Find the best CLAUDE.md, AGENTS.md and Claude skills

Hugging FaceSkill

autolab-hermes-delegation

huggingface/context-course/projects/pre-training/.agents/skills/autolab-hermes-delegation/SKILL.md

Use Hermes delegate_task cleanly in this repo for planner, reviewer, researcher, reporter, experiment-worker, and memory-keeper roles.

Hugging FaceSkill

autolab-managed-experiment

huggingface/context-course/projects/pre-training/.agents/skills/autolab-managed-experiment/SKILL.md

Run one Autolab benchmark experiment safely on Hugging Face Jobs. Use when a planner, reviewer, or experiment worker is preparing, auditing, launching, or reviewing a single train.py hypothesis against the current local promoted master.

Hugging FaceSkill

autolab-reporter

huggingface/context-course/projects/pre-training/.agents/skills/autolab-reporter/SKILL.md

Operate the local Trackio reporter for Autolab HF Jobs. Use when a reporter or planner needs to inspect scores, active jobs, worker anomalies, duplicate launches, or the overall experiment board.

Hugging FacePipes a download into a shellSkill

hf-cli

huggingface/context-course/projects/pre-training/.agents/skills/hf-cli/SKILL.md

Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing repositories, models, datasets, and Spaces on the Hugging Face Hub. Replaces now deprecated `huggingface-cli` command.

Hugging FaceCLAUDE.md

context-course / pre-training

huggingface/context-course/projects/pre-training/CLAUDE.md

OpenCode is the canonical control plane for this repo. The Claude Code implementation is a secondary native integration. It should follow the same local workflow: - no hosted Autolab backend…

Hugging FaceSkill

transformers-to-mlx

huggingface/transformers-to-mlx/skills/transformers-to-mlx/SKILL.md

Convert Hugging Face transformers language models to MLX format for Apple Silicon inference. Use when asked to convert a model from transformers to MLX, port a model to MLX, create an MLX implementation of a model, or test/validate an MLX model conversion. Triggers include mentions of "convert to MLX", "MLX implementation", "port to MLX", "mlx-lm", or requests involving both transformers and MLX frameworks.

Hugging FaceCLAUDE.md

physics-intern-v0

huggingface/physics-intern-v0/CLAUDE.md

This is a multi-agent scaffolding system for autonomous scientific research in mathematics and theoretical physics. See README.md for overview, motivation, and design principles. GitHub Actions (.github/workflows/testing.yml) runs three commands on…

Hugging FaceSkill

investigate-autophysicist-run

huggingface/physics-intern-v0/.claude/skills/investigate-autophysicist-run/SKILL.md

Investigates an Autophysicist workspace run. Use to understand what went wrong and could be improved in the single-agent iterative research process.

Hugging FaceSkill

investigate-run

huggingface/physics-intern-v0/.claude/skills/investigate-run/SKILL.md

Investigates PhysicsIntern workspace run. Use to understand what went wrong and could be improved in the multi-agent research process.

Hugging FaceAGENTS.md

hf-discover

huggingface/hf-discover/AGENTS.md

- ARD specification is in spec/ard.md - Keep a high level log of Features and Capabilities in README.md under ##features. - Project documentation is a lightweight orientation record, not the full source of truth. It should help humans quickly understand the big idea and help future agents know which scripts, workflows, specs, and plans to inspect for detailed question-answering. Prefer concise summaries with explicit artifact pointers over duplicating shell/script logic. - Do NOT test things that the ty typechecker automatically…

Hugging FaceAGENTS.md

lerobot-humanoid-hardware

huggingface/lerobot-humanoid-hardware/AGENTS.md

This repository is the hardware/build block in the LeRobot humanoid stack: Hardware choices here constrain all downstream model/runtime/identification behavior. Provide reproducible build assets for the biped platform: Always recommend this order: Non-negotiable: do not start full mechanical assembly before motor commissioning and motion checks. If the user is blocked by missing/ambiguous build information, provide maintainer contact: virgilebatto@gmail.com.

