CDA Data Synth

v1.0.0

CDA 因果数据合成器——根据领域描述自动生成 CDA 架构可消费的因果数据集。 生成 Entity-State Graph(JSON 格式)、CausalEdge 列表、带时间戳的观测轨迹、哈密顿量约束参数。 覆盖热力学、力学、流体、多域耦合等物理域,支持生成训练数据、验证数据、基准测试数据。 当用户需要为 C...

0· 0·0 current·0 all-time
by波动几何@wangjiaocheng

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for wangjiaocheng/cda-data-synth.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "CDA Data Synth" (wangjiaocheng/cda-data-synth) from ClawHub.
Skill page: https://clawhub.ai/wangjiaocheng/cda-data-synth
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Canonical install target

openclaw skills install wangjiaocheng/cda-data-synth

ClawHub CLI

Package manager switcher

npx clawhub@latest install cda-data-synth
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the actual contents: an instruction-only synthesizer with data-format/spec/protocol references and an example dataset. No unrelated credentials, binaries, or capabilities are requested.
Instruction Scope
SKILL.md instructs the agent to parse user scenario descriptions, consult the included spec/protocol docs, and produce JSON outputs in the declared CDA schema. It does not instruct reading unrelated system files, contacting external endpoints, or exfiltrating data.
Install Mechanism
No install spec and no code files — the skill is instruction-only, so nothing is written to disk by an installer and no external packages are pulled in.
Credentials
No required environment variables, credentials, or config paths are declared; the resources requested are proportional to a data-generation/instruction-only skill.
Persistence & Privilege
always:false and standard autonomous invocation allowed. The skill does not request persistent system-wide privileges or modify other skills/configurations.
Assessment
This skill appears coherent and limited in scope: it contains format specifications, synthesis protocols, and an example and only asks the agent to generate JSON datasets following those specs. Before installing, consider: (1) validate any generated dataset before using it in safety- or production-critical systems (physics fidelity, energy/mass conservation, numeric stability); (2) the skill will write files to a directory you specify — ensure you choose a safe output path and review outputs for sensitive data; (3) the SKILL.md claims 'ownership' of the protocol — if other skills rely on this protocol, confirm they use the same authoritative spec; (4) although no credentials or network calls are present, always review future versions for added install steps or external endpoints. Overall the package is internally consistent and low-risk.

Like a lobster shell, security has layers — review code before you run it.

latestvk97dq6tcjka547wf4het04zpnn85k4p8
0downloads
0stars
1versions
Updated 4h ago
v1.0.0
MIT-0

CDA 因果数据合成器(Data Synthesizer)

为 Causal Dynamics Architecture 架构生成标准格式的合成因果数据集。

核心定位

CDA 架构的输入不是 Token 序列,而是 Entity-State Graph(实体-状态因果图)。本技能解决从"领域描述"到"架构可消费数据"的桥梁问题。

数据格式所有权:本技能定义并维护 CDA 的数据序列化协议。Code Lab 技能依赖此协议生成代码。

工作流程

用户描述场景
  ↓
1. 解析领域类型(热力学/力学/流体/多域耦合)
  ↓
2. 设计实体拓扑(entities + edges 骨架)
  ↓
3. 参数化机制函数(mechanism parameters)
  ↓
4. 运行前向仿真生成轨迹(trajectory snapshots)
  ↓
5. 序列化为 JSON 格式输出

输出格式规范

所有输出必须符合 references/data-format-spec.md 中定义的 JSON Schema。

核心输出文件类型:

  • *.graph.json — 静态因果图(实体 + 边 + 属性)
  • *.trajectory.json — 时序轨迹(多时刻快照序列)
  • *.hamiltonian.json — 哈密顿量参数(势能函数 + 守恒量)
  • *.meta.json — 数据集元信息(域类型、规模、物理约束摘要)

参考文件

文件内容
references/data-format-spec.md核心协议:Entity-State Graph 的完整 JSON Schema 定义
references/synthesis-protocols.md各物理域的数据合成协议(热力学/力学/流体/耦合)
references/thermal-building-example.json热力学示例:建筑温度仿真数据集

数据合成原则

  1. 物理一致性:合成数据必须满足能量守恒、质量守恒等物理约束
  2. 因果真实性:因果边的方向和机制函数必须反映真实物理规律
  3. 可验证性:每条因果边都附带 ground truth,便于验证因果发现算法
  4. 可扩展性:从简单场景(3-5 实体)到复杂场景(100+ 实体)渐进生成

域类型与对应的物理约束

广义坐标 q共轭动量 p典型机制函数守恒量
热力学温度 T热流 J_q傅里叶定律、牛顿冷却能量
力学位移 x动量 p胡克定律、阻尼力能量、动量
流体压力场 P质量流 J_mNavier-Stokes 简化质量、动量
电路电荷 Q电流 I欧姆定律、基尔霍夫定律电荷、能量

与 CDA 主技能的关系

CDA(主技能)
  ├── 理论参考:架构设计、公式、路线图
  ├── CDA Data Synthesizer(本技能)
  │     └── 数据生成:Entity-State Graph → JSON
  └── CDA Code Lab
        └── 代码生成:读取数据 → 仿真/训练代码

使用指南

  1. 用户描述目标场景(如"一个有三台压缩机和两个冷库的制冷系统")
  2. 读取 references/data-format-spec.md 获取格式规范
  3. 读取 references/synthesis-protocols.md 获取对应域的合成协议
  4. 参考示例文件了解完整数据集结构
  5. 生成符合规范的 JSON 数据文件,输出到用户指定目录

Comments

Loading comments...