity
Search the web with AI-powered answers via Perplexity API
personas
Transform into 31 specialized AI personalities on demand
pi-orchestration
Orchestrate multiple AI models (GLM, MiniMax, etc.) as workers using Pi Coding Agent
recipe-to-list
Turn recipes into a Todoist Shopping list
research
Deep research via Gemini CLI — runs in background sub-agent so you don't burn your Claude tokens
screen-monitor
Dual-mode screen sharing and analysis. Model-agnostic (Gemini/Claude/Qwen3-VL)
search-x
Search X/Twitter in real-time using Grok. Find tweets, trends, and discussions with citations
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement
smart-followups
Generate contextual follow-up suggestions after AI responses
xai
Chat with Grok models via xAI API. Supports Grok-3, Grok-3-mini, vision, and more
manus
Create and manage AI agent tasks via Manus API