Skip to main content
affpapa.org
RU EN
skill CX Codex

transformers — Claude Code skill: Hugging Face models and training

A skill that walks your agent through Hugging Face Transformers: pulling checkpoints from the Hub, running pipeline inference, generating text and fine-tuning with Trainer.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add K-Dense-AI/scientific-agent-skills --skill transformers -a claude-code
Open on GitHub

What transformers does

The skill covers Transformers 5.18.0 and gives the agent a reference for loading Hub checkpoints, quick inference through pipeline, text generation with decoding controls, and fine-tuning on custom data via Trainer and TrainingArguments. It spans NLP, vision, audio and multimodal work.

Check your setup first. Python 3.10+, PyTorch 2.5+ and network access for Hub downloads are required. Keep the stack in its own environment: the pinned set is transformers[torch]==5.18.0, torch==2.14.1, datasets==5.0.1, accelerate==1.15.0, peft==0.21.2. Bumping packages one at a time breaks the combination — Datasets 5.0.1 needs Hub below 2, so a newer Hub makes the training stack unsatisfiable. Audio preprocessing pulls in librosa 1.0.0, which needs Python 3.12+.

Gated and private checkpoints need a Hugging Face token, either through hf auth login or the HF_TOKEN variable. Pick the narrowest scope that works: read for downloads, write only when you upload. Version 5 dropped the TensorFlow and JAX backends, and several pipeline tasks such as summarization and question-answering are gone — those need direct task models instead.

What it helps with

  • load a checkpoint from the Hugging Face Hub and run inference
  • build a text or image classification pipeline
  • tune text generation with temperature, top-k and top-p
  • fine-tune a model on a custom dataset with Trainer
  • figure out which PyTorch and datasets versions fit together

Example prompts for the agent

  • Load Qwen/Qwen2.5-1.5B and generate a continuation for my prompt
  • Set up a sentiment classification pipeline with distilbert-base-uncased-finetuned-sst-2-english
  • Configure TrainingArguments and fine-tune the model on my dataset

How to install transformers

1Skills CLI (Vercel)

npx skills add K-Dense-AI/scientific-agent-skills --skill transformers -a claude-code

2Manually: put the files in place

~/.claude/skills/transformers/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/transformers/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about transformers

How do I install transformers in Claude Code?

Run npx skills add K-Dense-AI/scientific-agent-skills --skill transformers -a claude-code. The skill lands in ~/.claude/skills/transformers/SKILL.md.

What does the transformers skill do?

It guides the agent through Hugging Face Transformers: loading Hub models, pipeline inference, text generation and Trainer fine-tuning.

What do I need before using it?

Python 3.10+, PyTorch 2.5+ and network access to download models. Gated checkpoints also need a Hugging Face token via hf auth login or HF_TOKEN.

Similar skills

Everything for AI and ML →
skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. CX Codex +1 1,100,000installs mcp-builder official anthropics This skill walks through building an MCP server in TypeScript or Python, from reading the protocol spec to writing tests and evaluation questions. 130,949installs subagent-driven-development Jesse Vincent This skill runs an implementation plan through fresh subagents for independent tasks and reviews each result. Use it for multi-step work in one session. CX Codex 237,746installs orchestration stablyai Coordinates supervised Orca workers with task DAGs, decision gates, and threaded messages. Fits workflows that split work across multiple agents. CX Codex +1 349,800installs

From the same set159

infographics Turns your data into a PNG infographic through Nano Banana 2, then scores the result against a quality threshold. Handy when a report needs a picture instead of another table. CX Codex +1 2,000installs dask A skill that teaches the agent to use Dask for DataFrames, arrays and tasks that outgrow RAM or run across a cluster. CX Codex +1 2,000installs shap Guides AI agents in explaining and auditing machine learning predictions with SHAP. Useful for selecting explainers, checking additivity, and rendering attribution plots. CX Codex +1 2,000installs pyzotero Manages Zotero libraries through the pyzotero Python client: search references, edit records, handle collections, tags, and attachments. Use it for bibliography automation. CX Codex +1 2,000installs generate-image Generates and edits images via OpenRouter Image API using Gemini, Recraft, and Seedream. Ideal for artwork, logos, concept art, and editing reference images. CX Codex +1 2,000installs networkx Build, analyse and visualise Python graphs with NetworkX. Use it for routes, centrality, communities and graph file formats. CX Codex +1 2,000installs sympy Skill for exact symbolic computation: algebra, differential equations, matrices, physics. When you need √2 exactly instead of 1.414, not numerical approximations. CX Codex +1 2,000installs pytorch-lightning Guides agents through structuring PyTorch Lightning 2.6.6 code, from LightningModules to distributed trainers. Useful when scaling training across GPUs. CX Codex +1 2,000installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor