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-research-workflowgit 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-research-workflow)<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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 | $0.00095 | $0.06793 |
| Opus 5.5 | $0.00038 | $0.02717 |
| Sonnet 5.5 | $0.00019 | $0.01359 |
| Haiku 4.5 | $0.00010 | $0.00679 |
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 yesterday.
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 — 370 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
- 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 - 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 - 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 - 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
- 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
- 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
- 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
-> 判断是否适用 Task-Centric 规划模式
-> [Task-Centric 模式] 检索 Scenario -> Task Graph -> 为每个 Task 选择 Method/Resource
-> [传统模式] 检查资源知识是否充足 -> 补充召回 -> 编排工作流节点
-> 将知识转写为执行级 workflow_nodes、checks、risks 和 fallback_options
-> 选择资源并说明理由
-> 返回 planner_proposal
Task-Centric 规划模式
新增:本技能支持 Task-Centric 规划模式。当用户请求涉及科研任务编排时,优先使用此模式。
触发条件
当规划请求满足以下任一条件时,进入 Task-Centric 模式:
- 用户请求中包含明确的科研目标(如“筛选材料”“预测性质”“分析稳定性”)
- planning_request 中包含
intent: task_centric或scenario_ref - 已有 Workflow 可以匹配当前科研目标
Task-Centric 规划流程
-
Scenario 识别:根据用户请求识别对应的科研场景(Scenario)。通过
type=resource技能以intent: scenario检索匹配的 Scenario。 -
Task Graph 构建:
- 若已有匹配的 Workflow,直接使用其 Task Graph
- 若无完全匹配的 Workflow,根据 Scenario 的
candidate_tasks和 Task 的relations(can_follow/can_precede)动态组合 Task Graph
-
Task Instance 生成:为 Task Graph 中的每个 Task 生成 Task Instance:
- 根据约束条件(精度、规模、速度、资源)为每个 Task 选择 Method
- 根据 Method 的
resource_candidates选择具体 Resource - 展开 Operation 列表
- 绑定 Validation 要求
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.
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.
- yesterday Changed 8db817bac3dc
- 8d ago Changed · +39 lines fb1332a0cb8a
- 1mo ago Changed · +79 lines · +25 tokens per session ef62287e39d5
- 2mo ago First seen · 252 lines · 70 tokens per session scan A 06762621949f
onescience-research-workflow is a skill published in the GitHub repository onescience-ai/OneSkills (24 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 6,793 once invoked, about $0.0004 per session on Opus 5.5. 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.
onescience-research-workflow compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| onescience-research-workflowonescience-ai/OneSkills | Skill | 24 | yesterday | MIT | A | 95 | Claude Code |
| paper-select-journalhuangwb8/ChineseResearchLaTeX | Skill | 3.0k | 5d ago | MIT | A | 194 | Claude Code, Codex |
| research-literature-radarhuangwb8/ChineseResearchLaTeX | Skill | 3.0k | 5d ago | MIT | A | 96 | Codex |
| nsfc-budgethuangwb8/ChineseResearchLaTeX | Skill | 3.0k | 5d ago | MIT | A | 138 | Claude Code, Codex |
| paper-searchopenags/paper-search-mcp | Skill | 3.0k | 1mo ago | MIT | A | 62 | Claude Code, Codex |
| bio-ortholog-inferencePKU-YuanGroup/OpenAI4S | Skill | 662 | 3d ago | MIT | A | 141 | Claude Code, Codex |
| bioprobenchPKU-YuanGroup/OpenAI4S | Skill | 662 | 3d ago | MIT | A | 46 | Claude Code, Codex |