How do I install the Hf Init skill?

Run npx skillmds@latest add richfrem/hf-init-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hf Init safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hf Init?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hf Init free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hf Init?

richfrem (@richfrem) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hf Init by richfrem — Agent Skill

Name: Hf Init
Author: richfrem

Hf Init

Initialize HuggingFace integration - validates .env variables, tests API connectivity, and ensures the dataset repository structure exists. Use when onboarding a new project to HuggingFace or when credentials change.

richfrem 26d5017 6 files · 13.9 KB Updated Sep 17, 2026

File contents

HuggingFace Init (Onboarding)

Status: Active Author: Richard Fremmerlid Domain: HuggingFace Integration

Purpose

Sets up everything needed for HuggingFace persistence. Run this once when onboarding a new project, or whenever credentials change.

What It Does

Validates required .env variables are set
Tests API connectivity with the configured token
Ensures the dataset repository exists on HF Hub
Creates the standard folder structure (lineage/, data/, metadata/)
Uploads the dataset card (README.md) with configurable discovery tags

Required Environment Variables

Variable	Required	Description
`HUGGING_FACE_USERNAME`	✅ Yes	Your HF username
`HUGGING_FACE_TOKEN`	✅ Yes	API token (set in `~/.zshrc`, NOT `.env`)
`HUGGING_FACE_REPO`	✅ Yes	Model repo name
`HUGGING_FACE_DATASET_PATH`	✅ Yes	Dataset repo name
`HUGGING_FACE_TAGS`	❌ No	Comma-separated discovery tags for dataset card
`HUGGING_FACE_PROJECT_NAME`	❌ No	Pretty name for dataset card heading
`SOUL_VALENCE_THRESHOLD`	❌ No	Moral/emotional charge filter (default: `-0.7`)

Usage

Validate Config

python ./scripts/hf_config.py

Full Init (Validate + Create Structure + Dataset Card)

python ./scripts/hf_init.py

Validate Only (No Changes)

python ./scripts/hf_init.py --validate-only

Quick Setup

# Token goes in shell profile (never committed):
export HUGGING_FACE_TOKEN=hf_xxxxxxxxxxxxx

# Project vars go in .env:
HUGGING_FACE_USERNAME=<your-username>
HUGGING_FACE_REPO=<your-model-repo>
HUGGING_FACE_DATASET_PATH=<your-dataset-repo>

# Optional customization:
HUGGING_FACE_TAGS=reasoning-traces,cognitive-continuity,your-project-tag
HUGGING_FACE_PROJECT_NAME=My Project Soul

# Run init
python ./scripts/hf_init.py

---name: hf-init-2description: Initialize HuggingFace integration - validates .env variables, tests API connectivity, and ensures the dataset repository structure exists. Use when onboarding a new project to HuggingFace or when credentials change.---# HuggingFace Init (Onboarding)**Status:** Active**Author:** Richard Fremmerlid**Domain:** HuggingFace Integration## PurposeSets up everything needed for HuggingFace persistence. Run this once whenonboarding a new project, or whenever credentials change.## What It Does1. **Validates** required `.env` variables are set2. **Tests** API connectivity with the configured token3. **Ensures** the dataset repository exists on HF Hub4. **Creates** the standard folder structure (`lineage/`, `data/`, `metadata/`)5. **Uploads** the dataset card (README.md) with configurable discovery tags## Required Environment Variables| Variable | Required | Description ||:---------|:---------|:------------|| `HUGGING_FACE_USERNAME` | ✅ Yes | Your HF username || `HUGGING_FACE_TOKEN` | ✅ Yes | API token (set in `~/.zshrc`, NOT `.env`) || `HUGGING_FACE_REPO` | ✅ Yes | Model repo name || `HUGGING_FACE_DATASET_PATH` | ✅ Yes | Dataset repo name || `HUGGING_FACE_TAGS` | ❌ No | Comma-separated discovery tags for dataset card || `HUGGING_FACE_PROJECT_NAME` | ❌ No | Pretty name for dataset card heading || `SOUL_VALENCE_THRESHOLD` | ❌ No | Moral/emotional charge filter (default: `-0.7`) |## Usage### Validate Config```bashpython ./scripts/hf_config.py```### Full Init (Validate + Create Structure + Dataset Card)```bashpython ./scripts/hf_init.py```### Validate Only (No Changes)```bashpython ./scripts/hf_init.py --validate-only```## Quick Setup```bash# Token goes in shell profile (never committed):export HUGGING_FACE_TOKEN=hf_xxxxxxxxxxxxx# Project vars go in .env:HUGGING_FACE_USERNAME=<your-username>HUGGING_FACE_REPO=<your-model-repo>HUGGING_FACE_DATASET_PATH=<your-dataset-repo># Optional customization:HUGGING_FACE_TAGS=reasoning-traces,cognitive-continuity,your-project-tagHUGGING_FACE_PROJECT_NAME=My Project Soul# Run initpython ./scripts/hf_init.py```

Frequently asked questions