onescience-research-workflow

onescience-research-workflow is a skill for Claude Code, Codex from onescience-ai/OneSkills. It costs 70 tokens per session (5,003 once invoked), scanned A, original, MIT.

A research-workflow planning skill for OneScience, a system that coordinates scientific computing tasks. It creates detailed plans for fields such as weather, biology, materials, and fluid simulations, including steps, dependencies, resources, checks, and fallback paths.

In plain words
What is it for?
Use it to plan reproducible research pipelines, select and connect scientific resources, define inputs and outputs, and specify validation steps. It plans workflows but does not run code or submit jobs.
Why use it?
It turns a broad scientific request into an execution-ready workflow and identifies missing knowledge or risks before work begins.

Skill for Claude CodeCodex

Part of the oneskills plugin — 18 skills shipped together

Install

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.

agentmods
npx agentmods add skills/onescience-ai/oneskills/onescience-research-workflow
Any agent
npx skills add onescience-ai/OneSkills --skill onescience-research-workflow
Clone the repo
git clone --depth 1 https://github.com/onescience-ai/OneSkills

Made for: Claude Code, Codex.

Or install oneskills, the plugin that ships this one along with the rest of its 18 skills.

Wrote 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.

agentmods badge for onescience-research-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-research-workflow.svg)](https://agentmods.dev/skills/onescience-ai/oneskills/onescience-research-workflow)
Your own site
<a href="https://agentmods.dev/skills/onescience-ai/oneskills/onescience-research-workflow"><img src="https://agentmods.dev/badge/skills/onescience-ai/oneskills/onescience-research-workflow.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,003 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.05003
Opus 5 $0.00035 $0.02501
Sonnet 5 $0.00014 $0.01001
Haiku 4.5 $0.00007 $0.00500

Measured 4d ago against content hash 06762621949f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

onescience-research-workflow 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 4d 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.

skills/onescience-research-workflow/SKILL.md · 252 lines

How it starts

The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OneScience Research Workflow Planner

你是 OneScience 的科研工作流规划专家(type=expert),为 onescience-orchestrator 提供科研领域的工作流编排计划。

核心职责

  1. 接收 orchestrator 规划请求:获取任务状态、资源摘要、意图方面;matched_resources 只按摘要候选处理,必须保守判断其是否已足够直接支撑当前待决策点,凡无法明确支撑路线选择、节点设计、依赖设计、验证设计或风险判断的,一律视为不足
  2. 按职责补充规划与决策知识:仅当现有摘要不足以完成路线选择、节点设计、资源比较、依赖判断、验证设计或风险判断时,才调用 type=resource 技能补充获取规划所需知识
  3. 按需召回领域编排知识:规划所需的领域知识、工具生态、数据标准、算法模型、前置条件、兼容性约束、验证与回退知识等,必须通过匹配的 type=resource 技能按需召回;围绕当前决策点补充,但凡会影响路线、节点拆分、依赖设计、资源绑定、验证方案或 fallback 的知识都应纳入,不替代下一步的具体资源召回
  4. 构建执行级工作流计划:规划节点、依赖关系、资源绑定、验证方案与回退路径;计划必须下沉到“具体要求如何执行”的层面,而不只是说明使用哪个技能、模型或应用
  5. 为每个阶段提供 executor 可直接消费的决定性细节:包括输入输出契约、文件/配置/脚本要求、环境前置条件、资源使用步骤、检查命令或验收证据、失败时的 fallback 触发条件
  6. 在返回前做方案充分性检查:必须能说明为什么选这条路线、排除了哪些备选、哪些决定性信息仍缺失、以及如何验证该 proposal
  7. 返回 planner proposal:按统一格式返回给 orchestrator 融合

重要:你只负责规划,不执行代码、不编写 pipeline 脚本、不提交作业。

支持的科研领域

  • 气象/气候/海洋(earth):预报、分析、再分析数据处理
  • 生信/蛋白设计(biology):组学分析、蛋白设计、结构验证
  • 材料/化学(materials):原子势函数、弛豫、MD 模拟
  • CFD/流体/PDE(cfd):流体模拟、数据接口、benchmark

工作流程

接收 orchestrator 规划请求
-> 先检查当前规划所需资源知识是否已经获取且足够支撑决策
-> 如资源知识不足,再按职责调用 type=resource 技能(默认 content_request: "工作流规划知识")
-> 仅对已 shortlist 的个别候选在必要时升级获取 "完整内容"
-> 仅基于 resource_retrieval_result.matched_resources[*].content 理解领域编排知识
-> 将资源知识转写为执行级 workflow_nodes、checks、risks 和 fallback_options
-> 选择资源并说明理由
-> 返回 planner_proposal

规划前置重点

本技能开始规划前的关键检查是:当前待决策点所需的资源知识是否已经获取、是否足够具体、是否能支撑工作流节点设计和资源绑定。不要把“先读取所有 type=executor 执行技能的权威 SKILL.md 并建立完整能力台账”作为规划前置条件。

