HuggingFace Best Model Finder

HuggingFace Best Model Finder is an AI Engineering skill for Claude Code, published by waybarrios in opencode-power-pack.

482 stars39 forkson waybarrios/opencode-power-packAdded 2026/08/26+2% in starsRepository updated 2026/08/24

View source on GitHub Download repo ZIP

ai-agentsanthropicclaude-codecode-reviewcodexcodex-clideveloper-toolsgradiohuggingfacellm-toolsmachine-learningml-trainingopenai-codexopencodepipi-coding-agentpi-packagepluginsecurity-auditskills

Install in seconds

Install HuggingFace Best Model Finder

Copy HuggingFace Best Model Finder into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/waybarrios/opencode-power-pack/tree/main/skills/huggingface-best ~/.claude/skills/huggingface-best

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/waybarrios/opencode-power-pack.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/huggingface-best/SKILL.md in waybarrios/opencode-power-pack
Installs to: ~/.claude/skills/huggingface-best
Collection: One of 25 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What HuggingFace Best Model Finder does

HuggingFace Best Model Finder finds recommended Hugging Face models for a task by checking official benchmark leaderboards and model size. It helps when you need to compare candidates against device constraints or choose a top model to try.

HuggingFace Best Model Finder is cataloged under AI Engineering on DirSkills. HuggingFace Best Model Finder comes from a repository tagged ai-agents, anthropic, claude-code, code-review and codex.

Documentation

README

Excerpt

HuggingFace Best Model Finder

Finds the best models for a task by querying official HF benchmark leaderboards, enriching results with model size data, filtering for what fits on the user's device, and returning a comparison table with benchmark scores.

Step 1: Parse the request

Extract from the user's message:

Task: what they want the model to do (coding, math/reasoning, chat, OCR, RAG/retrieval, speech recognition, image classification, multimodal, agents, etc.)
Device: hardware constraints (MacBook M-series 8/16/32/64GB unified memory, RTX GPU with VRAM amount, CPU-only, cloud/no constraint, etc.)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about HuggingFace Best Model Finder

What else does waybarrios publish alongside HuggingFace Best Model Finder?
HuggingFace Best Model Finder is one of 25 skills that DirSkills catalogs from waybarrios/opencode-power-pack, the repository it ships in. Its siblings there include AI Slop Rubric, AWS Context Discovery and Agentic Actions Auditor. Each one is a separate skill with its own page in this directory, installs the same way HuggingFace Best Model Finder does, and is maintained by waybarrios in that same repository. The rest of the collection is listed on the waybarrios/opencode-power-pack page.
How does HuggingFace Best Model Finder compare to other AI Engineering skills?
HuggingFace Best Model Finder ranks #2206 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of HuggingFace Best Model Finder against them. Open each page to compare what they document and how they install.