AI & LLM Engineering · For data scientists

巴逆逆反指標分析。觸發時機：使用者要求追蹤巴逆逆、分析反指標、抓取社群貼文並推送 Telegram 時. An agent skill from cablate/banini-tracker.

cablate/banini-tracker

Adds new custom nodes to the ComfyUI Nix project, including npins fetching, dependency resolution in package.nix, disabling impure pip installs, and verifying the Nix build.

nixified-ai/flake

Reference for all AI tools available in DBX Studio's AI chat system.

Dbxstudio/dbx-studio

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

Develop, optimize, debug, and validate an AReno CUDA, Triton, fused, attention, convolution, routing, or MoE operator.

inclusionAI/AReno

Query AutoRAG-Research pipeline results using natural language.

NomaDamas/AutoRAG-Research

Design, test, create, and attach LangSmith online evaluators for production traces or conversation threads.

langchain-ai/langsmith-skills

Policy for AlbumentationsX transforms that combine multiple images or objects.

albumentations-team/AlbumentationsX

Generate images with FLUX models (Black Forest Labs) via inference.sh CLI.

danielmeppiel/agentic-sdlc-handbook

CodeMie Analytics expert — use this skill whenever the user asks about CodeMie usage data, AI adoption metrics, user leaderboards, CLI insights, spending, LiteLLM costs, token usage, or wants to…

codemie-ai/codemie-code

A skill your agent uses when the user asks to pick a model, subscription, or reasoning effort, or to run router status, usage refresh, or resume a router session.

nidhi-singh02/agent-router

Query images with a local Ollama vision model without loading the image into the main agent context.

gridaco/grida

A skill your agent uses when asked to migrate IsaacLab projects to mjlab, compare IsaacLab and mjlab APIs, import meshes into mjlab tasks, or author new mjlab-native tasks/components directly from…

cmjang/mjlab-skillkit

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

pixeltable/pixeltable

This skill should be used when the user asks to "create an agent instruction", "add agent instructions", "scaffold an agent sample", "create a system prompt sample", "add a system prompt", "create a…

pnp/copilot-prompts

Model Hub — download pre-exported models from Qualcomm AI Hub, run inference on-device, and export them to App Builder as ready-to-import Packs.

qualcomm/qai-appbuilder

Applies Qt Canvas2D (QtCanvas2D / Qt Canvas Painter, Qt 6.12+) best practices when producing or working with Canvas2D QML source code.

TheQtCompanyRnD/agent-skills

Add a new diffusion model (text-to-image, text-to-video, image-to-video, text-to-audio, image editing) to vLLM-Omni, including native non-Diffusers ports, reference-parity validation, Cache-DiT…

vllm-project/vllm-omni

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

Consolidate recent logs, sessions, and existing memory files into durable topic memories, normalize dates, prune stale entries, and keep MEMORY.md short enough for prompt use.

LearnPrompt/cc-harness-skills

Shows how to launch distributed Megatron-LM training on a SLURM cluster: sbatch skeleton, torch.distributed.run setup, CUDA_DEVICE_MAX_CONNECTIONS rules and failure diagnosis.

NVIDIA/Megatron-LM

Refresh GitNexus indexing and regenerate local GitNexus skills when repository status is stale.

ML4ITS/TimeVQVAE

Inspect a PyTorch baseline with torch.compile graphs/code and torch.profiler before drafting a custom kernel, then compare TileLang and PyTorch timelines, forward/backward regions, and allocations.

sablin39/tilelang-cuda-skills

Plans memory headroom, works through out-of-memory failures and watches temperature and power during long ML training jobs on NVIDIA DGX Spark.

wshobson/agents

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

verl-project/verl-omni

交互式测验，将你的 AI/ML 知识映射到 523 节课、20 个阶段的 AI Engineering from Scratch 课程起点。

fancyboi999/ai-engineering-from-scratch-zh

Audit TSZ repo iteration speed and quality. An agent skill from tsz-org/tsz.

tsz-org/tsz

Explore, construct, and speak with identities in an LLM's latent space using YouSim's simulator prompts and its /locate /summon /speak /steer /request command grammar.

plastic-labs/yousim

A skill your agent uses when a user asks how many tokens (or how much context/cost) ContextPilot has saved, or wants a ContextPilot savings status/summary inside Hermes Agent — e.g.

EfficientContext/ContextPilot

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.

chengzhongwei/Prompt-sensei

Open OwnMem Console, the local dashboard for this repository's memory.

grpcer/ownmem

Audit imaging acquisition, reconstruction, series eligibility, quantitative transforms and protocol drift; not model training.

huang-sir1/radiology-skills

DeepSeek API 助手 - 编程辅助、模型选择、API调用指南、定价信息. An agent skill from dongsheng123132/u-claw.

dongsheng123132/u-claw

A skill your agent uses when implementing any endpoint, form handler, CLI tool, or function that accepts external input.

aiming-lab/MetaClaw

Keeps the engagement record for client work. An agent skill from suboss87/FDEOps.

suboss87/FDEOps

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Orchestra-Research/AI-Research-SKILLs

Turns a natural-language description of routing intent into a valid Lemonade collection.router policy JSON.

amd/skills

Review a proposed Agent Skill for structural validity and content quality before publishing.

mongodb/agent-skills

Mine AI coding-agent session transcripts into structured, gate-validated GPU-kernel optimization records for the wiki.

alibaba/atrex-kernel-agent

Create, build, validate, and upload a Packs SDK agent (pack.ts using sdk.newAgent()) to your Coda/Superhuman account, including registering an API token, wiring up tools…

coda/packs-sdk

Capture a Nsight Systems (.nsys-rep) profile of a short PithTrain run for performance analysis.

mlc-ai/pith-train

Create original, material-reference-driven, consistent, photorealistic character casting sheets for commercial, advertising, cinematic, model, occupational, everyday, historical…

dacnay816y62-hub/character-casting-studio-skill

Profile CUDA kernels with Nsight Compute on B200 / sm100. An agent skill from mit-han-lab/ncu-report-skill.

mit-han-lab/ncu-report-skill

A skill your agent uses when adding a new optimized kernel or operator to veomni/ops/.

ByteDance-Seed/VeOmni

Build DSPy 3.2.x programs through spec, program, metric and baseline; extend to optimization and export when requested and justified by task budget.

intertwine/dspy-agent-skills

Audit and improve the prompt surface of Avibe Agents across backends (Claude, Codex/GPT, OpenCode) — global and project rules, Agent system prompts, Skills, delegation briefs, and Task and Watch…

avibe-bot/avibe

Designs clear, testable prompts for agent workflows. An agent skill from repowise-dev/claude-code-prompts.

repowise-dev/claude-code-prompts

Triage and repair hipfire runtime failures such as daemon hangs, stale serve.pid, port 11435 conflicts, ROCm include-path problems, missing precompiled kernels, VRAM OOM, kernel JIT failures, and…

warpfront/hipfire