hugging-face-evaluation Skill
Add evaluation results to Hugging Face model repositories using the .evalresults/ format. Uses HF CLI for PR management and manual YAML creation. Published by huggingface in community-evals.
What is hugging-face-evaluation Skill?
Add evaluation results to Hugging Face model repositories using the .evalresults/ format. Uses HF CLI for PR management and manual YAML creation. Published by huggingface in community-evals. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Data analysis
- Data analysis use cases
Technical details
- Install or run with Copy skill directory
When to use hugging-face-evaluation Skill
- Use it for data analysis.
Built with
Editorial notes
Source
- Creator: huggingface
- Repository: huggingface/community-evals
- Skill file: .claude/skills/hugging-face-evaluation/SKILL.md
What it does
Add evaluation results to Hugging Face model repositories using the .evalresults/ format. Uses HF CLI for PR management and manual YAML creation.
Skill instructions
Overview This skill adds structured evaluation results to HuggingFace model repositories using the .evalresults/ format. What This Enables: - Results appear on model pages with benchmark links - Scores are aggregated into benchmark dataset leaderboards - Community contributions via Pull Requests Important Evaluation PRs can only be opened on the Hugging Face Hub. They cannot be opened on the GitHub repository. Version 3.0.0 Workflow Overview The actual workflow uses: 1. HF CLI (hf upload, hf download) for PR operations 2. Manual YAML creation in /tmp/pr-reviews/ 3. checkprs.py script to check for existing PRs 4. curl to fetch model cards and leaderboard data See references/hfcliforprs.md for detailed CLI instructions. --- CRITICAL: Multiple Scores for One Benchmark Models can have multiple scores for the same benchmark (with/without tools). Each variant MUST be in a separate file. File Naming Convention | Condition | File Name | Notes Field | |-----------|-----------|-------------| | D
Explore related resources
Frequently asked questions
What is hugging-face-evaluation?
hugging-face-evaluation is a open-source AI agent skill with Copy skill directory. Add evaluation results to Hugging Face model repositories using the .evalresults/ format. Uses HF CLI for PR management and manual YAML creation.
Who is hugging-face-evaluation best for?
hugging-face-evaluation is best for reusing agent instructions, scripts, and references, data analysis workflows.
How do I install hugging-face-evaluation?
Install or run hugging-face-evaluation using Copy skill directory. Check hugging-face-evaluation for the latest setup command.
Is hugging-face-evaluation actively maintained?
hugging-face-evaluation may need a closer maintenance check before production use.
Auto-fetched from GitHub.
