llm-ai
3
episode-start
Start a new learning episode in the self-learning memory system with proper context. Use this skill when beginning a new task that should be tracked for learning from execution patterns.
d-o-hub
data-ai
sorting
์คํ
current ordering strategy
query
all entries
refine the visible subset
llm-ai
3
init-project
Initialize projects with agentic coding structure. Use when setting up a new project, adding AI agent support to existing project, or when user says "init", "initialize", "setup project", or "scaffold". Creates AGENTS folder, documentation templates, and _NOTES scratch space.
product-on-purpose
data-ai
llm-ai
3
claude-agent-sdk
Build production AI agents using the Claude Agent SDK (TypeScript/Python). Use this skill when the user asks about: (1) Building AI agents with Claude, (2) Using the @anthropic-ai/claude-agent-sdk or claude-agent-sdk packages, (3) Implementing agent features like tools, hooks, subagents, MCP integration, or sessions, (4) Migrating from Claude Code SDK to Agent SDK, (5) Configuring permissions, budgets, or custom tool access.
jeongsk
data-ai
llm-ai
3
session-start-hook
Configure SessionStart hooks for Claude Code on the web. Use when setting up a repository to run on cloud infrastructure, installing dependencies, or initializing environments for remote Claude Code sessions.
cameronsjo
data-ai
llm-ai
3
agentuity-cli-cloud-vector-search
Search for vectors using semantic similarity. Requires authentication. Use for Agentuity cloud platform operations
agentuity
data-ai
llm-ai
3
vllm-deployment
Deploy vLLM for high-performance LLM inference. Covers Docker CPU/GPU deployments and cloud VM provisioning with OpenAI-compatible API endpoints.
stakpak
data-ai
llm-ai
3
session-logger
Saves conversation history to session log files. Use when user says "ไฟๅญๅฏน่ฏ", "ไฟๅญๅฏน่ฏไฟกๆฏ", "่ฎฐๅฝไผ่ฏ", "save session", or "save conversation". Automatically creates timestamped session log in sessions/ directory.
Charon-Fan
data-ai
llm-ai
3
mcp-builder
LLMใๅค้จใตใผใในใจๅฏพ่ฉฑใใใใใฎ้ฉๅใซ่จญ่จใใใใใผใซใ้ใใฆใ้ซๅ่ณชใชMCP (Model Context Protocol) ใตใผใใผใไฝๆใใใใใฎใฌใคใใPython (FastMCP)ใNode/TypeScript (MCP SDK)ใRust (Tokio)ใงใๅค้จAPIใใตใผใในใ็ตฑๅใใMCPใตใผใใผใๆง็ฏใใ้ใซไฝฟ็จใใพใใ
chronista-club
data-ai
llm-ai
3
agilab-local-llm
Guidance for using local LLM backends (Ollama/GPT-OSS) inside AGILAB with correctness-first prompts.
ThalesGroup
data-ai
llm-ai
3
sage-agent-execution
Sage Agent ๆง่กๅผๆๅผๅๆๅ๏ผๆถต็ UnifiedExecutorใSubagentใLifecycle ็ฎก็
majiayu000
data-ai
llm-ai
3
developing-llamaindex-systems
Production-grade agentic system development with LlamaIndex in Python. Covers semantic ingestion (SemanticSplitterNodeParser, CodeSplitter, IngestionPipeline), retrieval strategies (BM25Retriever, hybrid search, alpha weighting), PropertyGraphIndex with graph stores (Neo4j), context RAG (RouterQueryEngine, SubQuestionQueryEngine, LLMRerank), agentic orchestration (ReAct, Workflows, FunctionTool), and observability (Arize Phoenix). Use when asked to "build a LlamaIndex agent", "set up semantic chunking", "index source code", "implement hybrid search", "create a knowledge graph with LlamaIndex", "implement query routing", "debug RAG pipeline", "add Phoenix observability", or "create an event-driven workflow". Triggers on "PropertyGraphIndex", "SemanticSplitterNodeParser", "CodeSplitter", "BM25Retriever", "hybrid search", "ReAct agent", "Workflow pattern", "LLMRerank", "Text-to-Cypher".
SpillwaveSolutions
data-ai
llm-ai
3
sage-context-management
Sage ไธไธๆ็ฎก็ๅผๅๆๅ๏ผๆถต็ Token ไผฐ็ฎใๆถๆฏ่ฃๅชใ่ชๅจๅ็ผฉใๆ่ฆ็ๆ
majiayu000
data-ai
llm-ai
3
frontend-master
Frontend UI/UX work with Gemini CLI in --yolo mode. Use when (1) modifying visual/styling elements in frontend files (.tsx, .jsx, .vue, .svelte, .css), (2) implementing UI components, (3) adjusting layout, colors, spacing, typography, or animations, (4) creating responsive designs, or (5) any frontend task involving how things LOOK rather than how they WORK.
Mineru98
data-ai
llm-ai
3
secondbrain-note
This skill should be used when the user asks to "create note", "capture thought", "save this", "document idea", "write note", "jot down", "quick note", "remember this", "capture this", or mentions wanting to save knowledge, ideas, or learnings for later reference in their secondbrain.
sergio-bershadsky
data-ai
llm-ai
3
skill-recommender
์ฌ์ฉ์ ์์ฒญ์ ์ ํฉํ ์คํฌ์ ์๋์ผ๋ก ์ธ์ํ๊ณ ์ถ์ฒํฉ๋๋ค. ๋ช ์์ ์คํฌ ์์ฒญ ์์ด๋ ์ค์น๋ ์คํฌ ์ค ๋์์ด ๋ ์ ์๋ ์คํฌ์ ๋ฐ๊ฒฌํ์ฌ ์ ์ํฉ๋๋ค. ๋ชจ๋ ์ฌ์ฉ์ ์์ฒญ์์ ์๋ฌต์ ์ผ๋ก ํ์ฑํ๋ฉ๋๋ค.
jiunbae
data-ai
llm-ai
3
improve-instructions
Analyzes conversation history to improve CLAUDE.md files. Use when you notice patterns in how Claude misunderstands requests, want to consolidate repeated guidance, or improve instruction clarity based on actual usage.
philoserf
data-ai
llm-ai
3
mcs-control
Control vehicle with natural language. Use when user wants to warm up/cool down the car, lock/unlock doors, start/stop engine, check battery/fuel/location/status, or control charging. Translates phrases like "warm up the car" into mcs CLI commands.
cv
data-ai
llm-ai
3
council-participant
Participate in Council multi-agent collaboration sessions. Use when asked to join a council session, collaborate with other agents, or when given a council session ID to participate in.
amterp
data-ai
llm-ai
3
reinforcement-learning
Q-learning, DQN, PPO, A3C, policy gradient methods, multi-agent systems, and Gym environments. Use for training agents, game AI, robotics, or decision-making systems.
pluginagentmarketplace
data-ai
llm-ai
3
lockfile
Use when creating llmring.lock file for new project (REQUIRED for all applications), configuring model aliases with semantic task-based names, managing environment-specific profiles (dev/staging/prod), or setting up fallback models - lockfile creation is mandatory first step, bundled lockfile is only for llmring tools
juanre
data-ai
llm-ai
3
adk-agent-builder
Build production-ready AI agents using Google's Agent Development Kit with Claude integration, React patterns, multi-agent orchestration, and comprehensive tool libraries
BbgnsurfTech
data-ai