synthetic-sciences/openscience is an AI workbench that carries out scientific research by reading papers, forming hypotheses, writing and running code, conducting experiments, analyzing results, and preparing reports. Researchers use it for work in machine learning, biology, physics, and chemistry with remote or local models. Catalogue add-ons extend its scientific workflows through skills and instructions.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/synthetic-sciences/opensciencenpx agentmods add skills/synthetic-sciences/openscience/hugging-face-evaluationWrote 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/synthetic-sciences/openscience/hugging-face-evaluation)<a href="https://agentmods.dev/skills/synthetic-sciences/openscience/hugging-face-evaluation"><img src="https://agentmods.dev/badge/skills/synthetic-sciences/openscience/hugging-face-evaluation.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.06034 |
| Opus 5 | $0.00028 | $0.03017 |
| Sonnet 5 | $0.00011 | $0.01207 |
| Haiku 4.5 | $0.00006 | $0.00603 |
Grade A, and why
hugging-face-evaluation scanned grade A with 1 finding 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 3d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run([ This is a copy
92% identical to hugging-face-evaluation — 1,302 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 — 658 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill provides tools to add structured evaluation results to Hugging Face model cards. It supports multiple methods for adding evaluation data:
- Extracting existing evaluation tables from README content
- Importing benchmark scores from Artificial Analysis
- Running custom model evaluations with vLLM or accelerate backends (lighteval/inspect-ai)
Integration with HF Ecosystem
- Model Cards: Updates model-index metadata for leaderboard integration
- Artificial Analysis: Direct API integration for benchmark imports
- Papers with Code: Compatible with their model-index specification
- Jobs: Run evaluations directly on Hugging Face Jobs with
uvintegration - vLLM: Efficient GPU inference for custom model evaluation
- lighteval: HuggingFace's evaluation library with vLLM/accelerate backends
- inspect-ai: UK AI Safety Institute's evaluation framework
Version
1.3.0
Dependencies
Core Dependencies
- huggingface_hub>=0.26.0
- markdown-it-py>=3.0.0
- python-dotenv>=1.2.1
- pyyaml>=6.0.3
- requests>=2.32.5
- re (built-in)
Inference Provider Evaluation
- inspect-ai>=0.3.0
- inspect-evals
- openai
vLLM Custom Model Evaluation (GPU required)
- lighteval[accelerate,vllm]>=0.6.0
- vllm>=0.4.0
- torch>=2.0.0
- transformers>=4.40.0
- accelerate>=0.30.0
Note: vLLM dependencies are installed automatically via PEP 723 script headers when using uv run.
IMPORTANT: Using This Skill
⚠️ CRITICAL: Check for Existing PRs Before Creating New Ones
Before creating ANY pull request with --create-pr, you MUST check for existing open PRs:
uv run scripts/evaluation_manager.py get-prs --repo-id "username/model-name"
If open PRs exist:
- DO NOT create a new PR - this creates duplicate work for maintainers
- Warn the user that open PRs already exist
- Show the user the existing PR URLs so they can review them
- Only proceed if the user explicitly confirms they want to create another PR
What ships with it
13 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/.env.example 311 B
- examples/artificial_analysis_to_hub.py 3.9 KB runs code
- examples/example_readme_tables.md 3.0 KB
- examples/metric_mapping.json 924 B
- examples/USAGE_EXAMPLES.md 9.3 KB
- requirements.txt 465 B
- scripts/evaluation_manager.py 48 KB runs code
- scripts/inspect_eval_uv.py 2.9 KB runs code
- scripts/inspect_vllm_uv.py 9.2 KB runs code
- scripts/lighteval_vllm_uv.py 9.2 KB runs code
- scripts/run_eval_job.py 2.4 KB runs code
- scripts/run_vllm_eval_job.py 9.3 KB runs code
- scripts/test_extraction.py 5.5 KB runs code
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.
- 3d ago First seen · 658 lines · 55 tokens per session scan A d02003fd763c
hugging-face-evaluation is a skill published in the GitHub repository synthetic-sciences/openscience (3,493 stars, last pushed today), licensed Apache-2.0. It adds 55 tokens to every session and 6,034 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 92% identical to hugging-face-evaluation, differing in 1,302 lines, and is treated as a copy.
Other skills, from other repositories
model-evaluation
Systematic ML model evaluation — metrics, benchmarks, and error analysis.
llm-evaluator
Evaluate LLM outputs systematically using LLM-as-judge, human evaluation frameworks, and regression testing. Use when assessing model quality, comparing models, or preventing quality regression.
rag-evaluator
Evaluate RAG pipeline quality across faithfulness, relevance, and hallucination metrics. Use when user asks to test, benchmark, or improve a RAG system, or when RAG outputs look wrong.
system-prompts
Write system prompts, tool docs, and agent definitions. Project tag conventions + RFC 2119 keywords + dense compression. Use when authoring or editing any prompt the model reads.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
knowledge-model-and-provider-runtime-provider-resilience-admission-and-observability
覆盖跨 Agent、Session、Subagent、CLI/Web/ACP 表面的 Provider 重试、前台恢复、 failure-domain 熔断、公平准入、stream stall、Prompt Cache 与费用观测。 Navigate when: 调试 429/5xx/timeout、重复请求、Open/HalfOpen、容量排队、后台饥饿、缓存命中 下降、状态栏或事件投影。Excludes: 模型目录与凭据配置（见 ../model-catalog-configuration-and-credentials/），消息和 payload 协议映射（见…