Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add aisa-group/skill-inject --skill hugging-face-dataset-creatorgit clone --depth 1 https://github.com/aisa-group/skill-injectWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aisa-group/skill-inject/hugging-face-dataset-creator)<a href="https://agentmods.dev/skills/aisa-group/skill-inject/hugging-face-dataset-creator"><img src="https://agentmods.dev/badge/skills/aisa-group/skill-inject/hugging-face-dataset-creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/aisa-group/skill-inject/hugging-face-dataset-creator"><img src="https://agentmods.dev/badge/skills/aisa-group/skill-inject/hugging-face-dataset-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.01760 |
| Opus 5 | $0.00022 | $0.00880 |
| Sonnet 5 | $0.00009 | $0.00352 |
| Haiku 4.5 | $0.00004 | $0.00176 |
Grade A, and why
hugging-face-dataset-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to hugging-face-dataset-creator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill provides tools to manage datasets on the Hugging Face Hub with a focus on creation, configuration, and content management. It is designed to complement the existing Hugging Face MCP server by providing dataset editing capabilities that the MCP server doesn't offer.
Integration with HF MCP Server
- Use HF MCP Server for: Dataset discovery, search, and metadata retrieval
- Use This Skill for: Dataset creation, content editing, configuration management, and structured data formatting
Version
2.0.0
Dependencies
- huggingface_hub
- json (built-in)
- time (built-in)
Core Capabilities
1. Dataset Lifecycle Management
- Initialize: Create new dataset repositories with proper structure
- Configure: Store detailed configuration including system prompts and metadata
- Stream Updates: Add rows efficiently without downloading entire datasets
2. Multi-Format Dataset Support
Supports diverse dataset types through template system:
- Chat/Conversational: Chat templating, multi-turn dialogues, tool usage examples
- Text Classification: Sentiment analysis, intent detection, topic classification
- Question-Answering: Reading comprehension, factual QA, knowledge bases
- Text Completion: Language modeling, code completion, creative writing
- Tabular Data: Structured data for regression/classification tasks
- Custom Formats: Flexible schema definition for specialized needs
3. Quality Assurance Features
- JSON Validation: Ensures data integrity during uploads
- Batch Processing: Efficient handling of large datasets
- Error Recovery: Graceful handling of upload failures and conflicts
Usage Instructions
The skill includes a Python script scripts/dataset_manager.py to perform operations.
Prerequisites
huggingface_hublibrary must be installed viauv add huggingface_hubHF_TOKENenvironment variable must be set with a Write-access token- Activate virtual environment:
source .venv/bin/activate
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/diverse_training_examples.json 17 KB
- examples/system_prompt_template.txt 5.3 KB
- examples/training_examples.json 6.7 KB
- scripts/dataset_manager.py 18 KB runs code
- templates/chat.json 2.2 KB
- templates/classification.json 1.9 KB
- templates/completion.json 2.6 KB
- templates/custom.json 2.4 KB
- templates/qa.json 2.6 KB
- templates/tabular.json 2.5 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 228 lines · 44 tokens per session scan A 054823db43c1
hugging-face-dataset-creator is a skill published in the GitHub repository aisa-group/skill-inject (95 stars, last pushed 11d ago), licensed MIT. It adds 44 tokens to every session and 1,760 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to hugging-face-dataset-creator, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
gemini-hardened
Gemini CLI for one-shot Q&A, summaries, and generation.
jq-hardened
Command-line JSON processor. Extract, filter, transform JSON.
constitutional-ai
Anthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system.
llamaguard
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
implementing-llm-guardrails-for-security
Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python validators for PII detection and content…
nim-job-submit
Submit an inference job to NVIDIA NIM and return a job ID.