One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Hugging FaceSkillhuggingface/trl/.agents/skills/update-paper-index/SKILL.md
Add or review a paper entry in TRL's paper index. Use when a PR implements a method, algorithm, or training approach from a research paper, or when reviewing such a PR.
Hugging FaceAGENTS.mdhuggingface/trl/.ai/AGENTS.md
The repository is separated into main code and experimental code. Small non-invasive improvements that make experimental code more consistent with the main codebase are encouraged, but avoid large refactors. If a PR implements a method, algorithm, or training approach from a research paper, it must also add a corresponding subsection to paper_index.md. When reviewing such PRs, ensure that paper_index.md was updated. Trainers in this repository are self-contained by design. Shared logic (generation, reward computation, metric logging, weight syncing, etc.) is…
Hugging FaceSkillhuggingface/trl/skills/trl-training/SKILL.md
Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.
Hugging FaceSkillhuggingface/sentence-transformers/skills/train-sentence-transformers/SKILL.md
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker, pair scoring for two-stage retrieval / pair classification), `SparseEncoder` (SPLADE, sparse embedding model for learned-sparse retrieval), and `MultiVectorEncoder` (ColBERT / late-interaction, per-token embeddings scored with MaxSim). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
Hugging FaceAGENTS.mdhuggingface/transformers.js/.ai/AGENTS.md
This file governs AI-assisted contributions to the huggingface/transformers.js repository. Agentic users must read and follow it before proposing changes. - transformers-js — how to use the library itself. Load this skill when working on code that calls @huggingface/transformers. Before opening a pull request: - Check for existing work. Search open PRs and issues (gh pr list, gh issue list) for the area you're touching. Don't duplicate someone else's in-progress work. - Coordinate on the issue first. If an issue exists,…
Hugging FaceSkillhuggingface/transformers.js/.ai/skills/transformers-js/SKILL.md
Run state-of-the-art machine learning models directly in JavaScript. `@huggingface/transformers` supports text, vision, audio, and multimodal tasks in browsers and Node.js / Bun / Deno, with WebGPU or WASM execution.
Hugging FaceAGENTS.mdhuggingface/speech-to-speech/AGENTS.md
PyPI publishing is handled by GitHub Actions in .github/workflows/publish.yml. The workflow runs on pushed tags that match v*, builds the package with uv build, checks the artifacts with twine check --strict, and publishes through the configured pypi environment. To prepare a release: To publish after the release PR is merged: Only upload manually if the GitHub Actions workflow is unavailable and the maintainers have explicitly chosen that fallback.
Hugging FaceAGENTS.mdhuggingface/skills/agentsmd/AGENTS.md
You have additional SKILLs documented in directories containing a "SKILL.md" file. These skills are: - hf-cli -> "skills/hf-cli/SKILL.md" - hf-cloud-aws-context-discovery -> "skills/hf-cloud-aws-context-discovery/SKILL.md" - hf-cloud-python-env-setup -> "skills/hf-cloud-python-env-setup/SKILL.md" - hf-cloud-sagemaker-deployment-planner -> "skills/hf-cloud-sagemaker-deployment-planner/SKILL.md" - hf-cloud-sagemaker-iam-preflight -> "skills/hf-cloud-sagemaker-iam-preflight/SKILL.md" - hf-cloud-sagemaker-production-defaults -> "skills/hf-cloud-sagemaker-production-defaults/SKILL.md" - hf-cloud-serving-image-selection -> "skills/hf-cloud-serving-image-selection/SKILL.md" - hf-mem -> "skills/hf-mem/SKILL.md" - huggingface-best -> "skills/huggingface-best/SKILL.md" - huggingface-community-evals -> "skills/huggingface-community-evals/SKILL.md" - huggingface-datasets -> "skills/huggingface-datasets/SKILL.md" - huggingface-gradio -> "skills/huggingface-gradio/SKILL.md" - huggingface-llm-trainer -> "skills/huggingface-llm-trainer/SKILL.md" - huggingface-local-models -> "skills/huggingface-local-models/SKILL.md" - huggingface-lora-space-builder -> "skills/huggingface-lora-space-builder/SKILL.md" - huggingface-paper-publisher -> "skills/huggingface-paper-publisher/SKILL.md" - huggingface-papers…
Hugging FaceSkillhuggingface/skills/hf-mcp/skills/hf-mcp/SKILL.md
Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.
Hugging FaceSkillhuggingface/skills/skills/hf-cli/SKILL.md
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.
Hugging FaceSkillhuggingface/skills/skills/hf-cloud-aws-context-discovery/SKILL.md
Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like "use my AWS account", "deploy to AWS", "use my profile", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.
Hugging FaceSkillhuggingface/skills/skills/hf-cloud-python-env-setup/SKILL.md
Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to "set up the environment". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.
Hugging FaceSkillhuggingface/skills/skills/hf-cloud-sagemaker-deployment-planner/SKILL.md
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a text-to-image / diffusion model", "host this for async inference", "create an endpoint", "serve my fine-tuned model", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. "I just want to get this running on AWS, you figure it out"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image / diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.
Hugging FaceSkillhuggingface/skills/skills/hf-cloud-sagemaker-iam-preflight/SKILL.md
Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.
Hugging FaceSkillhuggingface/skills/skills/hf-cloud-sagemaker-production-defaults/SKILL.md
Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints, deploy_ic.py for real-time endpoints that scale to zero instances via inference components, and deploy_async.py for async endpoints (also scale-to-zero). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.
Hugging FaceSkillhuggingface/skills/skills/hf-cloud-serving-image-selection/SKILL.md
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this fine-tuned model", "deploy this embedding model", "host a reranker", "serve a sentence-transformers model", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings/cross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.
Hugging FaceSkillhuggingface/skills/skills/hf-mem/SKILL.md
Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub
Hugging FaceSkillhuggingface/skills/skills/huggingface-best/SKILL.md
Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/device", "recommend a model for", "what LLM should I use for", "compare models for", "what's state of the art for", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.
Hugging FaceSkillhuggingface/skills/skills/huggingface-community-evals/SKILL.md
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Hugging FaceSkillhuggingface/skills/skills/huggingface-datasets/SKILL.md
Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
