AI & LLM Engineering · For data scientists

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

celestiaorg/docs

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

maxiaosong1124/ncu-cuda-profiling-skill

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

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

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

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

intel/auto-round

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

marin-community/marin

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

samchon/typia

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

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

Design, implement, validate, and calibrate a new eval for the convex-evals suite.

get-convex/convex-evals

Get JSON out of the model reliably. An agent skill from Archive228/loopkit.

Archive228/loopkit

Guides users through selecting, configuring, or creating a PyTorch model for a PINA problem.

PINA-org/PINA

Turn unstructured text into validated, structured variables at corpus scale with LLMs: codebook design, dev/gold-set construction, DSPy prompt optimization, a hard reliability gate (Cohen κ ≥ 0.70)…

joshzyj/open-scholar-skill

How PostHog "canvas" dashboards work end-to-end — the two rendering tiers (json-render vs freeform React-in-iframe), the agent system prompts that steer each, and the RIGHT way to fetch PostHog data…

PostHog/code

Logs and visualizes ML training metrics with Trackio, firing alerts for issues like loss spikes, and syncing a live dashboard to a Hugging Face Space.

huggingface/skills

A skill your agent uses for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search.

timescale/pg-aiguide

Verify a CV-CUDA optimization campaign's deterministic definition-of-done and concise versioned MR summary per .agents/guidance/OPTIMIZATIONGUIDELINES.md.

CVCUDA/CV-CUDA

Test adam's agent builder (platform/) end-to-end — builder form, deploy pipeline, and the deployed eve-style agent page.

michaelshimeles/adam

Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence.

bytedance/deer-flow

Align a MuJoCo MJCF robot model with a URDF source while preserving kinematics, geometry, masses, centers of mass, and inertia tensors.

i2rt-robotics/i2rt

Build a lightweight proactive mode with scheduled checks, sleep intervals, concise user briefs, and expiry safeguards so an agent can work in the background without becoming an uncontrolled daemon.

LearnPrompt/cc-harness-skills

Pick the right SDAF BOM for a target SAP product / release / DB platform / version / kernel / topology.

Azure/sap-automation

Run and extend embodiment-aware GR00T N1.7 post-training workflows from successful robot-policy collection through semantic recording, LeRobot conversion, statistics, fine-tuning, open-loop…

nvidia-isaac/video_to_data

Analyze a job description (pasted text OR a URL) and find the AI/ML/GenAI topics it requires that this learn-ai course does NOT yet cover.

starkyru/learn-ai

Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories.

lllllllama/RigorPilot-Skills

Benchmarks code generation models with the BigCode Evaluation Harness across HumanEval, MBPP, MultiPL-E and other suites using pass@k metrics.

Orchestra-Research/AI-Research-SKILLs

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

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

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

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

lyonzin/knowledge-rag

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

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

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

ZhangShenao/harness9

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

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

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

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

sohu-mptc/FlashRec

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