← All skills
hugging-face-evaluation
82 / 100 · Low risk
Fine to try.
By kursku/skills (GitHub) · marketing · 128 stars · scanned at commit 346c313
Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README.
Found in 28 places.
Show 17 more
- packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 158
uv run scripts/evaluation_manager.py inspect-tables --repo-id "username/model" - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 190
AA_API_KEY="your-api-key" uv run scripts/evaluation_manager.py import-aa \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 199
echo "AA_API_KEY=your-api-key" >> .env - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 211
uv run scripts/evaluation_manager.py import-aa \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 224
HF_TOKEN=$HF_TOKEN \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 234
HF_TOKEN=$HF_TOKEN \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 244
uv run scripts/run_eval_job.py \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 271
uv run scripts/lighteval_vllm_uv.py \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 295
hf jobs uv run scripts/lighteval_vllm_uv.py \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 333
uv run scripts/inspect_vllm_uv.py \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 352
hf jobs uv run scripts/inspect_vllm_uv.py \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 374
uv run scripts/run_vllm_eval_job.py \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 407
uv run scripts/evaluation_manager.py --help - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 413
uv run scripts/evaluation_manager.py inspect-tables --repo-id "username/model-name" - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 418
uv run scripts/evaluation_manager.py extract-readme \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 430
AA_API_KEY=... uv run scripts/evaluation_manager.py import-aa \ - packs/global-skillshare-import/wave-007/hugging-face-evaluation/SKILL.md, line 439
uv run scripts/evaluation_manager.py show --repo-id "username/model-name"
and 8 more places
Downloads and installs other software
The author does not mention this.
Found in 1 place.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'hugging-face-evaluation' ] || [ -L ~/.agents/skills/'hugging-face-evaluation' ]; then echo 'A skill folder named hugging-face-evaluation already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/kursku/skills' "$d" && git -C "$d" checkout --quiet '346c313fd2ec241a088c68274da26c538422568b' -- 'packs/global-skillshare-import/wave-007/hugging-face-evaluation' && mkdir -p ~/.agents/skills && cp -R "$d"/'packs/global-skillshare-import/wave-007/hugging-face-evaluation' ~/.agents/skills/'hugging-face-evaluation' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'hugging-face-evaluation' ~/.claude/skills/'hugging-face-evaluation' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for kursku/skills shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/kursku/skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-07 | 346c313 | 82 |