AI & LLM Engineering · For developers

Shows how to organize PyTorch training with Lightning's LightningModule and Trainer, covering validation, DDP, callbacks and learning-rate scheduling.

Orchestra-Research/AI-Research-SKILLs

A skill your agent uses when benchmarking denoise latency or profiling a diffusion bottleneck in SGLang.

sgl-project/sglang

Convert make demo/img statusline snapshots into ANSI-stripped plain text for diffing and PR embedding.

tmck-code/yet-another-statusline

Create, modify, and improve PINA skills. An agent skill from PINA-org/PINA.

PINA-org/PINA

Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

Haohao-end/openagent

Turn llmprobe reports into the charts a perf PR embeds (one line per arm across context size, every point labelled, machine and model in the caption) and host them so the PR body renders them.

ddalcu/mlx-serve

PaddlePaddle (飞桨) C++ 算子开发指南。提供从 YAML 配置、InferMeta 函数、Kernel 实现、Python API 封装、单元测试到编译验证的完整算子开发流程指导。在以下场景使用此 skill：(1) 为 Paddle 框架新增 C++ 算子 (2) 修改或调试已有 Paddle 算子 (3) 编写算子的 YAML…

PaddlePaddle/Paddle

Integrates a hosted API or local/open-weight model end-to-end across OpenTryOn (adapter, CLI registry, MCP, docs) and TryOn Studio (catalog, Connect keys, planner).

tryonlabs/opentryon

Shows how to add Deepgram analytics such as diarization, summaries, sentiment, topics, redaction and language detection to speech transcription in Python.

deepgram/deepgram-python-sdk

Migrate Python apps from Azure OpenAI Chat Completions to the Responses API.

microsoft/ai-agents-for-beginners

Stop and consult this skill whenever your response would include specific facts about Anthropic's products.

syahiidkamil/Software-Engineer-AI-Agent-Atlas

A skill your agent uses whenever writing, modifying, reviewing, or debugging code involving Celeste, celeste-ai, celeste-python, import celeste, src/celeste, or withceleste app integrations.

withceleste/celeste-python

Create, manage, and use E2B sandboxes — run commands, manage files, use git, persist state, and configure networking.

agent-sandbox/agent-sandbox

Gives patterns, a tool design checklist and an architecture decision tree for building agent harnesses, tools and multi-agent setups around a model.

FareedKhan-dev/claude-code-from-scratch

Call vision models (Doubao, Qwen, DeepSeek, OpenAI) to analyze images.

xiincs/claude-code-vision-skill

Rigor Setup skill for README-first deep learning repo reproduction.

lllllllama/RigorPilot-Skills

Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle.

yuting0624/antigravity-for-claude-code

Build voice AI agents with ElevenLabs. An agent skill from tadaspetra/loop.

tadaspetra/loop

Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion.

waybarrios/opencode-power-pack

Configure and test prompt compression from the CLI. Manage RTK filters, Caveman rules, stacked compression modes, and preview compression output…

diegosouzapw/OmniRoute

Installs, tunes and enforces Sponsio contracts that block unsafe tool calls in LLM agents, covering setup, auditing, observe mode and flipping to enforce.

SponsioLabs/Sponsio

Build, extend, and debug AI agents in Egroo using the Microsoft Agent Framework (C .NET).

jihadkhawaja/Egroo

Build multimodal AI apps with Pixeltable. An agent skill from pixeltable/pixeltable.

pixeltable/pixeltable

Plan a documentation eval for supabase/evals, where a docs guide is the subject under test.

supabase/evals

Review changed code for reuse, quality, and efficiency, then fix any issues found.

truffle-ai/dexto

当任务需要创建、修改、扩展或重组阿里云 SLS 的 dashboard JSON 或可导入的大盘配置时使用；尤其适用于线上大盘、强对比的分析看板、已校验的查询包，或需要专业中文标签与指标定义的运维向大盘。

alibaba/loongsuite-pilot

Creates and validates dubbo-go-pixiu LLM gateway conf.yaml. An agent skill from apache/dubbo-go-pixiu.

apache/dubbo-go-pixiu

Integrate Java business systems with ReachAI SDK registration, SDK instance heartbeat, gateway/embed access, and optional API Management handoff.

w8123/EnterpriseAgentFramework

CLI to manage emails via IMAP/SMTP. An agent skill from trpc-group/trpc-agent-go.

trpc-group/trpc-agent-go

Guides evaluation of a RAG system by diagnosing failures in traces, building a retrieval test set and scoring retrieval and generation separately.

ai-evals-course/evals-skills

Give a Node.js agent (such as OpenClaw) durable, local-first memory plus a queryable SPARQL knowledge graph, backed by CortexDB through its gRPC sidecar and the cortexdb-client npm package.

liliang-cn/cortexdb

Use this skill working with Ash Framework or any of its extensions.

podlove/radiator

Maintain and extend AFM (maclocal-api), a Swift OpenAI-compatible local LLM server and CLI for Apple Foundation Models, MLX models, API gateway proxying, and Vision OCR.

scouzi1966/maclocal-api

Fans a list of independent items out to subagents in parallel, merges the results back into a table and supports retrying only the rows that failed.

langchain-ai/langchain-skills

Enforce this repository's local-review-first GitHub sync policy.

R6410418/Jackrong-llm-finetuning-guide

A skill your agent uses when optimizing or generating a CUDA megakernel for a HuggingFace Llama-family model with AutoMegaKernel (AMK), drives the correctness-gated propose - eval - keep/revert loop…

RightNow-AI/AutoMegaKernel

Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface.

google/adk-python

Install, convert, debug, and benchmark sim2real ONNX GPU and TensorRT inference backends on onboard JetPack 5 Orin hosts such as g1-cable.

EGalahad/sim2real

The user asks a question about a video that was already watched or indexed — "what did they say about X", "what error code appears", "what happens at 2:30", "does the video show Y".

oxbshw/watch-skill

Refreshes the OpenAI and Anthropic model lists in Typebot's forge blocks using models.dev as the reference, adding new models first and keeping older ones.

baptisteArno/typebot.io

Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.

JuliusBrussee/caveman

当 Agent 接到专业任务（编码/爬虫/文件操作/API调用/数据分析/文档/部署/推送等）时，强制先查记忆层和技能索引，有匹配必用、无匹配必搜、答复时自动推荐（排除已装）。用于防止 Agent 跳过技能直接硬扛通用能力。跨平台通用（WorkBuddy/Claude/ChatGPT/Cursor/Gemini 等 20+ 框架）。完整版本史见 CHANGELOG.md。

jiabaobei/skills-constitution

Route a verl-omni performance investigation to the right tool and capture a usable trace.

verl-project/verl-omni

Builds a NeMo Gym (NVIDIA) variant of an RL environment. An agent skill from adithya-s-k/FineEnvs.

adithya-s-k/FineEnvs

Working with diverse data formats: binary, text, structured, and custom

vstorm-co/pydantic-deepagents

Turns the lead model into a foreman that plans, routes and verifies while cheaper Claude, Codex or Grok workers do the typing, using a per-machine routing card.

olsenbrands/fable-foreman

Interviews you about provider, cost, openness and image needs, then designs the models section of a mecatl settings file with aliases, slots and router categories.

stacklok/mecatl

Diagnose and fix Cosmos3 environment, installation, and runtime errors.

NVIDIA/cosmos-framework