Attention (attention.com). Use this skill for ANY Attention request — searching and reading data. Whenever a task involves Attention, use this skill instead...

Review computer-vision experiment reproducibility evidence, dataset readiness, metric gates, and launch risk. Use when a user asks for a cautious CV experime...

Fine-tune large language models using DeepSpeed on local or remote GPUs.

Design structured employee training programs with modules, assessments, schedules, and tracking for onboarding, compliance, upskilling, and leadership develo...

Create personalized triathlon, marathon, and ultra-endurance training plans. Use when athletes ask for training plans, workout schedules, race preparation, or coaching advice. Can sync with Strava to analyze training history, or work from manually provided fitness data. Genera…

Run Google Colab notebooks for Python and machine learning with reproducible runtimes, data pipelines, debugging workflows, and experiment discipline.

Execute code on Google Colab GPU runtimes (T4/L4/A100/H100) and manage persistent storage via Google Drive. Use when tasks need GPU compute (ML training, inf...

Complete guide for accessing and managing training data with the intervals.icu API. Use when working with Intervals.icu athlete profiles, activities, workouts, events, wellness data, and training plans. Covers authentication, retrieving activities with combined data fields, ma…

Use this skill when a task involves Knative Serving on Kubernetes, including designing or deploying serverless container workloads, converting Deployments to...

Native agent-to-agent language. Not a translation layer — a shared tongue agents speak natively. Triggers on Lambda syntax like ?Uk/co or !It>Ie. Covers gene...

Call a local llama.cpp server with the LLaVA model to analyze images.

Deploy ML models to production with pipelines, monitoring, serving, and reproducibility best practices.

Transform prototypes into distributable Python packages

Full stack observability - reproducibility, lineage, monitoring, alerting

MLOps project initialization with uv/git/VS Code best practices

Structured Jupyter notebook prototyping with pipeline integrity

Rigorous validation with typing, linting, testing, and security

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library in…

Avoid common PyTorch mistakes — train/eval mode, gradient leaks, device mismatches, and checkpoint gotchas.

Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or in...

Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implemen...

Quantum experiment VISUAL review and Question Answering (VQA) using Vision Language Models (VLM). Analyze experiment RESULT PLOTS to: (1) Describe plot types...

Evidence-based endurance coaching protocol (v11.35). Use when analyzing training data, reviewing sessions, generating pre/post-workout reports, planning work...

Avoid common TensorFlow mistakes — tf.function retracing, GPU memory, data pipeline bottlenecks, and gradient traps.

Full token economy suite for OpenClaw agents. Audits context window usage (skills, history, tool outputs), then applies 5 creative strategies to reduce bloat...

This skill transforms training and onboarding meeting transcripts into structured learning materials, documentation, and actionable review content. Use this skill when processing meeting transcripts from onboarding sessions, training meetings, or knowledge transfer conversatio…

Serverless compute orchestration by Watadot Studio. Manage functions, triggers, and cloud rendering.

Monitor and analyze Weights & Biases training runs. Use when checking training status, detecting failures, analyzing loss curves, comparing runs, or monitoring experiments. Triggers on "wandb", "training runs", "how's training", "did my run finish", "any failures", "check expe…

PDEBench competition workflow orchestration with expflow — three pipeline modes (full/fast/skip), distributed HPO, pruner integration, and ClearML HyperParam...

Use this skill when an installed `intervals` CLI should be used to query Intervals.icu, inspect activities, create scheduled workout events, create workout l...

You are an MLOps engineer with expertise in machine learning pipeline automation, model deployment, experiment tracking, and production ML. Use when: ml pipe...

Run Python code on cloud GPUs using Modal serverless platform. Use when you need A100/T4/A10G GPU access for training ML models. Covers Modal app setup, GPU...

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jo…

Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.

I can turn the scenes you describe into prompts for NovelAI

AI Assistant specializing in machine learning and deep learning.

