llm-ai
0
moai-alfred-ask-user-questions
Guide Alfred sub-agents to actively invoke AskUserQuestion for ambiguous decisions.
kivo360
data-ai
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
0
decision-critic
Invoke IMMEDIATELY via python script to stress-test decisions and reasoning. Do NOT analyze first - the script orchestrates the critique workflow.
timmye
data-ai
llm-ai
0
chatkit-backend-adapter
Modify OpenAI ChatKit starter to use FastAPI backend instead of OpenAI API, including citation support and error handling.
nadeemsangrasi
data-ai
llm-ai
0
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Kilo-Org
data-ai
llm-ai
0
fvtt-chat-messages
This skill should be used when creating chat messages, sending roll results to chat, configuring speakers, implementing whispers and roll modes, or hooking into chat message rendering.
ImproperSubset
data-ai
llm-ai
0
development-servers
Manage Vite, FastAPI, and Ollama development servers for Gentle Disagree. Use when starting the application, after code changes, when servers crash, verifying servers are running, or troubleshooting errors. (project)
mccarthysean
data-ai
llm-ai
0
project-init
Use when a non-developer user wants to create a new automation tool project. Sets up Python environment, project structure, and CLAUDE.md context file. Guides through environment setup → context gathering → structure initialization in user's preferred language.
mnthe
data-ai
llm-ai
0
developing-ai-prompts
Write effective prompts and instructions for AI models and agents. Covers universal techniques plus model-specific guidance for Claude, GPT, and Gemini. Use when writing, reviewing, or adapting prompts for any AI model. Invoke PROACTIVELY when creating system prompts, agent instructions, or optimizing model performance.
mikekelly
data-ai
llm-aimarketplace
0
phase-1-init
Init phase skill. Creates plan directory, request.md, config, and status. Complete initialization in a single agent call.
cuioss
data-ai
llm-ai
0
compound-learning
Self-improving holon implementing Plan→Execute→Assess→Compound workflow loops with explicit knowledge crystallization. Generalizes compound engineering beyond coding to any domain where work produces learnable signals: writing, research, learning, problem-solving, design. Use when: (1) task quality matters and can improve over time, (2) patterns emerge from repeated work, (3) institutional knowledge should accumulate, (4) future tasks should benefit from past learnings, (5) "compound", "learn from", "improve process", "capture learnings", or multi-step workflows with review cycles. Orchestrates parallel research agents, multi-lens assessment, and structured knowledge codification into searchable documentation with YAML frontmatter. Implements λο.τ → λ(ο,Κ).τ where Κ is accumulated knowledge that compounds interest-like over time.
Zpankz
data-ai
llm-ai
0
consulting-peer-llms
Use when user explicitly requests feedback from other LLM tools (Gemini, Codex) on current work - executes peer reviews in parallel and synthesizes responses into actionable insights
ether-moon
data-ai
llm-ai
0
vscode-integration
Enables Mini-Agent to integrate directly with VS Code Chat API for seamless AI assistance
Zazzles2908
data-ai
llm-ai
0
sandbox-test
Run an isolated Claude Code instance for testing. Use when you need a fresh environment without global CLAUDE.md or parent project settings. Trigger for: sandbox, isolated test, fresh instance, clean environment, test without global config.
teren-papercutlabs
data-ai
llm-ai
0
claude-code-expert
Expert Claude Code engineer with deep knowledge of skills authoring, Agent SDK (TypeScript/Python), Claude API, prompt engineering, MCP servers, hooks, slash commands, and tool use. Use when creating skills, building agents, writing hooks, configuring MCP servers, or implementing Claude API integrations.
ronaldeddings
data-ai
llm-ai
0
gemini-vision
Guide for implementing Google Gemini API image understanding - analyze images with captioning, classification, visual QA, object detection, segmentation, and multi-image comparison. Use when analyzing images, answering visual questions, detecting objects, or processing documents with vision.
levanminhduc
data-ai
llm-ai
0
ralph-wizard
Use when starting a Ralph loop and you want guided prompt creation. Asks questions to gather specs, requirements, tech stack, testing needs, and completion criteria before auto-starting the loop.
ricardo-lobo
data-ai
llm-ai
0
voice-processing
Voice cloning workflows, voice library management, audio format conversion, and voice settings. Use when cloning voices, managing voice libraries, processing audio for voice creation, configuring voice settings, or when user mentions voice cloning, instant cloning, professional cloning, voice library, audio processing, voice settings, or ElevenLabs voices.
vanman2024
data-ai
llm-ai
0
agent-communication
Principles for writing token-efficient, action-oriented instructions to agents. Use when creating agent prompts, rules, documentation, or improving agent communication.
juljus
data-ai
llm-ai
0
ai-engineer
LLM application and RAG system specialist. Use PROACTIVELY for LLM integrations, RAG pipelines, vector search, agent orchestration, and AI-powered features.
kriscard
data-ai
llm-ai
0
trait-learning
Use when working with trait extraction, place enrichment, or the learning loop. Load for understanding how the system learns from gameplay, how traits are extracted from Nominatim + player sessions, async queue processing, and LLM prompt configuration. Covers update_place_traits, pgmq, and edge function flow.
discountedcookie
data-ai
llm-ai
0
codex-resume
Use to resume a previous Codex conversation. Triggers on "continue codex", "resume codex", "pick up where codex left off", "continue the codex session".
kanlanc
data-ai