home/categories/llm-ai

category focus

LLM & AI

Large Language Models and AI agents.

4725 skillsall categories

sorting

stars

current ordering strategy

query

all entries

refine the visible subset

llm-ai

708

lpend

Fetch the latest reply from Claude storage via the `lpend` CLI. Use only when the user explicitly asks to view the Claude reply/response (e.g. "看下 Claude 回复/输出"); do not run proactively after `lask` unless requested.

bfly123

data-ai

open

llm-ai

708

lping

Test connectivity with Claude via the `lping` CLI. Use when the user explicitly asks to check Claude status/connection (e.g. "l ping", "Claude alive?"), or when troubleshooting Claude not responding.

bfly123

data-ai

open

llm-ai

708

lask

Send a task to Claude via the `lask` CLI and wait for the reply. Use only when the user explicitly delegates to Claude; not for questions about Claude itself.

bfly123

data-ai

open

llm-ai

708

gask

Send a task to Gemini via the `gask` CLI and wait for the reply. Use only when the user explicitly delegates to Gemini (ask/@gemini/let gemini/review); not for questions about Gemini itself.

bfly123

data-ai

open

llm-ai

708

cask

Async via cask, end turn immediately; use only when user explicitly delegates to Codex (ask/@codex/let codex/review); NOT for questions about Codex itself.

bfly123

data-ai

open

llm-ai

708

gask

Async via gask, end turn immediately; use only when user explicitly delegates to Gemini (ask/@gemini/let gemini/review); NOT for questions about Gemini itself.

bfly123

data-ai

open

llm-ai

693

complete-example

AI 增强版 LaTeX 示例智能生成器，实现 AI 与硬编码的有机融合。AI 做"语义理解"（分析章节主题、推理资源相关性、生成连贯叙述），硬编码做"结构保护"（格式验证、哈希校验、访问控制）。用于用户要求"填充示例内容/生成示例/补充 LaTeX 示例"等场景。

huangwb8

data-ai

open

llm-ai

683

codex-claude-loop

Orchestrates a dual-AI engineering loop where Claude Code plans and implements, while Codex validates and reviews, with continuous feedback for optimal code quality

bear2u

data-ai

open

llm-ai

683

codex-claude-cursor-loop

Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality

bear2u

data-ai

open

llm-ai

683

codex-claude-cursor-loop

Orchestrates a triple-AI engineering loop where Claude plans, Codex validates logic and reviews code, and Cursor implements, with continuous feedback for optimal code quality

bear2u

data-ai

open

llm-ai

627

pi-share

Load and parse session transcripts from shittycodingagent.ai/buildwithpi.ai/buildwithpi.com (pi-share) URLs. Fetches gists, decodes embedded session data, and extracts conversation history.

mitsuhiko

data-ai

open

llm-ai

620

open-prose

OpenProse is a programming language for AI sessions. Activate on ANY `prose` command (prose boot, prose run, prose compile, prose update, etc.), running .prose files, mentioning OpenProse/Prose, or orchestrating multi-agent workflows. The skill intelligently interprets what the user wants.

openprose

data-ai

open

llm-ai

535

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).

skillcreatorai

data-ai

open

llm-ai

532

moai-foundation-core

MoAI-ADK's foundational principles - TRUST 5, SPEC-First DDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows

modu-ai

data-ai

open

llm-ai

515

prompt-optimization

Applies prompt repetition to improve accuracy for non-reasoning LLMs

asklokesh

data-ai

open

llm-ai

505

decision-critic

Invoke IMMEDIATELY via python script to stress-test decisions and reasoning. Do NOT analyze first - the script orchestrates the critique workflow.

solatis

data-ai

open

llm-ai

505

prompt-engineer

Invoke IMMEDIATELY via python script when user requests prompt optimization. Do NOT analyze first - invoke this skill immediately.

solatis

data-ai

open

llm-ai

505

deepthink

Invoke IMMEDIATELY via python script when user requests structured reasoning for open-ended analytical questions. Do NOT explore first - the script orchestrates the thinking workflow.

solatis

data-ai

open

llm-ai

494

typescript-sdk-reference

Comprehensive reference for the TypeScript Agent SDK with functions, types, and interfaces for programmatic Claude Code interactions

CaptainCrouton89

data-ai

open

llm-ai

469

prompt-refiner-claude

Refine prompts for Claude models (Opus, Sonnet, Haiku) using Anthropic's best practices. Use when preparing complex tasks for Claude.

Factory-AI

data-ai

open

llm-ai

469

prompt-refiner-gpt

Refine prompts for GPT models (GPT-5, GPT-5.1, Codex) using OpenAI's best practices. Use when preparing complex tasks for GPT.

Factory-AI

data-ai

open

llm-ai

456

ui-skills

Opinionated constraints for building better interfaces with agents.

ibelick

data-ai

open

llm-ai

454

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Trevoke

data-ai

open

llm-ai

451

add-model

Add a new language model to the Giselle codebase. Use when the user wants to add, register, or integrate a new LLM model (OpenAI, Anthropic, Google) into the system.

giselles-ai

data-ai

open

Page 50 / 197