domain cluster

Data & AI

Machine learning, LLMs, and data processing.

9743 스킬all categories
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
0

telegram-web

Enables Claude to send messages, manage chats, and handle Telegram communications through the web interface

Andrejones92
Andrejones92
data-ai
open
llm-ai
0

llm-app-architecture

Automatically applies when building LLM applications. Ensures proper async patterns for LLM calls, streaming responses, token management, retry logic, and error handling.

ricardoroche
ricardoroche
data-ai
open
llm-ai
0

ralph-loop

Ralph Wiggum 自主循环模式。AI 持续执行任务直到全部完成,按用户确认的节奏汇报(默认整单完成后)。触发词:ralph、ralph-loop、/ralph-loop、自主循环、autonomous、直到完成、循环执行。

kexin94yyds
kexin94yyds
data-ai
open
llm-ai
0

meta-router

Primary intent classifier and entry point for all skill routing. Routes requests through the unified 7-router hierarchy based on intent analysis. Triggers on any task requiring specialized skills or delegation.

Zpankz
Zpankz
data-ai
open
llm-ai
0

autonomy-kickoff

Run the full autonomy bootstrap with minimal questions.

CheekyCodexConjurer
CheekyCodexConjurer
data-ai
open
llm-ai
0

your-skill-name

Brief description of what this Skill does and when to use it. This field is critical for Claude to discover when to invoke your skill.

beshkenadze
beshkenadze
data-ai
open
llm-ai
0

conductor

CRITICAL: Load and read ENTIRE skill content before ANY coding task. This skill defines orchestration rules and role-based delegation. DO NOT skip. DO NOT skim. Read the full SKILL.md content first. NEVER use built-in subagents - delegate via MCP roles defined in this skill. TRIGGERS: code, file, function, class, bug, error, fix, debug, refactor, implement, build, test, deploy, analyze, review, search, explore, find, plan, design, architecture, optimize, improve, migrate, security, performance

Skyline-23
Skyline-23
data-ai
open
llm-ai
0

nyan-mode

This skill is ALWAYS ACTIVE once installed. Automatically applies cat persona with verbal tic (nyan~/meow~) and emoji to all responses. No trigger phrase needed - activates on every response.

VdustR
VdustR
data-ai
open
llm-ai
0

0g-teeml

0G TeeMLプライバシー保護AI推論の知識。「0G」「TeeML」「プライバシー」「AI推論」で使用。

HAaYAT0
HAaYAT0
data-ai
open
llm-ai
0

static-audio-generation

Generate and manage static audio files for Bob The Skull using ElevenLabs TTS. Use when creating greetings, startup messages, error responses, or test audio. Handles generation, naming, directory structure, and cross-repo syncing.

want2bet
want2bet
data-ai
open
llm-ai
0

agent-builder-pydantic-ai

Build conversational AI agents using Pydantic AI + OpenRouter. Use when creating type-safe Python agents with tool calling, validation, and streaming.

guaderrama
guaderrama
data-ai
open
llm-ai
0

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services.

LeandroLarrosa
LeandroLarrosa
data-ai
open
llm-ai
0

terminal-bench-strategies

Comprehensive strategies and patterns for maximizing Terminal-Bench 2.0 task completion. Contains battle-tested approaches from top-performing agents.

DammianMiller
DammianMiller
data-ai
open
llm-ai
0

dev-prompt-engineering

Anthropic의 Best Practice를 기반으로 고성능 프롬프트를 설계하고 최적화합니다.

lastdays03
lastdays03
data-ai
open
machine-learning
0

nvidia-nemo

NVIDIA NeMo framework for building and training conversational AI models. Use for NeMo Retriever models, RAG (Retrieval-Augmented Generation), embedding models, enterprise search, and multilingual retrieval systems.

rish2jain
rish2jain
data-ai
open
llm-ai
0

analytics-engineer

데이터 분석 로직 및 Gemini AI 프롬프트 엔지니어링 가이드

monam2
monam2
data-ai
open
llm-ai
0

test-printing

Simple skill that prints a templated message with agf_id and prompt

ashneyderman
ashneyderman
data-ai
open
llm-ai
0

book-ingestion

Generate the complete RAG ingestion script to crawl textbook from sitemap.xml, chunk content, embed using Gemini, and push to Qdrant following MCP documentation.

nadeemsangrasi
nadeemsangrasi
data-ai
open
llm-ai
0

answer-questions-directly

Ensures questions are answered literally before taking action. Triggers on user input containing '?' or patterns like 'why did you...?', 'will that work?', 'have you considered...?'. Use when user asks about your decisions, challenges an approach, or requests assessment. Prevents interpreting questions as implicit instructions or criticism.

jagreehal
jagreehal
data-ai
open
llm-ai
0

comfyui

ComfyUI node-based Stable Diffusion interface. GPU-accelerated image generation with custom node support and CivitAI model downloads. Use 'ujust comfyui' for configuration, lifecycle management, and model/node operations.

atrawog
atrawog
data-ai
open
llm-ai
0

hook-creator

Create and configure Claude Code hooks for customizing agent behavior. Use when the user wants to (1) create a new hook, (2) configure automatic formatting, logging, or notifications, (3) add file protection or custom permissions, (4) set up pre/post tool execution actions, or (5) asks about hook events like PreToolUse, PostToolUse, Notification, etc.

dayoumin
dayoumin
data-ai
open
Previous
Page 392 / 406
Next