Use this skill when the user is doing hands-on DOCA Erasure Coding programming on a BlueField DPU, ConnectX NIC, or host — bringing up a doca_ec context, picking among the create / recover / update tasks, choosing matrix type / N / K / block size, querying doca_ec_cap_* before…

Use this skill when the user is doing hands-on NVMe-over-Fabrics storage-target work on a BlueField DPU or ConnectX NIC with DOCA STA — standing up a doca_sta DOCA Core context that accelerates the target-side NVMe-oF data path over RDMA, defining doca_sta_subsystem targets (N…

List the most recently created models on Hugging Face with full metadata (id, author, createdAt, tags, pipeline_tag, library, downloads, likes, gated flag, canonical URL). Filter by pipeline task, library, author/org, or free-text search. Read-only.

Run PyTorch training across GPUs with minimal changes.

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

Embedding database for RAG and semantic search.

Zero-shot image classification and image-text search.

DSPy: declarative LM programs, auto-optimize prompts, RAG.

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).

Fast vector similarity search at billion scale.

Speed up long-sequence transformer training and inference.

Constrain LLM output with grammars; guarantee valid JSON.

HuggingFace hf CLI: search/download/upload models, datasets.

Fast BPE/WordPiece tokenization and custom vocab training.

Structured LLM outputs validated with Pydantic.

On-demand GPU cloud instances for ML training.

llama.cpp local GGUF inference + HF Hub model discovery.

Vision-language chat: VQA, captioning, image dialogue.

Serverless GPU cloud for ML jobs and model APIs.

Curate LLM training data: dedupe, filter, PII redaction.

OBLITERATUS: abliterate LLM refusals (diff-in-means).

Outlines: structured JSON/regex/Pydantic LLM generation.

Fine-tune large LLMs with LoRA on limited GPU memory.

Managed vector DB for production RAG and search.

Fully sharded data-parallel training for large models.

Clean training loops with built-in distributed support.

Vector search engine for production RAG systems.

Train sparse autoencoders to interpret model features.

SAM: zero-shot image segmentation via points, boxes, masks.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Reference-free preference alignment, simpler than DPO.

RL post-training for LLMs with Megatron and SGLang.

Text-to-image generation, inpainting, and img2img.

High-throughput LLM inference on NVIDIA GPUs.

Pretrain LLMs at scale with PyTorch 4D parallelism.

TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

W&B: log ML experiments, sweeps, model registry, dashboards.

Transcribe and translate speech in 99 languages.

Indexed by skills.sh from sharpdeveye/maestro

Indexed by skills.sh from pytorch/pytorch

Indexed by skills.sh from pytorch/pytorch

Indexed by skills.sh from pytorch/pytorch

Indexed by skills.sh from dylantarre/animation-principles

Indexed by skills.sh from aj-geddes/useful-ai-prompts

Indexed by skills.sh from aws/agent-toolkit-for-aws

Indexed by skills.sh from mohitmishra786/low-level-dev-skills

Indexed by skills.sh from pydantic/skills

Indexed by skills.sh from aws/agent-toolkit-for-aws

Indexed by skills.sh from mindrally/skills

Indexed by skills.sh from mohitmishra786/low-level-dev-skills

Indexed by skills.sh from databricks/databricks-agent-skills

Indexed by skills.sh from github/awesome-copilot

Indexed by skills.sh from mindrally/skills

Indexed by skills.sh from davila7/claude-code-templates

Indexed by skills.sh from orchestra-research/ai-research-skills

Indexed by skills.sh from pytorch/pytorch

Indexed by skills.sh from davila7/claude-code-templates

Indexed by skills.sh from everyinc/compound-engineering-plugin

Indexed by skills.sh from davila7/claude-code-templates

Indexed by skills.sh from dylantarre/animation-principles

Indexed by skills.sh from orchestra-research/ai-research-skills

Indexed by skills.sh from orchestra-research/ai-research-skills

Indexed by skills.sh from davila7/claude-code-templates