← All skills
hugging-face-community-evals
95 / 100 · Low risk
Fine to try.
By boisenoise/skills-collections (GitHub) · other · 12 stars · scanned at commit 419c39f
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
The author does not mention this.
Found in 16 places.
Show 13 more
- skills/antigravity-hugging-face-community-evals/SKILL.md, line 116
uv run scripts/inspect_vllm_uv.py \ - skills/antigravity-hugging-face-community-evals/SKILL.md, line 131
uv run scripts/lighteval_vllm_uv.py \ - skills/antigravity-hugging-face-community-evals/SKILL.md, line 141
uv run scripts/lighteval_vllm_uv.py \ - skills/antigravity-hugging-face-community-evals/scripts/inspect_eval_uv.py, line 98
subprocess.run(cmd, check=True, cwd=tasks_root) - skills/antigravity-hugging-face-community-evals/scripts/inspect_eval_uv.py, line 100
except subprocess.CalledProcessError as exc: - skills/antigravity-hugging-face-community-evals/scripts/inspect_vllm_uv.py, line 104
subprocess.run(cmd, check=True) - skills/antigravity-hugging-face-community-evals/scripts/inspect_vllm_uv.py, line 106
except subprocess.CalledProcessError as exc: - skills/antigravity-hugging-face-community-evals/scripts/inspect_vllm_uv.py, line 169
subprocess.run(cmd, check=True) - skills/antigravity-hugging-face-community-evals/scripts/inspect_vllm_uv.py, line 171
except subprocess.CalledProcessError as exc: - skills/antigravity-hugging-face-community-evals/scripts/lighteval_vllm_uv.py, line 101
subprocess.run(cmd, check=True) - skills/antigravity-hugging-face-community-evals/scripts/lighteval_vllm_uv.py, line 103
except subprocess.CalledProcessError as exc: - skills/antigravity-hugging-face-community-evals/scripts/lighteval_vllm_uv.py, line 165
subprocess.run(cmd, check=True) - skills/antigravity-hugging-face-community-evals/scripts/lighteval_vllm_uv.py, line 167
except subprocess.CalledProcessError as exc:
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'hugging-face-community-evals' ] || [ -L ~/.agents/skills/'hugging-face-community-evals' ]; then echo 'A skill folder named hugging-face-community-evals already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/boisenoise/skills-collections' "$d" && git -C "$d" checkout --quiet '419c39fde874b8baecbb36a397b967e0190a2ece' -- 'skills/antigravity-hugging-face-community-evals' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/antigravity-hugging-face-community-evals' ~/.agents/skills/'hugging-face-community-evals' && 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-community-evals' ~/.claude/skills/'hugging-face-community-evals' (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 boisenoise/skills-collections shows the score of its lowest-scoring skill.

[](https://zalavijaysinh.github.io/skilltrust/repos/boisenoise/skills-collections/)
Score history
| Date | Version | Score |
|---|
| 2026-11-12 | 419c39f | 95 |
| 2026-11-08 | 5fe45e5 | 95 |
| 2026-11-06 | b89b2f5 | 95 |