← 返回 Skills 市场
orbisz

simulation-doc-writer

作者 orbisz · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
38
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install simulation-doc-writer-skill
功能描述
Write, revise, or review Chinese plain-text documentation for communication simulation programs. Use when Codex needs to produce a plain-text (.txt) 仿真程序说明文档...
使用说明 (SKILL.md)

Simulation Doc Writer

Overview

Use this skill to write Chinese plain-text (.txt) documentation for communication simulation programs with enough technical detail for readers to understand, run, verify, and extend the simulation.

Prefer a professional engineering style: precise, traceable, concise, and reproducible. Explain the simulation purpose, model assumptions, signal chain, parameters, input/output data, experiment design, result interpretation, and known limitations.

Workflow

  1. Clarify missing essentials before drafting if the user's request lacks the simulation object, code language/tool, target reader, or expected document type.
  2. Inspect any provided code, configs, plots, logs, papers, or existing notes before inventing details.
  3. Choose the document structure from references/communication-simulation-doc-template.md.
  4. Draft in Chinese unless the user asks otherwise.
  5. Separate confirmed facts from reasonable assumptions. Mark uncertain items as "待确认" instead of silently fabricating.
  6. For MATLAB folders, enumerate every .m file before writing. For each file, identify whether it is a main script, function file, helper function file, plotting script, data-processing script, or obsolete/backup artifact.
  7. For each .m file, document every function it defines, including local/subfunctions inside the file. State the function purpose, inputs, outputs, calling relationship, and role in the simulation.
  8. When a paper is provided, map each named paper algorithm, model, benchmark, metric, and simulation setup to concrete code files and function names. If no matching implementation is found, mark it as "未找到明确对应实现" and explain the evidence.
  9. Explicitly identify simulation-environment files: main entry scripts, parameter/configuration locations, channel/model construction files, codebook/data generation files, metric/statistics files, plotting files, and saved-data dependencies.
  10. Generate the program description document as a plain-text file with a .txt extension. Do not use .md, .docx, .pdf, or other formats unless the user explicitly requests an additional export.
  11. Put generated code, generated Markdown documentation, and related output files in the folder containing the user-provided paper. If there is no paper path, the paper path cannot be resolved, or the folder does not exist, ask the user where to save the outputs before creating files.
  12. Include runnable commands, parameter tables, and result file descriptions when the codebase provides them.
  13. End with verification and reproduction guidance: environment, command sequence, expected outputs, and common failure cases.

Document Quality Rules

  • Use terminology common in communication engineering, such as 调制方式, 信道模型, 编码率, 载噪比, 信噪比, 误码率, 误帧率, 吞吐量, 频谱效率, 链路级仿真, 系统级仿真.
  • State mathematical models with symbols, units, and assumptions. Define each symbol near first use.
  • For algorithms, describe both the processing flow and where the implementation lives in code.
  • For paper-code comparison, provide an "论文算法/模型到代码映射表" with paper section/algorithm/figure, corresponding file, corresponding function, consistency judgment, and notes.
  • For MATLAB code documentation, provide a "MATLAB 文件与函数说明表" that covers every .m file in the target folder and every function defined in those files. Do not skip small helper files.
  • For simulation environment documentation, provide a "仿真环境对应代码文件" section that identifies where language/tool versions, system parameters, channel parameters, random seeds, Monte Carlo count, SNR/Ka sweeps, codebook size, and plotting/data loading paths are set.
  • For parameters, provide name, meaning, unit, default value, allowed range, and effect on results when possible.
  • For random simulations, document random seed policy, Monte Carlo iteration count, stopping criteria, and confidence/variance caveats.
  • For results, explain how plots or metrics are generated and how to judge whether the result is reasonable.
  • Avoid marketing language. Keep the tone like an engineering design note or lab deliverable.

Reference

Read references/communication-simulation-doc-template.md when drafting or reviewing a full document, choosing section order, or creating tables/checklists.

Self-Evolution Mechanism

After each execution of this Skill:

  1. Evaluate whether the output achieved the intended goal: pass / fail.
  2. If it fails, reflect on the cause of failure and append a “failure case + improvement suggestion” to diary/YYYY-MM-DD.md.
  3. If a certain improvement suggestion is repeatedly mentioned in the most recent three executions, refine it into a formal rule and submit a PR to modify this SKILL.md.
安全使用建议
Review before installing. The documentation-writing behavior is understandable, VirusTotal and static scan were clean, and there are no executable scripts, but the self-evolution section should be removed or disabled unless you explicitly want the agent to write diary files and propose changes to its own SKILL.md. Also confirm whether outputs should be .txt only, because the artifacts conflict about .txt versus Markdown and companion files.
能力评估
Purpose & Capability
The core purpose of reading simulation artifacts and producing Chinese documentation is coherent, but the artifacts also instruct generation of code/Markdown companion files despite the declared plain-text .txt scope.
Instruction Scope
SKILL.md requires .txt output, while README and the reference template repeatedly refer to Markdown output and companion files, creating unclear scope for what files the agent may create.
Install Mechanism
Installation guidance copies the skill into standard user or project skill directories and includes optional npx-based installation; no executable package code or dependencies were present.
Credentials
Reading user-provided code, papers, configs, logs, and plots is proportionate for documentation generation, provided users understand those local artifacts may be inspected.
Persistence & Privilege
SKILL.md instructs the agent after each execution to append failed cases to diary/YYYY-MM-DD.md and, after repeated failures, submit a PR modifying SKILL.md, which is persistent self-modification outside the stated documentation task.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install simulation-doc-writer-skill
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /simulation-doc-writer-skill 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
feat: enforce Markdown output and add self-evolution mechanism
元数据
Slug simulation-doc-writer-skill
版本 1.0.0
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 1
常见问题

simulation-doc-writer 是什么?

Write, revise, or review Chinese plain-text documentation for communication simulation programs. Use when Codex needs to produce a plain-text (.txt) 仿真程序说明文档... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 38 次。

如何安装 simulation-doc-writer?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install simulation-doc-writer-skill」即可一键安装,无需额外配置。

simulation-doc-writer 是免费的吗?

是的,simulation-doc-writer 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

simulation-doc-writer 支持哪些平台?

simulation-doc-writer 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 simulation-doc-writer?

由 orbisz(@orbisz)开发并维护,当前版本 v1.0.0。

💬 留言讨论