Skip to content

Commit 0499fae

Browse files
snowmeadclaude
snowmead
and
claude
committed
Add Claude Code plugin marketplace support
Enable Claude Code users to install Hugging Face skills directly via the plugin marketplace system. Changes: - Add .claude-plugin/marketplace.json for marketplace registration - Add plugin.json manifests to each plugin for strict mode validation - Restructure to follow Claude Code's recommended skill directory layout: plugin-name/ ├── plugin.json └── skills/ └── skill-name/ ├── SKILL.md ├── scripts/ ├── references/ └── templates/ Users can now install via: /plugin marketplace add huggingface/skills /plugin install model-trainer 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <[email protected]>
1 parent a93950b commit 0499fae

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

50 files changed

+105
-0
lines changed

‎.claude-plugin/marketplace.json‎

Lines changed: 32 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,32 @@
1+
{
2+
"name": "huggingface-skills",
3+
"owner": {
4+
"name": "Hugging Face"
5+
},
6+
"metadata": {
7+
"description": "Agent Context Protocol (ACP) skills for AI/ML tasks including dataset creation, model training, evaluation, and research paper publishing on Hugging Face Hub",
8+
"version": "1.0.0"
9+
},
10+
"plugins": [
11+
{
12+
"name": "model-trainer",
13+
"source": "./hf-llm-trainer",
14+
"description": "This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup."
15+
},
16+
{
17+
"name": "hugging-face-paper-publisher",
18+
"source": "./hf-paper-publisher",
19+
"description": "Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles."
20+
},
21+
{
22+
"name": "hugging-face-dataset-creator",
23+
"source": "./hf_dataset_creator",
24+
"description": "Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows."
25+
},
26+
{
27+
"name": "hugging-face-evaluation-manager",
28+
"source": "./hf_model_evaluation",
29+
"description": "Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content and importing scores from Artificial Analysis API. Works with the model-index metadata format."
30+
}
31+
]
32+
}

‎hf-llm-trainer/plugin.json‎

Lines changed: 21 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
{
2+
"name": "model-trainer",
3+
"version": "1.0.0",
4+
"description": "Train and fine-tune language models using TRL on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling, plus GGUF conversion for local deployment.",
5+
"author": {
6+
"name": "Hugging Face"
7+
},
8+
"repository": "https://github.com/huggingface/skills",
9+
"license": "Apache-2.0",
10+
"keywords": [
11+
"huggingface",
12+
"trl",
13+
"training",
14+
"fine-tuning",
15+
"llm",
16+
"sft",
17+
"dpo",
18+
"grpo",
19+
"gguf"
20+
]
21+
}

hf-llm-trainer/SKILL.md renamed to hf-llm-trainer/skills/model-trainer/SKILL.md

hf-llm-trainer/references/gguf_conversion.md renamed to hf-llm-trainer/skills/model-trainer/references/gguf_conversion.md

hf-llm-trainer/references/hardware_guide.md renamed to hf-llm-trainer/skills/model-trainer/references/hardware_guide.md

hf-llm-trainer/references/hub_saving.md renamed to hf-llm-trainer/skills/model-trainer/references/hub_saving.md

hf-llm-trainer/references/reliability_principles.md renamed to hf-llm-trainer/skills/model-trainer/references/reliability_principles.md

hf-llm-trainer/references/trackio_guide.md renamed to hf-llm-trainer/skills/model-trainer/references/trackio_guide.md

hf-llm-trainer/references/training_methods.md renamed to hf-llm-trainer/skills/model-trainer/references/training_methods.md

hf-llm-trainer/references/training_patterns.md renamed to hf-llm-trainer/skills/model-trainer/references/training_patterns.md

0 commit comments

Comments
 (0)