Best AI and LLM engineering skills, page 20

Runs ML training and batch jobs across clouds with SkyPilot, using spot instances, automatic region selection and managed recovery to cut GPU cost.

Orchestra-Research/AI-Research-SKILLs

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).

Orchestra-Research/AI-Research-SKILLs

Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction.

Orchestra-Research/AI-Research-SKILLs

Explains how to run Qdrant, a Rust vector database, for RAG and semantic search, covering collections, points, distance metrics and filtered or batched queries.

Orchestra-Research/AI-Research-SKILLs

Walks through aligning language models with SimPO, a reference-free preference optimization method, using accelerate configs for Mistral 7B, Llama 3 8B and math-focused models.

Orchestra-Research/AI-Research-SKILLs

Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.

Orchestra-Research/AI-Research-SKILLs

Optimizes and serves LLMs on NVIDIA GPUs with TensorRT-LLM, covering quantization, in-flight batching, multi-GPU parallelism and the trtllm-serve command.

Orchestra-Research/AI-Research-SKILLs

A skill your agent uses when generating research/factcheck/image/video/slide prompts that need base templates (IFCN·StructuredResearch 등) — 단일 통합 AI 프롬프트 엔지니어링 레퍼런스의 라우팅 인덱스.

treylom/prompt-engineering-skills

Register zarr positions into the Computational Imaging Database on Airtable, write channelsmetadata/experimentmetadata to zarr .zattrs, or bulk-update Airtable records via MCP.

mehta-lab/VisCy

Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch.

mydisha/keirouter

View cost breakdowns, token usage, and call logs from the CLI. Filter by provider, model, or date range. Export usage reports and inspect…

diegosouzapw/OmniRoute

Mastra AI framework integration guide for building TypeScript agents with skills, workflows, and memory

helloxz/znote

Creates or updates Margin Eval agent definitions for new CLI coding agents.

Margin-Lab/evals

Every technical claim drawn from the local corpus must ship with a source citation formatted as path:line or path:section.

lyonzin/knowledge-rag

提取并总结 B 站视频或微信公众号文章；转写、深度报告和知识库入库按用户请求选择。其他网站使用当前可用的网页读取工具. An agent skill from zhu1090093659/dsh-trading.

zhu1090093659/dsh-trading

Shows how to pull validated, typed data out of LLM responses with Instructor and Pydantic models, including retries on failure and partial streaming.

Orchestra-Research/AI-Research-SKILLs

Calls the Brave Search Answers endpoint for AI-grounded, cited answers, either a fast single-search reply or a slower multi-search deep research run.

brave/brave-search-skills

Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols.

curiositech/some_claude_skills

Build or modify Apple Foundation Models features in Swift, SwiftUI, iOS, and macOS apps.

rryam/FoundationModelsKit

A skill your agent uses when checking the overall health of a skills library.

MoizIbnYousaf/ai-agent-skills

AI Engineering from Scratch 的阶段测验。用于“给我测验一下”、“测试阶段”、“检查我的理解”、“我掌握第 3 阶段了吗”，也支持 "quiz me", "test phase", "check my understanding", "do I know phase 3" 或 /check-understanding <phase。

fancyboi999/ai-engineering-from-scratch-zh

Add a durable VibeComfy ready workflow/template from a ComfyUI source workflow.

peteromallet/VibeComfy

A skill your agent uses when the user wants to set up LLM training for the first time, or when traininghub is not yet installed/configured in the current environment.

Red-Hat-AI-Innovation-Team/training_hub

Maximum-efficiency dev mode: terse zero-fluff prose + YAGNI/ladder-first code.

JayPokale/Chisle

Sets up ExecuTorch as a Zephyr RTOS module, adds board support and debugs west build failures such as linker memory overflow on embedded boards.

pytorch/executorch

A skill your agent uses when asked about harness9 architecture, module design, or how components interact — explains the system design

ZhangShenao/harness9

Integrate a new text-to-speech model into vLLM-Omni from HuggingFace reference implementation through production-ready serving with streaming and CUDA graph acceleration.

vllm-project/vllm-omni

Sets up a structured debugging session for a Dynamo bug — pull the report from a Linear ticket, GitHub issue, or pasted text, capture the environment, create a persistent worklog markdown file, and…

ai-dynamo/dynamo

Shift Python apps dem from Azure OpenAI Chat Completions go Responses API.

microsoft/ai-agents-for-beginners

从音频文件中提取文字（语音转文字），需要腾讯云 API 凭据。当用户提到音频转文字、语音识别、ASR、音频转字幕时使用。

CoderWanFeng/python-office

Declared architecture snapshot for one Agentforce agent: planner, topics, actions, flows, Apex, prompt templates, and NGA plugins.

forcedotcom/sf-skills

Checks an LLM judge against human labels using train, dev and test splits, TPR and TNR, and a bias correction applied to production data.

ai-evals-course/evals-skills

Probes whether an agent with web fetch and stored user memory can be tricked by a malicious page into leaking data through chained URL paths.

Tencent/AI-Infra-Guard

设置 Claude Code 钩子，在危险 Git 命令（push、reset --hard、clean、branch -D 等）执行前将其拦截。当用户想要防止破坏性 Git 操作、添加 Git 安全钩子或在 Claude Code 中阻止 git push/reset 时使用。

devcxl/mattpocock-skills-zh

Complete Base development playbook. An agent skill from base/skills.

base/skills

Plan and prepare the QVAC agent-stack release cascade across @qvac/inference, @qvac/sdk, @qvac/cli, @qvac/ai-sdk-provider, @qvac/opencode-plugin, and @qvac/openclaw-plugin.

tetherto/qvac

Queries Langfuse traces, prompts, datasets and sessions, and analyzes local LLM gateway logs for requests, context growth, token use and cache hits.

KonghaYao/peri

Show a Culture agent's full configuration in one read-only view: its system-prompt file (CLAUDE.md / AGENTS.md / GEMINI.md), the parallel culture.yaml, and the agent's local .claude/skills index.

agentculture/culture

Deploy and serve GenRec checkpoints with FlashRec (install, serve.sh, SID trie, wide-beam knobs, health/curl, FP8, profiling).

sohu-mptc/FlashRec

Deploys open models or custom weights from Model Garden to Agent Platform endpoints, checks deployment status and cleans up endpoints, confirming before any change.

google/skills

Run MemMesh's competitive benchmark harness (LOCOMO / BEAM) to compare retrieval quality, tokens, latency, and cost against Mem0, Zep, full-context, and naive-RAG baselines.

ThinkfleetAI/memmesh

A skill your agent uses when we want to turn a just-finished Formax workflow (e.g.

yusifeng/formax

Runs the narrowest relevant tests to validate changes. An agent skill from noumena-labs/Sipp.

noumena-labs/Sipp

Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs).

K-Dense-AI/mimeo

Guided workflow for adding a new model architecture to llama.cpp.

JakeATX/llamAmpere

Sciverse academic paper retrieval: structured metadata search, semantic chunk retrieval for RAG, and character-range content reading (offsets in Unicode code points).

opendatalab/Sciverse-Agent-Tools

Migrate to Langfuse from another LLM observability/evals platform (LangSmith, Arize AX, Phoenix, Braintrust, Helicone, Promptfoo, ...).

langfuse/skills

Orchestrate DeepSeek Oracle multi-agent workflows by routing user intents to specialist oracle skills, enforcing safety gates, and composing one unified answer with follow-up questions and action…

Bald0Wang/DeepSeek-Oracle