Best AI and LLM engineering skills, page 18

Routes LangGraph agents with typed decision models that return probabilities, and finds LLM calls that only exist to produce a routing decision.

langchain-ai/langchain-skills

Wires up an Airbyte connector for use in a PydanticAI, Claude SDK, or other agent.

airbytehq/airbyte-agent-sdk

Use FlowFlow spaces safely through their scoped MCP server. An agent skill from mirkobozzetto/flowflow.

mirkobozzetto/flowflow

Bilingual guide for running offlinepacking/autopipe.sh across multiple nodes to produce padding-free packed WebDataset shards for SFT, with Energon Metadataset assembly

EvolvingLMMs-Lab/LLaVA-OneVision-2

Repository-level wrapper for the canonical Qwen MTP or nextn GGUF release workflow.

R6410418/Jackrong-llm-finetuning-guide

Advanced image prompt engineering assistant for Chinese-first users.

TanShilongMario/PromptSkill4image

Define a spend budget for Claude Code and, optionally, create a cost alert rule that fires when usage crosses the limit, via POST /api/alerts/rules on the Agent Monitor dashboard.

hoangsonww/Claude-Code-Agent-Monitor

Reference desk for Nemotron 3 Nano / Llama-Nemotron Nano 3 — architecture, training data, recipes, evaluation, quantization, deployment.

NVIDIA-NeMo/Nemotron

Find the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic classifier, or a small model, with fail-closed routing.

undefined-ui/second-brain-os

Build consistent characters, environments and props in Guaardvark's Cast Library and train LoRAs for them locally (reference photos → vision bible → sample plan → approved samples → training).

guaardvark/guaardvark

Discord CLI with YAML-first structured output for AI agents — fetch chat history, search messages, sync channels, and AI analysis

jackwener/discord-cli

A skill your agent uses whenever the user asks to debug something, fix a bug, troubleshoot an issue, or mentions "scientific debugging".

UKGovernmentBEIS/vllm-lens

A skill your agent uses when creating, improving, or optimizing prompts for Claude.

chrispangg/deepagentsdk

A skill your agent uses when a Lens change needs backend HTTP contract coverage.

dyedd/lens

用 Twinkle Eval 跑一次評測——建立 config.yaml、下載或指定資料集、驗證設定、執行並讀結果。當使用者說「跑 benchmark」「跑評測」「建 config」「evaluate 這個模型」「twinkle-eval 怎麼跑」「評測結果怎麼看」「為什麼分數是 0」時使用。涵蓋 15 種 evaluationmethod 的 config 差異、27 個內建可下載…

ai-twinkle/Eval

Review and adapt vllmmetax/registry registrations, quantization configurations, CustomOps and kernel dispatch against a target vLLM revision and installed MetaX APIs.

MetaX-MACA/vLLM-metax

Generate model metadata for an ML model so it works with xybrid.

xybrid-ai/xybrid

Guidance for using the MMSP Python SDK (mmsp). An agent skill from Prism-Shadow/model-message-stream-protocol.

Prism-Shadow/model-message-stream-protocol

Call the OpenAgents API (Open Responses and Chat Completions, many models, one key) and read its docs.

OpenAgentsInc/openagents

Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then…

jszmajda/lid

Route Celestia requests to the correct repo and apply canonical blob submit/retrieve guidance (Go, Rust, and Node RPC) with docs guardrails.

celestiaorg/docs

Opens the Token Optimizer dashboard in the browser (context usage, quality, savings).

alexgreensh/token-optimizer

Automated NCU (Nsight Compute) profiling workflow with full metrics collection and persistent storage

maxiaosong1124/ncu-cuda-profiling-skill

Shared execution protocol for the Alibaba Cloud Bailian bl skill family, covering consent, version checks, authentication and install, issue reporting and output conventions.

modelstudioai/cli

Register, extend, or audit instructions in the table-driven T.ptx dialect (python/tvm/backend/cuda/ptx/table.py), and move the table to a newer PTX ISA version.

mlc-ai/relax

A skill your agent uses when writing, reviewing, or debugging JAX code that involves quax — custom array-ish objects (physical units, LoRA, sparse, symbolic zero, named axes), quax.quaxify…

nstarman/quax

Interact with a Meshtastic LoRa mesh network through MESH-API — list nodes, read messages, send texts, and check connection status.

mr-tbot/mesh-api

在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team…

zjp1997720/codex-model-routing-team

Google Coral Edge TPU — real-time object detection natively (macOS / Linux)

SharpAI/DeepCamera

Spins up a local Omnigent server and exercises the Antigravity (Gemini) SDK harness end to end: building agents, running real turns, smoke tests and bug-bashing.

omnigent-ai/omnigent

Creates and refactors model and controller concerns for shared behavior.

dilolabs/nosia

Run a full GEO analysis — guides you through setup, brand research, query generation, execution, analysis, and reporting

onvoyage-ai/voyage-geo-agent

Research a competitor across the web and produce a cited, structured brief.

openlegion-ai/openlegion

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab.

JimLiu/science-skills

Configure how the playground is displayed: full, focus, simple, lite, editor, codeblock, and result modes.

live-codes/livecodes

Generate YAML configuration files and run CLI commands to onboard organizations into ModelGuide.

modelguide/modelguide

Acquire images as files — generate them with an AI image model (14 providers: OpenAI/gpt-image, Gemini, Qwen, Zhipu, Volcengine, Stability, FLUX, Ideogram, MiniMax, and more), search openly-licensed…

open-octo/octo-agent

Add a new quantization data type to AutoRound (e.g., INT, FP8, MXFP, NVFP, GGUF variants).

intel/auto-round

Scaffold new Celeritas source and test files with the required copyright header and register them in CMake.

celeritas-project/celeritas

把本地长视频/音频转写成文字稿 + 可选字幕，纯本地（不上传云端），用 sherpa-onnx X-ASR Zipformer transducer 模型（int8 量化、中英双语、自动标点）。已在 macOS Apple Silicon（int8 + AMX，~100× 实时）、Linux ARM64（CPU，~32× 实时）与 Windows（PowerShell…

ysyecust/lecture-to-notes

PenShot 项目开发 Skill。用于修改或审查 Agent、LangGraph 工作流、任务生命周期、记忆/RAG、配置、REST、MCP、CLI、测试和项目文档；先核实源码与工具配置，再按现有架构实施并验证。

neopen/story-shot-agent

Query Finelog logs and telemetry for Iris tasks, workers, profiles, training, vLLM, and cross-cluster forwarding.

marin-community/marin

Test LLM models served by xinfer for correctness, output quality, and performance.

guoqingbao/xinfer

Tune and review Langfuse autoscaling for web, web-iso, and web-ingestion.

langfuse/langfuse

Defines typia benchmark fixture integrity, result reporting, and publication safeguards.

samchon/typia

Turn Bilibili videos that are already registered and parsed in MindSpace, or Bilibili opus/article posts, into evidence-linked Markdown learning notes.

mingchen666/Reviva

Expert guidance for Satori, the library that converts JSX/HTML and CSS into SVG (the engine behind dynamic Open Graph images and social cards).

usenotra/notra

Building chat interfaces in Streamlit. An agent skill from iusztinpaul/designing-real-world-ai-agents-workshop.

iusztinpaul/designing-real-world-ai-agents-workshop