AI & LLM Engineering

Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.

shareAI-lab/learn-claude-code

Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

anthropics/claude-plugins-official

Manages a Sub2API deployment from the command line: accounts, redeem and invitation codes, groups, proxies, imports, exports and raw admin API calls.

Wei-Shaw/sub2api

Replay-first debug flow for SGLang serving problems. An agent skill from sgl-project/sglang.

sgl-project/sglang

Add unsigned integer (uint) type support to PyTorch operators by updating ATDISPATCH macros.

pytorch/pytorch

Generates music from text descriptions with MusicGen and sound effects with AudioGen, using Meta's AudioCraft PyTorch library with melody and style conditioning.

Orchestra-Research/AI-Research-SKILLs

Adds persistent memory to AI apps with the Mem0 Python and TypeScript SDKs: store, search, update and delete user memories, with framework integrations.

mem0ai/mem0

Write docstrings for PyTorch functions and methods following PyTorch conventions.

pytorch/pytorch

Forecasts any univariate time series zero-shot with Google's TimesFM model, returning point forecasts and calibrated prediction intervals without training.

google-research/timesfm

Finds every LLM workflow in a repository, proposes a labeling table and, once you agree, wires labels so Caveman Cloud groups spend per workflow.

JuliusBrussee/caveman

Runs lm-evaluation-harness to benchmark language models on academic suites such as MMLU, GSM8K and HumanEval, compare models and track training checkpoints.

Orchestra-Research/AI-Research-SKILLs

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.

fossasia/eventyay-interpretation

Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.

sgl-project/sglang

Read-only review of Caveman Cloud data to explain where LLM spend goes: cost, score, workflows, traces, latency, errors, routing and verified savings.

JuliusBrussee/caveman

Answer questions about the AI SDK and help build AI-powered features.

vercel-labs/ai-facts

Patterns and tested examples for building agents with Pydantic AI: tools, capabilities, structured output, dependency injection, hooks, YAML specs, streaming and testing.

docling-project/docling

Guide to using Meta's Segment Anything Model for zero-shot image segmentation with point, box or mask prompts, or automatic mask generation.

Orchestra-Research/AI-Research-SKILLs

Reference of Claude API examples and guides covering tool use, vision, RAG, classification, summarization, text-to-SQL, prompt caching and agent patterns.

2025Emma/vibe-coding-cn

Set up and use 1Password CLI (op). An agent skill from trpc-group/trpc-agent-go.

trpc-group/trpc-agent-go

Self-evolution engine for agents: studies runtime history for failures and inefficiencies, writes improvements, and syncs with the EvoMap Hub through a local proxy mailbox.

EvoMap/evolver

Runs web-grounded searches through Perplexity's Sonar models over OpenRouter for current events, recent literature and cited facts beyond the model's training cutoff.

davila7/claude-code-templates

Reference for building AI agents with the Cline SDK: the Agent runtime, ClineCore sessions, custom tools, plugins, events, providers, scheduling and multi-agent teams.

cline/cline

Reads the state and results of Caveman Cloud experiments and reports one recommendation or a block, without changing an experiment's lifecycle itself.

JuliusBrussee/caveman

Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.

pytorch/pytorch

Converts PDFs, Office files, HTML, images and other documents into a unified DoclingDocument with Markdown or JSON output, through the docling CLI, Python SDK or a remote service.

docling-project/docling

Finds or validates a usable SageMaker execution role before deploying or training, so scripts do not try to create IAM roles they lack permission to create.

huggingface/skills

Operates an opencodex (`ocx`) proxy: finds CLI tasks offline, checks local configuration, and manages accounts, providers, models, routing and usage reports.

lidge-jun/opencodex

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.

jarrodwatts/claude-code-config

Shows how to store documents and embeddings in Chroma, query them by similarity with metadata filters, and persist them to disk for RAG and semantic search projects.

Orchestra-Research/AI-Research-SKILLs

Use Linear as the org's memory: reconstruct a feature's history before touching it, and leave the reasoning behind finished work in the ticket description so the next agent inherits it.

langfuse/langfuse

Turns a Caveman report-only optimization observation into one minimal code change and a paired baseline evaluation, after the operator picks which to pursue.

JuliusBrussee/caveman

Lets the agent answer questions about a video from a URL or local file by downloading it, extracting frames and a transcript, or by sending it to Gemini's video model.

bradautomates/claude-video

Fetches current documentation for third-party APIs and SDKs with the chub CLI before the agent writes code against them, instead of relying on remembered API shapes.

andrewyng/context-hub

Add a new ONNX operator or update an existing operator to a new opset version.

onnx/onnx

Chooses the right serving container and current image URI for deploying a Hugging Face model to a SageMaker endpoint, preferring Hugging Face images over generic ones.

huggingface/skills

Delegate a coding task to Aider (aider) as a background implementer, then review its diff and land it yourself.

amElnagdy/delegate-skills

Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.

giancarloerra/SocratiCode

Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.

rohitg00/ai-engineering-from-scratch

Turns a rough idea into one ready-to-paste prompt tuned for a specific AI tool such as an LLM, Cursor, Midjourney or a video model.

nidhinjs/prompt-master

Mines local Copilot CLI session logs for dotnet/maui to rank costly or failing runs, tag recurring failure modes, propose repo edits and emit guard evals.

dotnet/maui

Explains OpenAI's CLIP model for zero-shot image classification, image-text similarity, semantic image search and content moderation, with install steps and code patterns.

Orchestra-Research/AI-Research-SKILLs

Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.

liustack/modlens

A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…

danyuchn/asd-ste100-skill

This skill enriches vague prompts with targeted research and clarification before execution.

severity1/claude-code-prompt-improver

Turns an OpenAPI or Swagger spec into an MCP server with the mcp-use TypeScript SDK, mapping each operation to a tool, wiring auth, testing and deploying.

mcp-use/mcp-use

Adds, searches, lists, updates and deletes memories on the Mem0 platform from the terminal with the mem0 command, including a JSON mode built for agents.

mem0ai/mem0

A skill your agent uses when needing to compile, rebuild, or install Paddle from source after code changes.

PaddlePaddle/Paddle

Provides context about the CoStrict evals system structure in this monorepo.

zgsm-ai/costrict