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 agentmods add skills/onescience-ai/oneskills/onescience-infernpx skills add onescience-ai/OneSkills --skill onescience-infergit clone --depth 1 https://github.com/onescience-ai/OneSkillsWrote 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/onescience-ai/oneskills/onescience-infer)<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-infer"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-infer.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 | $0.00153 | $0.02887 |
| Opus 5 | $0.00077 | $0.01443 |
| Sonnet 5 | $0.00031 | $0.00577 |
| Haiku 4.5 | $0.00015 | $0.00289 |
Grade A, and why
onescience-infer 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
输入获取方式
本技能支持两种输入方式:
- 上下文 handoff(默认):从调用方传入的
step_handoff获取任务信息。 - 文件 handoff(autonomous_mode):从
.onescience/handoff/step_{step_id}.yaml读取任务信息。执行后,将结果写入.onescience/handoff/step_{step_id}_result.yaml。
启动时优先检查 .onescience/handoff/ 目录是否存在对应的交接文件;若存在则使用文件模式,否则使用上下文模式。
文件交接格式参见 skills/onescience-orchestrator/references/file_handoff_contract.md。
OneScience Infer
职责
将本技能作为科学模型推理任务的执行工作流。把 orchestrator 交给本技能的当前步骤,例如“为 HuggingFace checkpoint 生成推理入口”“使用本地 checkpoint 跑一次材料性质预测”“准备生信模型输入并执行推理”“验证流体仿真 surrogate 输出”,转化为从模型知识获取到结果验证的可追踪闭环。
本技能只消费当前执行步骤,不重新规划完整用户目标。本技能负责推理工作流契约和阶段顺序;当代码实现、数据构建或运行提交由已有执行技能更适合负责时,应将当前步骤交接给对应技能。依赖包、硬件和运行环境需求不单独成阶段,而是在推理执行阶段交给 onescience-runtime。
工作流
创建或更新工作目录:
产物路径规则:
-
repro_artifact_dir:所有可复现推理产物的根目录,默认<work_dir>/repro_artifacts/<run_id>/。该目录与源码目录(如paper_cases/)强制隔离,不得将推理脚本、输出结果散落在案例源码目录中。repro_artifact_dir/code/:生成的推理启动器脚本、runner 等代码产物(默认 =code_save_dir)repro_artifact_dir/outputs/:推理输出结果(mmCIF、confidence JSON、ranking CSV 等)repro_artifact_dir/logs/:运行日志repro_artifact_dir/.infer_work/:中间知识产物(=infer_workdir)
-
code_save_dir用于保存最终代码入口和 runner。若上游已显式提供step_handoff.inputs.runtime.code_save_dir,优先使用;若未提供,默认 =<repro_artifact_dir>/code/。 -
infer_workdir用于保存模型知识、计划、manifest、runtime 请求/结果、验证报告等 infer 中间知识产物,默认 =<repro_artifact_dir>/.infer_work/。若上游已显式提供step_handoff.inputs.runtime.infer_workdir,则直接使用该目录。 -
若上游未提供
code_save_dir,但step_handoff.inputs.runtime.workdir、task_context.relevant_artifacts或用户明确指定了工作目录,则repro_artifact_dir首选<work_dir>/repro_artifacts/<run_id>/;否则兼容性回退到.onescience/infer/<run_id>/。 -
进入具体代码生成或执行阶段时,必须从
infer_workdir中已保存的知识文件读取并交接,不依赖未落盘的会话上下文。
GPU 分配规则:
- 禁止将论文协议参数(如 seed 数量)硬编码为 GPU 数量。
seed_count(协议参数)、gpu_count(硬件资源)、worker_count(并发工作单元)必须分别建模为独立变量。 - 代码生成和执行阶段必须通过
nvidia-smi --query-gpu=index,name,memory.total,memory.free --format=csv,noheader或rocm-smi检测实际可用 GPU 列表,不得硬编码 GPU 索引。 worker_count = seed_count × samples_per_seed(或其他业务粒度),gpu_count = 实际可用 GPU 数。调度策略:worker_count > gpu_count时分批轮转执行,worker_count <= gpu_count时一卡一 worker。
What ships with it
8 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.
- references/gpu-oom-handling.md 12 KB
- references/phase_1_model_knowledge.md 2.0 KB
- references/phase_3_data_preparation.md 4.7 KB
- references/phase_4_model_loading.md 1.7 KB
- references/phase_5_codegen.md 7.3 KB
- references/phase_6_execution.md 8.7 KB
- references/phase_7_validation.md 5.3 KB
- references/workflow_contract.md 8.8 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.
- 5d ago First seen · 159 lines · 153 tokens per session scan A 8d361581bad5
onescience-infer is a skill published in the GitHub repository onescience-ai/OneSkills (20 stars, last pushed 21d ago), licensed MIT. It adds 153 tokens to every session and 2,887 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.
nsfc-budget
当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料,输出一份可提交的预算说明书 LaTeX 项目并渲染 budget.pdf。若用户未指定工作目录,必须暂停并先要求其指定。⚠️ 不适用:用户只是想了解预算原则;用户仅要预算表数字而不写说明书;或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。.
paper-select-journal
当用户明确要求“推荐投稿期刊”“帮我的论文选 SCI 杂志”“这篇 manuscript 适合投哪些 journal”“期刊匹配/选刊/投稿建议”时必须使用。适用于用户提供全文、摘要、Markdown、LaTeX、PDF、Word 或混合材料的场景;本 skill 会基于 manuscript 与用户偏好,先用内置 2023IF.xlsx 做最小硬过滤生成候选池,再由宿主模型自主规划 Set1/Set2/Set3,并联网核验 scope / 质量 / 近 3 个月 PubMed 论文,最后输出 1 份按推荐度排序的 Markdown 选刊报告。⚠️…
paper-search
Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, etc). Use when the user asks to find papers, search for research, look up academic literature, download a paper PDF, or extract text from a paper.
bio-ortholog-inference
Pull pre-computed ortholog calls from public databases (OrthoDB, Ensembl Compara, OMA browser, eggNOG, PANTHER, KEGG Orthology, HomoloGene) via their REST APIs. Use when orthologs are already curated upstream, when the question is "what is the X ortholog of Y" rather than "how to infer orthology de novo", when…
bioprobench
Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.