huggingface/skills
Give your agents the power of the Hugging Face ecosystem
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ claude mcp add --transport http huggingface-skills 'https://huggingface.co/mcp?login' $ npx degit huggingface/skills/skills ./rig-skills/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ claude mcp add --transport http huggingface-skills 'https://huggingface.co/mcp?login' $ npx degit huggingface/skills/hf-mcp/skills/hf-mcp .claude/skills/hf-mcp $ npx degit huggingface/skills/skills/hf-cli .claude/skills/hf-cli $ npx degit huggingface/skills/skills/hf-cloud-aws-context-discovery .claude/skills/hf-cloud-aws-context-discovery $ npx degit huggingface/skills/skills/hf-cloud-python-env-setup .claude/skills/hf-cloud-python-env-setup $ npx degit huggingface/skills/skills/hf-cloud-sagemaker-deployment-planner .claude/skills/hf-cloud-sagemaker-deployment-planner $ npx degit huggingface/skills/skills/hf-cloud-sagemaker-iam-preflight .claude/skills/hf-cloud-sagemaker-iam-preflight $ npx degit huggingface/skills/skills/hf-cloud-sagemaker-production-defaults .claude/skills/hf-cloud-sagemaker-production-defaults $ npx degit huggingface/skills/skills/hf-cloud-serving-image-selection .claude/skills/hf-cloud-serving-image-selection $ npx degit huggingface/skills/skills/hf-mem .claude/skills/hf-mem $ npx degit huggingface/skills/skills/huggingface-best .claude/skills/huggingface-best $ npx degit huggingface/skills/skills/huggingface-community-evals .claude/skills/huggingface-community-evals $ npx degit huggingface/skills/skills/huggingface-datasets .claude/skills/huggingface-datasets $ npx degit huggingface/skills/skills/huggingface-gradio .claude/skills/huggingface-gradio $ npx degit huggingface/skills/skills/huggingface-llm-trainer .claude/skills/huggingface-llm-trainer $ npx degit huggingface/skills/skills/huggingface-local-models .claude/skills/huggingface-local-models $ npx degit huggingface/skills/skills/huggingface-lora-space-builder .claude/skills/huggingface-lora-space-builder $ npx degit huggingface/skills/skills/huggingface-paper-publisher .claude/skills/huggingface-paper-publisher $ npx degit huggingface/skills/skills/huggingface-papers .claude/skills/huggingface-papers $ npx degit huggingface/skills/skills/huggingface-spaces .claude/skills/huggingface-spaces $ npx degit huggingface/skills/skills/huggingface-tool-builder .claude/skills/huggingface-tool-builder $ npx degit huggingface/skills/skills/huggingface-trackio .claude/skills/huggingface-trackio $ npx degit huggingface/skills/skills/huggingface-vision-trainer .claude/skills/huggingface-vision-trainer $ npx degit huggingface/skills/skills/huggingface-zerogpu .claude/skills/huggingface-zerogpu $ npx degit huggingface/skills/skills/train-sentence-transformers .claude/skills/train-sentence-transformers $ npx degit huggingface/skills/skills/transformers-js .claude/skills/transformers-js $ npx degit huggingface/skills/skills/trl-training .claude/skills/trl-training
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} MCP servers (1)
| server | source | est. tokens |
|---|---|---|
| huggingface.co · "huggingface-skills" | remote · remote | 2.5k |
Skills (26)
hf-mcphf-clihf-cloud-aws-context-discoveryhf-cloud-python-env-setuphf-cloud-sagemaker-deployment-plannerhf-cloud-sagemaker-iam-preflighthf-cloud-sagemaker-production-defaultshf-cloud-serving-image-selectionhf-memhuggingface-besthuggingface-community-evalshuggingface-datasetshuggingface-gradiohuggingface-llm-trainerhuggingface-local-modelshuggingface-lora-space-builderhuggingface-paper-publisherhuggingface-papershuggingface-spaceshuggingface-tool-builderhuggingface-trackiohuggingface-vision-trainerhuggingface-zerogputrain-sentence-transformerstransformers-jstrl-training
Similar rigs
waybarrios/opencode-power-pack
54 rigorous skills for Codex, OpenCode, and Pi: code review, security audit, feature development, frontend design, MCP tools, Hugging Face ML/training, and more.
Skill Collector 3.9k tok ·
Harmitx7/tribunal-kit
A universal, native-Rust governance layer for AI coding agents. Enforces Subagent-Driven Development (SDD) to stop hallucinations before they hit disk.
Skill Collector 9.9k tok ·
CharlesGuooo/ai-agent-config-sync
Cross-device sync for Claude Code, Codex, OpenCode configs
MCP Hoarder 92.0k tok ·
abhinand5/pi-setup
Personal Pi coding agent setup
Skill Collector 762 tok ·