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 skills add onescience-ai/OneSkills --skill onescience-paper-reprogit 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-paper-repro)<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-paper-repro"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-paper-repro.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00093 | $0.02421 |
| Opus 5 | $0.00046 | $0.01210 |
| Sonnet 5 | $0.00019 | $0.00484 |
| Haiku 4.5 | $0.00009 | $0.00242 |
Grade A, and why
onescience-paper-repro 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 8d 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 — 132 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 论文复现信息提取
职责边界
本技能负责从论文或论文信息中提取结构化的复现规格,并生成编码任务提示词,不具备编码权限。
- 作为执行技能:由
onescience-orchestrator调用,接收标准化输入,返回标准化输出。 - 核心职责:论文获取、解析、信息抽取、任务描述生成。
- 不负责:编码实现、调用其他技能、任务规划。
论文复现规格必须优先来自论文正文、附录、补充材料、用户提供材料和公开数据/论文页面信息。只有当这些来源对某个实现必需细节仍缺失或说明不足时,才允许补充使用官方开源仓库的只读参考;优先从论文正文、附录或补充材料中解析官方仓库,若论文未给出,再在 GitHub 上搜索官方开源仓库。只允许在线读取与该缺失细节直接相关的模型、数据处理、特征/变量选择、训练、推理和评估实现信息,例如层数、hidden size、参数形状或具体实现连线;禁止下载、clone、复制仓库到本地,禁止参考第三方复现仓库。若论文与官方仓库实现存在冲突,以论文为主,并把差异写入规格中的冲突、缺口或假设;官方仓库内容只能作为补充实现线索,不能升级为论文事实来源。
输入输出接口
输入(从 onescience-orchestrator 接收)
{
"paper_source": "论文来源,可为:arXiv URL、DOI、PDF 路径、论文标题",
"paper_content": "可选:用户提供的论文正文片段或补充材料",
"output_dir": "可选:用户指定的最终代码输出目录",
"domain_hint": "可选:领域提示(earth/cfd/materials/biology)"
}
输出(返回给 onescience-orchestrator)
{
"status": "success | partial | failed",
"paper_workdir": ".paper2code_work/<arxiv_id>/",
"reproduction_spec_path": "reproduction_spec.md 路径",
"coder_task_description_path": "coder_task_description.md 路径",
"coder_task_description_content": "coder_task_description.md 完整内容",
"key_gaps": ["关键缺口列表"],
"key_assumptions": ["实现假设列表"],
"metadata": {
"task_method": "paper2code",
"domain_task_family": "paper-reproduction",
"coder_reference_mode": "paper_plus_official_repo_readonly",
"coder_static_review_required": true
}
}
总控流程
本技能把论文材料转换成结构化复现规格和编码任务提示词。总控流程只负责编排阶段,不在主技能文件中写领域特例或单篇论文特例。
核心产物只有:
reproduction_spec.md:结构化事实源和审计产物。coder_task_description.md:自包含的编码任务提示词,必须完整承载reproduction_spec.md中所有已确定内容。
编码任务提示词必须自包含,不应要求下游再读取其他文件补齐细节。
执行时按顺序读取以下独立 workflow:
What ships with it
9 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.
- assets/domain_knowledge/biology.md 1.9 KB
- assets/domain_knowledge/cfd.md 1.7 KB
- assets/domain_knowledge/earth.md 1.8 KB
- assets/domain_knowledge/materials.md 1.8 KB
- references/acquisition_text_workflow.md 5.0 KB
- references/audit_workflow.md 6.5 KB
- references/coder_handoff_workflow.md 8.2 KB
- references/structured_extraction_workflow.md 22 KB
- scripts/variable_channel_audit.py 4.4 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.
- 8d ago First seen · 132 lines · 93 tokens per session scan A 99ea15a230ef
onescience-paper-repro is a skill published in the GitHub repository onescience-ai/OneSkills (20 stars, last pushed yesterday), licensed MIT. It adds 93 tokens to every session and 2,421 once invoked, about $0.0005 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
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
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.
paper-select-journal
A workflow for choosing suitable SCI journals for a scientific manuscript. It reviews the paper, filters possible journals using impact-factor data, and checks journal scope and recent publications.
nsfc-budget
A tool that creates an editable LaTeX budget justification and renders it as a PDF for an NSFC research-funding application. NSFC is China’s National Natural Science Foundation, and a budget justification explains why proposed costs are needed.
research-literature-radar
A research workflow for finding, judging, classifying, tracking, and archiving important research papers. It treats bioRxiv and similar sources as places where researchers share papers, and combines database searches with other discovery signals.
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.