Skills for Real Engineers. Straight from my .agents directory.
science-discipline-methods
Agent skill fromyzlin286-wq/Deepscient
Use when a research question is still a question rather than a plan — when you know the field but not which study design the field accepts, how many samples it demands, which measurements count as evidence, or which software is standard; also use when a review came back saying the design cannot answer the question, when you are switching fields or advising a student in an unfamiliar one, when two supervisors disagree about method, or when you need to know what reviewers in that field attack first before you commit months to a protocol.
How to install science-discipline-methods
npx skills add yzlin286-wq/Deepscient# or add only this skill to Claude Code: copy the folder
dsh-science/skills/science/science-discipline-methods/
# into
~/.claude/skills/science-discipline-methods/ (all projects)
.claude/skills/science-discipline-methods/ (one project)
1# 学科方法库:先定设计,再谈统计23## 这一层解决什么问题45一个研究生最常见的卡点不是「不会做统计」,而是**问错了问题类型**。67他手里有一个现象、一份数据、一个想说的话,但不知道这个领域**用什么方式把现象变成证据**。8心理学靠随机分配与操纵检查,经济学靠外生变异与平行趋势,化学靠表征链,材料靠批次与标准,9机器学习靠多种子与强基线——同样是「证明 A 影响 B」,各领域要求的证据形态完全不同。1011所以这一层的产出不是结论,是**这个领域公认的走路方式**:12能问什么、用哪个设计、要多少样本、量什么、跑什么方法、装什么软件、审稿人先打哪里。1314## 入口1516```17science_discipline_list {} # 有哪些学科包18science_discipline_profile { domain: "biomed" } # 某个学科的全貌19science_discipline_profile { question: "我想用 fMRI 研究注意力的神经机制" } # 只有问题也行20science_discipline_profile { design: "重复测量" } # 反向查:哪些领域有这个范式21science_discipline_profile { tool: "RDKit" } # 反向查:这软件在哪个领域是标准22science_discipline_profile { journal: "nature" } # 只知道要投哪23```2425`domain` 可以给 id、中文名、英文名,或者整段研究问题——匹配器按26「显式 → 期刊族 → 别名精确 → 别名包含 → 关键词 → generic」六级降级,27并把 `matchedBy` / `confidence` / `candidates` 一起返回,让你知道它有多确定。2829**generic 不是失败**,是诚实:没匹配上时不硬塞一个最近的学科,因为错误的学科包30会让后面每一步建议都错(样本量、默认校正方法、报告规范全都跟着错)。3132## 一个学科包里有九样东西3334| 字段 | 回答什么 | 什么时候必看 |35| --- | --- | --- |36| `questionTypes` | 这个领域能问哪几类问题,各需要什么前置 | 选题阶段 |37| `designs` | 有哪几种被接受的设计,各自的 `requires` / `nRule` / `threats` | 写方案前 |38| `measurements` | 量什么、单位、精度、伪迹来源、怎么校准 | 设计问卷/实验时 |39| `methods` | 分析方法的适用条件、`tool`、`pitfall` | 分析前 |40| `tools` | 装什么、`install`、`minimalScript`、是否离线、许可 | 开工第一天 |41| `statsDefaults` | 该领域的 α、校正方法、首选效应量 | 分析前 |42| `reviewerAttacks` | 审稿人会先打哪里,以及怎么挡 | 投稿前自检 |43| `benchmarks` | 顶刊的**方法学门槛** | 判断「我这够不够」 |44| `exemplarStructure` | Results 该按什么顺序写,图给几张 | 写作时 |45…
Excerpt shown under the repository's MIT license.
More skills in Deepscient
- ▸science-agent-scheduling
- ▸science-campaign-design
- ▸science-consensus-report
- ▸science-experiment-runbook
- ▸science-figure-for-journal
- ▸science-frontier-to-paper
- ▸science-fulltext-hunting
- ▸science-journal-intel
- ▸science-journal-selection
- ▸science-literature-search
- ▸science-manuscript-formatting
- ▸science-org-roles
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