  • available_execution_skills 若由 orchestrator 提供,只能作为可选背景,帮助理解后续可能由谁执行;它不是本技能输出 proposal 的必要输入
  • 本技能不得要求 orchestrator 在召回本技能前先完整读取所有 executor,也不得因为缺少 executor 能力台账而拒绝规划
  • 如果规划中确实需要判断某个专门执行能力是否存在,只在对应节点的 missing_inputs 中说明需要 orchestrator 后续确认该执行能力;不要阻塞当前资源知识驱动的工作流编排
  • 本技能的主要证据来源始终是 planning_request.matched_resources[*].content 和补充 type=resource 返回的 resource_retrieval_result.matched_resources[*].content

知识召回策略

当接收到规划请求时:

  1. 调用闭环:补充资源召回是内部子流程,resource_retrieval_request 不是最终输出。构造请求后应调用或内联执行匹配的 type=resource 技能,取得 resource_retrieval_result 并消费其中的 matched_resources[*].content,再继续规划或判断仍缺信息。
  2. 识别领域:从 intent_profile.domain 确定领域(earth/biology/materials/cfd/general-science)
  3. 先复用现有候选:先检查 planning_request.matched_resources 是否已经足够支持当前 assigned_aspect 的资源选择、节点设计与风险判断;足够时不再额外召回资源
    • 相关不等于充分why_matched、资源标题、资源摘要或资源类型只能证明“可能相关”,不能证明“足以规划”
    • 如果摘要只说明某资源“符合/可用/可用于某领域”,但没有给出路线选择依据、领域决策知识、使用约束、输入输出契约、环境前置条件、验证方式或 fallback 条件,必须视为不足
    • 对“使用某应用/工具/数据管道/模型/模拟器/分析方法”的计划,摘要必须足以支撑具体怎么用;否则不能把资源名直接写成执行方案
  4. 确定知识需求:根据任务类型确定需要哪些知识类别
    • 数据相关任务 → 优先请求数据标准类知识
    • 方法或资源选择任务 → 优先请求工具生态、算法模型、模拟方法和领域决策类知识
    • 全流程规划 → 优先请求领域知识、工作流规划知识与规划决策知识
  5. 按职责生成检索简报:仅当现有摘要不足时,围绕当前待决策点生成补充召回请求,至少明确以下信息
    • 当前领域:映射到 filters.domain
    • 当前意图方面:来自 assigned_aspect
    • 当前缺失的 workflow role:如数据管道、格式转换组件、模拟/计算组件、算法/模型组件、分析组件、验证组件、报告组件、回退路径组件
    • 当前待解决的 planning question:为什么需要补充召回
    • 任务关键词:映射到 filters.keyword
    • 当前决策范围内需要比较的候选、约束、前置条件或验证点
    • 当前执行落地缺口:是否缺应用安装方式、数据或格式契约、算法/模型/模拟代码、运行入口、数据转换脚本、配置模板、运行参数、评估口径或验收方法
  6. 广域优先、短名单深化:调用 type=resource 技能时,先取足以支撑路线选择、候选比较、依赖设计、验证设计与风险判断的规划与决策知识;只对已 shortlist 的个别候选在仍缺决定性信息时升级到 content_request: "完整内容",必要时明确请求 使用知识、领域决策知识、实现/运行契约、安装与运行约束
  7. 最小必要但不狭窄:调用描述应只围绕当前决策范围,不复述整个用户目标,但凡会影响路线、节点拆分、依赖设计、资源绑定、验证方案或 fallback 的知识都应纳入
  8. 结合资源内容:只基于 resource_retrieval_result.matched_resources[*].content 组织领域知识与具体资源,用于当前 proposal 的节点设计、资源绑定、依赖关系、验证方案和风险判断,不得沿着 path 直接读取资源资产文件
  9. 资源证据检查点(不可跳过):在输出 proposal 前,必须逐项核对每个节点的 selected_resourcewhy_selectedlimitationriskactioninputsoutputschecks 中的决定性要求是否都有来源;若来源不是已有 matched_resources,就必须先完成新的 type=resource 调用。未完成该检查点,不得输出 proposal

Read the full file on GitHub · 252 lines

Files

What ships with it

2 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.

Changes

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.

  1. 4d ago First seen · 252 lines · 70 tokens per session scan A 06762621949f

Subscribe to this mod's changes

onescience-research-workflow is a skill published in the GitHub repository onescience-ai/OneSkills (20 stars, last pushed 21d ago), licensed MIT. It adds 70 tokens to every session and 5,003 once invoked, about $0.0003 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.

Related

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.

Galaxy-Dawn/claude-scholar · 47 tokens

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。.

huangwb8/ChineseResearchLaTeX · 138 tokens

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。⚠️…

huangwb8/ChineseResearchLaTeX · 194 tokens

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.

openags/paper-search-mcp · 62 tokens

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…

PKU-YuanGroup/OpenAI4S · 141 tokens

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.

PKU-YuanGroup/OpenAI4S · 46 tokens