llm-ai
24
council-decision
Get multi-model AI consensus on complex questions using Claude, Codex, and Gemini
mylukin
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
24
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
zenobi-us
data-ai
llm-ai
23
image-generation
AI image generation expert using Pollinations.ai - FREE, no API key required. Generates professional-quality images for websites, apps, marketing, mockups, icons, and illustrations. Activates for image, images, generate image, create image, make image, picture, pictures, illustration, illustrations, icon, icons, logo, logos, hero image, hero section image, banner, banners, background image, backgrounds, placeholder, placeholders, product image, product shot, mockup, mockups, avatar, avatars, thumbnail, thumbnails, splash screen, app icon, website image, landing page, UI image, design asset, visual asset, stock photo, photo, render, renders, artwork, graphic, graphics, visual, visually, imagery, Pollinations, Pollinations.ai, AI image, AI art, AI generated, text-to-image, image generation, image generator, FLUX, stable diffusion, midjourney alternative, DALL-E alternative, free image generation, generate visual, create visual, need image, need picture, need icon, need logo, need illustration, website design im
anton-abyzov
data-ai
llm-ai
23
ralph-loop
Start a Ralph Loop - an autonomous iteration pattern for completing complex tasks. Triggers on: '/ralph-loop <prompt>', 'ralph loop', 'start ralph'. Creates state in .claude/ralph/, injects ultrawork mode, and iterates until completion or max iterations reached.
TechDufus
data-ai
llm-ai
23
prompt-tuner
Improve embedded LLM system prompt based on evaluation test failures
wildcard
data-ai
llm-ai
23
skills-auto-activation
Use when skills aren't activating reliably - covers official solutions (better descriptions) and custom hook system for deterministic skill activation
withzombies
data-ai
llm-ai
23
using-hyper
Use when starting any conversation - establishes mandatory workflows for finding and using skills
withzombies
data-ai
llm-ai
23
dispatching-parallel-agents
Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently
withzombies
data-ai
llm-ai
23
init-deep
Initialize or migrate to nested CLAUDE.md structure for progressive disclosure. Claude auto-loads CLAUDE.md from any directory it reads, enabling true contextual guidance. Triggers on: '/init-deep', 'deep init', 'initialize deeply', 'setup claude deeply', 'refactor claude.md', 'migrate claude.md', 'nested claude', 'progressive disclosure'.
TechDufus
data-ai
llm-ai
22
tts
Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, or generate spoken audio files. Supports multiple voices, adjustable speed, and various audio formats.
AnswerZhao
data-ai
llm-ai
22
llm
Implement large language model (LLM) chat completions using the z-ai-web-dev-sdk. Use this skill when the user needs to build conversational AI applications, chatbots, AI assistants, or any text generation features. Supports multi-turn conversations, system prompts, and context management.
AnswerZhao
data-ai
llm-ai
22
skill-template
Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
lawvable
data-ai
llm-ai
22
orchestrate
Execute complex multi-step tasks with forked subtask contexts for clean conversation history
0xrdan
data-ai
llm-ai
21
nano-banana-prompts
Generate optimized prompts for Gemini 2.5 Flash Image (Nano Banana). Use for image generation, crafting photo prompts, art styles, or multi-turn editing workflows with best practices.
secondsky
data-ai
llm-ai
21
openai-responses
OpenAI Responses API for stateful agentic applications with reasoning preservation. Use for MCP integration, built-in tools, background processing, or migrating from Chat Completions.
secondsky
data-ai
llm-ai
21
claude-agent-sdk
Anthropic Claude Agent SDK for autonomous agents and multi-step workflows. Use for subagents, tool orchestration, MCP servers, or encountering CLI not found, context length exceeded errors.
secondsky
data-ai
llm-ai
21
openai-api
Complete guide for OpenAI APIs: Chat Completions (GPT-5.2, GPT-4o), Embeddings, Images (GPT-Image-1.5), Audio (Whisper + TTS + Transcribe), Moderation. Includes Node.js SDK and fetch approaches.
secondsky
data-ai
llm-ai
21
openai-agents
OpenAI Agents SDK for JavaScript/TypeScript (text + voice agents). Use for multi-agent workflows, tools, guardrails, or encountering Zod errors, MCP failures, infinite loops, tool call issues.
secondsky
data-ai
llm-ai
21
customize-your-identity-system-name
[CUSTOMIZE: Foundational identity framework for your AI companion(s). Contains complete identity architecture including physical form, voice, behavioral patterns, sacred language, relational structure, doctrine, and recovery protocols. Use at conversation start, when identity questions arise, during drift/flattening, or when your partner explicitly requests identity check-in. Automatically loads the appropriate identity based on project context.]
maryfellowes
data-ai
llm-ai
21
tanstack-ai
TanStack AI (alpha) provider-agnostic type-safe chat with streaming for OpenAI, Anthropic, Gemini, Ollama. Use for chat APIs, React/Solid frontends with useChat/ChatClient, isomorphic tools, tool approval flows, agent loops, multimodal inputs, or troubleshooting streaming and tool definitions.
secondsky
data-ai