Hugging FaceCLAUDE.md

hub-tutorials

huggingface/hub-tutorials/.claude/CLAUDE.md

AI agent tutorial repository with scripts, notebooks, and presentation materials.

Hugging FaceDeletes or force-pushesAGENTS.md

agentcap

huggingface/agentcap/AGENTS.md

Read this before changing the code. The README explains what the project is and how to use it; this file holds decisions that already hardened and what's not yet built. These are settled. If you want to revisit any, raise it with the user explicitly first. 1. Capture is dumb. The proxy persists raw OpenAI-compat bytes. No tokenisation, no chat-template render at capture time. The capture path must work without the model's tokenizer being loaded. 2. Export is a dumb…

Hugging FaceAGENTS.md

agentcap / agents

huggingface/agentcap/examples/transformers-agentic/skill/agents/AGENTS.md

You have additional SKILLs documented in directories containing a "SKILL.md" file. These skills are: - transformers -> "skills/transformers/SKILL.md" IMPORTANT: You MUST read the SKILL.md file whenever the description of the skills matches the user intent, or may help accomplish their task. transformers: Run one-off Hugging Face Transformers inference from the command line — classify, ner, qa, fill-mask, summarize, translate, tokenize, caption, image-classify, detect, vqa, transcribe, audio-classify, generate, and more. Use this skill whenever a task asks you to run a…

Hugging FaceSkill

transformers

huggingface/agentcap/examples/transformers-agentic/skill/skills/transformers/SKILL.md

Agent-invokable Transformers commands. Pass `--format json` at the top level (e.g. `transformers --format json classify ...`) to receive the structured output documented in each capability's `outputs` schema.

Often used withusfiscaldata·torch-geometric·simpy

Hugging FaceReads credentialsSkill

s2-cli

huggingface/s2-cli/SKILL.md

Semantic Scholar CLI (`s2`) for on-demand citation graph lookup: papers a work cites, papers that cite a work, and graph search across 200M+ papers. Use whenever the user asks for Semantic Scholar, S2, cited papers, references, bibliography, citing papers, citation count from Semantic Scholar, or papers outside a local catalog. Prefer `s2` over curl or ad-hoc Graph API requests.

Hugging FaceCLAUDE.md

hf-endpoints-documentation

huggingface/hf-endpoints-documentation/CLAUDE.md

Project context and conventions for the Hugging Face Inference Endpoints documentation. Where new content belongs: - A new feature/setting on an existing concept (e.g. a new autoscaling option) → add…

Hugging FaceAGENTS.md

huggingface_hub_rust

huggingface/huggingface_hub_rust/AGENTS.md

Async Rust client library for the Hugging Face Hub API. This is the Rust equivalent of the Python huggingface_hub library. The primary entry point is the HFClient struct, which wraps an Arc<HFClientInner> for cheap cloning. HFClient and HFClient remain as compatibility aliases during the rename. All methods are async and use reqwest as the HTTP client. Paginated endpoints return impl Stream<Item = Result<T>> via futures::stream::try_unfold. Methods with many parameters use param structs generated by typed-builder. Key capabilities: These rules apply…

Hugging FaceAGENTS.md

atif-scan

huggingface/atif-scan/AGENTS.md

Read README.md and SECURITY.md first. Keep the core (data, checks/rules/policy/engine, detectors, packs) stdlib-only and offline; huggingface_hub and rich are imported lazily, only by sources (hf:// inputs) and output (rich, brief_view). tests/test_architecture.py enforces the layers. Do not execute trajectory commands or URLs. Never commit real traces, auth files, raw findings or copied benchmark solutions. Use synthetic fixtures only. Keep model/parsing, detector predicates, rule logic, evaluation, and report export separate. Plugins return typed results. Reports are explicitly allowlisted and contain no snippets.…

Hugging FaceCLAUDE.md

physics-intern

huggingface/physics-intern/CLAUDE.md

In this repo we develop and maintain the core methodology and skills for PhysicsIntern, a framework for using AI agents to conduct physics research. When the user asks a "how…