AI & LLM Engineering

Guide for using SLIME (LLM post-training framework for RL Scaling).

yzlnew/infra-skills

Guides a one-question-at-a-time design interview, captures alignment in agent/EVE-BRIEF.md, then scaffolds and implements a runnable eve agent with verbose teaching comments.

Asymmetric-al/core

Harvest every honey: comment in the codebase into a debt ledger, so the deliberate shortcuts Lever 1 leaves behind get tracked instead of rotting into "later means never".

Green-PT/honey-for-devs

3DGS compression-to-deployment pipeline: quantization (scalar/VQ/mixed-precision), pruning (coreset/adaptive/variational/merge/Bayesian), progressive streaming & LoD, Web/WebGPU/mobile deployment…

jaccen/Awesome-Gaussian-Skills

Generate (and optionally open) a PyTorch release tracker / cherry-pick tracking issue from a release announcement, like https://github.com/pytorch/pytorch/issues/180506.

pytorch/test-infra

职业 Skill 工厂 2.0（career-skill-planner 升级版）。用户输入一个职业或行业，本 Skill 自动完成： (1) 遴选该行业 3 位顶尖专家，蒸馏其心智模型和决策方式，生成 3 个专家视角 Skill（参考女娲方法论）； (2) 遴选该行业 3 本顶尖书籍，提炼成可执行方法论，生成 3 个方法论 Skill（参考 book2skills 方法论）； (3) 生成…

SpaceZephyr/career.skill

Use early in an AI-agent project — before ship, before real traffic — to decide which evaluations to set up and to scaffold a starter experiment.

grafana/agento11y

Configure HTTP/HTTPS/SOCKS proxies for upstream provider requests. Set per-provider or global proxy rules, test connectivity, and manage proxy…

diegosouzapw/OmniRoute

Trim large MetaX model directories for dummy smoke tests or real-checkpoint loading on limited GPUs.

MetaX-MACA/vLLM-metax

Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn.

Archive228/loopkit

A skill your agent uses when the user wants to capture AI tool costs, review spending trends, set cost budgets, or integrate cost data into health snapshots — guides quarterly cost capture, records…

Habitat-Thinking/ai-literacy-superpowers

Apply the SGLang kernels RFC when adding, moving, splitting, or reviewing kernel APIs, registry metadata, kernel tests, benchmarks, and model-specific implementations.

sgl-project/sglang

Entry point for creating PINA problems. An agent skill from PINA-org/PINA.

PINA-org/PINA

llama.cpp local GGUF inference + HF Hub model discovery. An agent skill from Tommy-yw/RunbookHermes.

Tommy-yw/RunbookHermes

Answers questions about agent spend, token use, traces, events, errors and tool usage by running read-only SQL against a local TMA1 observability store.

tma1-ai/tma1

Browse installed bkit skills, agents, and evals via lib/discovery/explorer.js (filesystem scan, no subprocess).

ww-w-ai/bkit-claude-code

A skill your agent uses when moving skills between library workspaces or upgrading from a personal library to a team library.

MoizIbnYousaf/ai-agent-skills

Ancient text restoration, attribution, dating, contextualization, and embedding via Aeneas (Latin) / Ithaca (Ancient Greek).

google-deepmind/science-skills

AI Engineering from Scratch 中文版中的 MCPA（Model Context Protocol Associate）AI 原生导师与入门流程。学习者需要备考 MCPA、继续认证路线、 交互式学习下一课、运行并验证实践实验、参加诊断或全真模拟、根据薄弱领域 补弱时使用。适用于 Claude Code、Codex、ChatGPT、Cursor 或其他 agent。

fancyboi999/ai-engineering-from-scratch-zh

Search for ComfyUI workflow precedents, VibeComfy ready templates, node wiring examples, Banodoco/Hivemind community workflow knowledge, and concrete graph patterns before editing or adding a…

peteromallet/VibeComfy

Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

ntorga/agent-starter-kit

Compares a vision-language model's yes/no predictions with ground truth and writes the false-positive and false-negative cases to a JSONL file with a summary report.

NVIDIA/skills

Write idiomatic Elixir code with OTP patterns, supervision trees, and Phoenix LiveView.

davila7/claude-code-templates

Quick reference card for DSPy + Agent Framework integration patterns: typed signatures, assertions, routing cache, and agent handoffs.

Qredence/agentic-fleet

Use at review and ship, automatically for feature or architecture changes and on request for error handling, logging, crash reporting, or observability; verify errors reach production monitoring.

KbWen/agentic-os

ComfyUI node input types - INT, FLOAT, STRING, BOOLEAN, COMBO widgets, hidden inputs, optional inputs, lazy inputs, forceinput.

jtydhr88/comfyui-custom-node-skills

Cline's system prompt includes a timestamp that may be recomputed per request, invalidating the system-prompt cache.

OnlyTerp/prompt-cache-skills

Build content moderation applications with Azure AI Content Safety SDK for Java.

microsoft/skills

Azure AI Content Safety SDK for Python. An agent skill from microsoft/skills.

microsoft/skills

Azure AI Text Analytics SDK for sentiment analysis, entity recognition, key phrases, language detection, PII, and healthcare NLP.

microsoft/skills

Build image analysis applications with Azure AI Vision SDK for Java.

microsoft/skills

Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping.

microsoft/skills

Azure AI Voice Live SDK for JavaScript/TypeScript. An agent skill from microsoft/skills.

microsoft/skills

Azure AI Search SDK for .NET (Azure.Search.Documents). An agent skill from microsoft/skills.

microsoft/skills

Azure Speech to Text REST API for short audio (Python). An agent skill from microsoft/skills.

microsoft/skills

Build, inspect, prepare, generate and export Overmind datasets in Data Workshop.

overmind-core/overmind

Run work through subagents instead of the main thread. An agent skill from tola-rs/tola-ssg.

tola-rs/tola-ssg

Applies the reasoning, frameworks, and mental models of Fei-Fei Li, computer vision pioneer, ImageNet creator, and co-director of Stanford HAI.

K-Dense-AI/mimeo

Opinionated app components building on top of ./ui primitives

JakeATX/llamAmpere

Specifies how quota-axi reads LLM subscription quota windows, derives pace and runway, computes a selection signal and renders output in TOON, JSON and TUI tiers.

kunchenguid/quota-axi

Run TLX kernel performance benchmarks on Hopper, Blackwell, and AMD (gfx950/CDNA4, gfx1250) GPUs.

facebookexperimental/triton

Work on the actively maintained LangChain v1 agent package: initchatmodel, createagent, structured output, tools, middleware, embeddings initialization, provider routing, and agent runtime…

VectorSpaceLab/AREX-Skill

Patterns and techniques for evaluating and improving AI agent outputs.

github/awesome-copilot

Implement a production SageMaker endpoint with autoscaling, CloudWatch alarms, and tags.

waybarrios/opencode-power-pack

After making a non-obvious architectural decision, solving a novel bug, agreeing on a coding standard, or reaching a conclusion worth remembering, index it back into the knowledge base so the next…

lyonzin/knowledge-rag

Build agentic applications with GitHub Copilot SDK. An agent skill from github/awesome-copilot.

github/awesome-copilot

L3 recipe that runs quark.onnx.AutoSearchPro end-to-end on a user .onnx model: intake → preset selection (or custom search space) → calibration / eval data reader → standalone autosearch script…

amd/Quark

Security-role assignment, user access, application users, business units, and admin self-elevation in Dataverse environments.

microsoft/Dataverse-skills