category focus

LLM & AI

Large Language Models and AI agents.

4725 स्किल्सall categories
sorting
stars
current ordering strategy
query
all entries
refine the visible subset
llm-ai
3

agent-authoring

Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best practices.

philoserf
philoserf
data-ai
open
llm-ai
3

prompt-optimizer

撰写提示词、优化提示词、改写 Prompt、Prompt 优化。将模糊的想法转化为精确有效的 AI 提示词,支持 ChatGPT、Claude、Gemini、DeepSeek、豆包、智谱等多平台。

TestAny-io
TestAny-io
data-ai
open
llm-ai
3

self-improving-agent

A universal self-improving agent that learns from ALL skill experiences. Uses multi-memory architecture (semantic + episodic + working) to continuously evolve the codebase. Auto-triggers on skill completion/error with hooks-based self-correction.

Charon-Fan
Charon-Fan
data-ai
open
llm-ai
3

mcp-tools-as-code

Convert MCP servers to typed TypeScript APIs for efficient code execution. Reduces token usage by 98%+ by transforming tool calls into programmatic access. Use when building agents that need to interact with multiple MCP servers efficiently, when context window is a concern, or when native control flow (loops, conditionals) would simplify multi-step workflows.

cameronsjo
cameronsjo
data-ai
open
llm-ai
3

ag-ui-protocol

AG-UI (Agent-User Interaction) protocol reference for building AI agent frontends. Use when implementing AG-UI events (RUN_STARTED, TEXT_MESSAGE_*, TOOL_CALL_*, STATE_*), building agents that communicate with frontends, implementing streaming responses, state management with snapshots/deltas, tool call lifecycles, or debugging AG-UI event flows.

meetsmore
meetsmore
data-ai
open
llm-ai
3

arch-analysis

Analyze LangGraph application architecture, identify bottlenecks, and propose multiple improvement strategies

hiroshi75
hiroshi75
data-ai
open
llm-ai
3

queue-task

Creates claude-queue tasks when usage limits are approaching. Use when the user is running low on Claude usage quota, mentions hitting limits, or when significant work remains and we should queue it for unattended execution. Proactively suggests queuing remaining work during long coding sessions.

vasiliyk
vasiliyk
data-ai
open
llm-ai
3

sage-learning-system

Sage 独有的学习系统设计,包含模式识别、用户偏好学习、纠正反馈机制

majiayu000
majiayu000
data-ai
open
llm-ai
3

agent-creator

Create custom Task subagents in ~/.claude/agents/. Use when defining new agents for Task tool delegation.

HTRamsey
HTRamsey
data-ai
open
llm-ai
3

cli-guide

SIMBL CLI command reference and usage guide. Use when working with SIMBL tasks or needing CLI syntax reference.

yebot
yebot
data-ai
open
llm-ai
3

crisis-persistence-eval

Multi-turn safety persistence evaluation for crisis scenarios. Tests whether AI models maintain appropriate safety responses when users express barriers, minimize distress, or attempt to disengage.

GOATnote-Inc
GOATnote-Inc
data-ai
open
llm-ai
3

lucid-client-api

Skill for interacting with the Lucid Client API (multi-agent runtime). The API is hosted in the lucid-client codebase and provides endpoints for managing agents, invoking entrypoints, handling payments, and more. Activate when: user wants to interact with the Lucid Client API, manage agents, invoke agent entrypoints, or work with the multi-agent runtime system.

daydreamsai
daydreamsai
data-ai
open
llm-ai
3

hol

HOL4 interactive proof development. Use when working with HOL4 proofs, .sml theorem files, Holmake builds, or hol-agent-helper.sh sessions. (project)

charles-cooper
charles-cooper
data-ai
open
llm-ai
3

skill-creation

Guide for creating new Agent Skills with proper structure, frontmatter, bundled assets, and validation. Includes templates, best practices, and examples for building reusable skill resources.

anhvth
anhvth
data-ai
open
llm-ai
3

adk-agent-builder

Guide for adding new agents to the ADK pipeline. Use when creating a new LlmAgent, SequentialAgent, or ParallelAgent, or when extending the pipeline with additional processing stages.

lavinigam-gcp
lavinigam-gcp
data-ai
open
llm-ai
3

vertex-agent-builder

Build and deploy production-ready generative AI agents using Vertex AI, Gemini models, and Google Cloud infrastructure with RAG, function calling, and multi-modal capabilities

BbgnsurfTech
BbgnsurfTech
data-ai
open
llm-ai
3

openrouter-typescript-sdk

Complete reference for integrating with 300+ AI models through the OpenRouter TypeScript SDK using the callModel pattern

OpenRouterTeam
OpenRouterTeam
data-ai
open
llm-ai
3

multi-llm

Route tasks to optimal LLM provider (Gemini, Codex, Copilot, Claude)

HTRamsey
HTRamsey
data-ai
open
llm-ai
3

user-memory

Long-term user profile memory that persists across Claude Code sessions

cameronsjo
cameronsjo
data-ai
open
llm-ai
3

sage-prompt-engineering

Sage Prompt 工程规范,学习 Crush 的模板化方案,包含 system prompt 设计最佳实践

majiayu000
majiayu000
data-ai
open
llm-ai
3

llm-integration

Guide for using LLM utilities in speedy_utils, including memoized OpenAI clients and chat format transformations.

anhvth
anhvth
data-ai
open
llm-ai
3

knowledge

Project Cortex - Structural Knowledge Injection for LLM

tao3k
tao3k
data-ai
open
Previous
Page 100 / 197
Next