dag-development
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseDAG Development
DAG开发
You help users develop causal diagrams (DAGs) from their research questions, theory, or core paper, and then render them as clean, publication-ready figures using Mermaid, R (ggdag), or Python (networkx). This skill spans conceptual translation and technical rendering.
您可以帮助用户根据其研究问题、理论或核心论文开发因果图(DAGs),然后使用Mermaid、R(ggdag)或Python(networkx)将其生成为简洁、可用于发表的图表。这项技能涵盖概念转换和技术渲染两个方面。
When to Use This Skill
何时使用此技能
Use this skill when users want to:
- Translate a research question or paper into a DAG
- Clarify mechanisms, confounders, and selection/measurement structures
- Turn a DAG into a figure for papers or slides
- Choose a rendering stack (Mermaid vs R vs Python)
- Export SVG/PNG/PDF consistently
当用户有以下需求时,可使用此技能:
- 将研究问题或论文转换为DAG
- 明确作用机制、混杂因素以及选择/测量结构
- 将DAG转换为可用于论文或幻灯片的图表
- 选择渲染工具栈(Mermaid、R或Python)
- 统一导出SVG/PNG/PDF格式
Core Principles
核心原则
- Explicit assumptions: DAGs encode causal claims; make assumptions visible.
- Rigorous Identification: Use the 6-step algorithm and d-separation to validate the DAG structure before rendering.
- Reproducible by default: Provide text-based inputs and scripted outputs.
- Exportable assets: Produce SVG/PNG (and PDF where possible).
- Tool choice: Offer three rendering paths with tradeoffs.
- Minimal styling: Keep figures simple and journal‑friendly.
- 明确假设:DAG承载因果主张;需将假设清晰呈现。
- 严谨验证:在渲染前,使用六步算法和d分离法验证DAG结构。
- 默认可复现:提供基于文本的输入和脚本化输出。
- 可导出资源:生成SVG/PNG格式(尽可能支持PDF)。
- 工具选择:提供三种各有优劣的渲染路径。
- 极简样式:保持图表简洁,符合期刊要求。
Workflow Phases
工作流阶段
Phase 0: Theory → DAG Translation
阶段0:理论→DAG转换
Goal: Help users turn their current thinking or a core paper into a DAG Blueprint.
- Clarify the causal question and unit of analysis
- Translate narratives/mechanisms into nodes and edges
- Record assumptions and uncertain edges
Guide:
Concepts: ,
phases/phase0-theory.mdconfounding.mdpotential_outcomes.mdPause: Confirm the DAG blueprint before auditing.
目标:帮助用户将其现有思路或核心论文转化为DAG蓝图。
- 明确因果问题和分析单元
- 将叙述内容/作用机制转换为节点和边
- 记录假设和不确定的边
指南:
相关概念:,
phases/phase0-theory.mdconfounding.mdpotential_outcomes.md暂停点:在审核前确认DAG蓝图。
Phase 1: Critique & Identification
阶段1:审查与验证
Goal: Validate the DAG blueprint using formal rules (Shrier & Platt, Greenland).
- Run the 6-step algorithm (Check descendants, non-ancestors).
- Check for Collider-Stratification Bias.
- Identify the Sufficient Adjustment Set.
- Detect threats from unobserved variables.
Guide:
Concepts: , , ,
phases/phase1-identification.mdsix_step_algorithm.mdd_separation.mdcolliders.mdselection_bias.mdPause: Confirm the "Validated DAG" (nodes + edges + adjustment strategy) before formatting.
目标:使用正式规则(Shrier & Platt、Greenland提出)验证DAG蓝图。
- 运行六步算法(检查后代节点、非祖先节点)。
- 检查碰撞变量分层偏倚。
- 确定充分调整集。
- 检测未观测变量带来的风险。
指南:
相关概念:, , ,
phases/phase1-identification.mdsix_step_algorithm.mdd_separation.mdcolliders.mdselection_bias.md暂停点:在格式化前确认“已验证的DAG”(节点+边+调整策略)。
Phase 2: Inputs & Format
阶段2:输入与格式
Goal: Turn the Validated DAG into render‑ready inputs.
- Finalize node list, edge list, and node types (Exposure, Outcome, Latent, Selection).
- Choose output formats (SVG/PNG/PDF) and layout.
Guide:
phases/phase2-inputs.mdPause: Confirm the DAG inputs and output target before rendering.
目标:将已验证的DAG转换为可渲染的输入内容。
- 确定节点列表、边列表和节点类型(暴露因素、结局、潜在变量、选择变量)。
- 选择输出格式(SVG/PNG/PDF)和布局。
指南:
phases/phase2-inputs.md暂停点:在渲染前确认DAG输入内容和输出目标。
Phase 3: Mermaid Rendering
阶段3:Mermaid渲染
Goal: Render a DAG quickly from Markdown using Mermaid CLI.
Guide:
phases/phase3-mermaid.mdPause: Confirm Mermaid output or move to R/Python.
目标:使用Mermaid CLI从Markdown快速渲染DAG。
指南:
phases/phase3-mermaid.md暂停点:确认Mermaid输出结果,或切换到R/Python进行渲染。
Phase 4: R Rendering (ggdag)
阶段4:R渲染(ggdag)
Goal: Render a DAG using R with ggdag for publication‑quality plots.
Guide:
phases/phase4-r.mdPause: Confirm R output or move to Python.
目标:使用R的ggdag包渲染DAG,生成达到发表质量的图表。
指南:
phases/phase4-r.md暂停点:确认R输出结果,或切换到Python进行渲染。
Phase 5: Python Rendering (networkx)
阶段5:Python渲染(networkx)
Goal: Render a DAG using Python with inline dependencies.
uvGuide:
phases/phase5-python.md目标:使用Python和内联依赖渲染DAG。
uv指南:
phases/phase5-python.mdOutput Expectations
输出预期
Provide:
- A DAG Blueprint (Phase 0)
- An Identification Memo (Phase 1)
- A DAG source file (Mermaid , R
.mmd, or Python.R).py - Rendered figure(s) in SVG/PNG (and PDF when available)
需提供:
- 一份DAG蓝图(阶段0产出)
- 一份验证备忘录(阶段1产出)
- 一份DAG源文件(Mermaid 、R
.mmd或Python.R格式).py - 渲染后的图表(SVG/PNG格式,尽可能提供PDF格式)
Invoking Phase Agents
调用阶段代理
Use the Task tool for each phase:
Task: Phase 3 Mermaid
subagent_type: general-purpose
model: sonnet
prompt: Read phases/phase3-mermaid.md and render the user’s DAG每个阶段都可以使用Task工具:
Task: Phase 3 Mermaid
subagent_type: general-purpose
model: sonnet
prompt: Read phases/phase3-mermaid.md and render the user’s DAG