← 返回 Skills 市场

Paper Writing Workflow

Name: Paper Writing Workflow
Author: earthwalking

作者 Roma · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ✓ 安全检测通过

1439

总下载

当前安装

版本数

在 OpenClaw 中安装

/install paper-writing-workflow

功能描述

Standardized paper writing workflow integrating academic-writing, research-paper-writer, scientific-writing and other skills. Provides complete paper writing...

使用说明 (SKILL.md)

Paper Writing Workflow

Overview

标准化论文写作工作流，整合多个论文写作技能，提供从选题到完稿的完整流程。

6 Workflow Stages

1. 选题与假设 (10-20 分钟)

研究问题生成
假设形成
变量定义

使用技能: hypothesis-generation, research-lookup

2. 文献搜索与综述 (30-60 分钟)

文献搜索
文献整理
文献综述写作

使用技能: literature-search-workflow, paper-parse, citation-management

3. 论文大纲设计 (15-30 分钟)

IMRAD 结构设计
每部分关键点
图表计划

使用技能: scientific-writing, research-paper-writer

4. 初稿写作 (60-120 分钟)

摘要写作
引言写作
方法写作
结果写作
讨论写作

使用技能: scientific-writing, academic-writing, research-paper-writer

5. 图表生成 (30-60 分钟)

图形摘要（必需）
方法流程图
结果图表
理论框架图

使用技能: scientific-schematics, scientific-visualization

6. 润色与格式检查 (30-60 分钟)

语言润色
格式检查
引用检查

使用技能: academic-writing, citation-management

Supported Templates

模板	期刊	字数	图表
scientific_data	Scientific Data (Nature)	3000	5+ 图，2+ 表
nature_communications	Nature Communications	5000	6+ 图，2+ 表
ieee_conference	IEEE Conference	4000 (6-8 页)	4+ 图
pnas	PNAS	5000	5+ 图

Usage

基本使用

# 生成完整论文
python paper_writing_workflow.py --template scientific_data --topic "AI psychology research"

# 生成特定部分
python paper_writing_workflow.py --section introduction --topic "AI psychology"

# 润色论文
python paper_writing_workflow.py --action polish --input draft.md --style APA

高级使用

# 指定阶段
python paper_writing_workflow.py --stage 3 --topic "AI psychology"  # 大纲设计

# 批量生成
python paper_writing_workflow.py --template ieee_conference --output-dir papers/

# 格式检查
python paper_writing_workflow.py --action check --input paper.md --template scientific_data

IMRAD Structure

Introduction (引言)

研究背景（宽）
文献综述（窄）
研究空白
研究问题
研究假设
研究意义

字数: 800-1200 字

Methods (方法)

研究设计
参与者
材料/工具
程序
数据分析

字数: 1000-1500 字

Results (结果)

描述统计
推断统计
图表展示
效应量报告

字数: 1000-1500 字

Discussion (讨论)

主要发现总结
与现有研究对比
理论贡献
实践意义
局限性
未来方向

字数: 1500-2000 字

Quality Checks

结构检查

IMRAD 结构完整
各部分字数符合要求
图表数量符合要求
参考文献数量充足（30-50 篇）

内容检查

研究问题明确
方法详细可重复
结果客观准确
讨论深入全面
结论简洁有力

格式检查

引用格式正确
参考文献列表完整
图表格式规范
字数符合要求
DOI 包含

Best Practices

写作建议

先写再改
- 初稿不求完美
- 完成比完美重要
- 多次修改润色
图表驱动
- 先规划图表
- 图表引导写作
- 确保质量
文献支撑
- 充分文献搜索
- 引用关键文献
- 避免过度引用
寻求反馈
- 导师审阅
- 同行评议
- 多次修改

避免错误

结构问题
- ❌ 缺少关键部分
- ✅ 遵循 IMRAD 结构
内容问题
- ❌ 方法不详细
- ✅ 详细到可重复
引用问题
- ❌ 格式不一致
- ✅ 使用引用管理工具
语言问题
- ❌ 口语化表达
- ✅ 学术风格

Integration

与文献搜索配合

literature-search-workflow: 负责文献搜索
paper-parse: 负责论文解析
paper-writing-workflow: 负责论文写作

与图表生成配合

scientific-schematics: 负责技术图表
scientific-visualization: 负责数据图表
paper-writing-workflow: 负责整合到论文

Examples

示例 1: 生成 Scientific Data 论文

python paper_writing_workflow.py \
  --template scientific_data \
  --topic "CPWBD-2025: A National Wellbeing Dataset from China" \
  --output paper.md

输出:

完整论文草稿
参考文献列表
图表清单
格式检查报告

示例 2: 润色论文

python paper_writing_workflow.py \
  --action polish \
  --input draft.md \
  --output polished.md \
  --style APA

输出:

润色后论文
修改建议
格式检查报告

References

Scientific Data: https://www.nature.com/sdata/
Nature Communications: https://www.nature.com/ncomms/
IEEE: https://ieeeauthorcenter.ieee.org/
APA Style: https://apastyle.apa.org/

技能版本: v1.0.0
创建时间: 2026-03-14
维护者: academic-assistant
下次更新: 功能改进时

完整论文写作，从工作流开始！📝✨

安全使用建议

This skill appears to do what it says: a local workflow and helper script for drafting and formatting academic papers. Before installing, note two items: (1) the SKILL.md CLI examples use flag-style arguments but the included script accepts positional arguments (topic, template, action) — either call it as a positional CLI or edit the script to accept flags; (2) the skill expects other skills (literature-search-workflow, academic-writing, etc.) to be available for full automation — verify you trust and have those skills, because this package will instruct you to call them even though it doesn't fetch or manage their credentials. The script writes files to the current directory; review the code if you need different behavior. No credentials or network downloads are requested by this package.

功能分析

Type: OpenClaw Skill Name: paper-writing-workflow Version: 1.0.0 The skill bundle provides a legitimate workflow for academic paper writing, including stage management and outline generation. The primary script, scripts/paper_writing_workflow.py, performs standard file operations and console output without any indicators of data exfiltration, malicious execution, or unauthorized access.

能力评估

✓ Purpose & Capability

Name, description, openclaw.skill.json metadata, SKILL.md, and the included Python script all describe a paper‑writing workflow and templates; required skills listed (literature search, citation management, scientific writing, etc.) are consistent with that purpose.

ℹ Instruction Scope

SKILL.md instructs the agent/user to use other writing/search/visualization skills and shows CLI examples. The included script implements basic workflow/output behavior (outline generation, printing stages) and writes files to the current directory. However, SKILL.md examples use long-form flags (--template, --topic, --action) while the provided script only parses positional arguments (topic, template, action), an inconsistency that will cause the example invocations to fail unless the script is modified. The instructions do not attempt to read secrets or other unrelated files.

✓ Install Mechanism

This is instruction-only with a small helper script and no install spec; nothing is downloaded or written by an installer and there is no remote code fetch.

✓ Credentials

No environment variables, credentials, or config paths are requested. The skill does reference other skills it expects to be present but does not request access to unrelated credentials or secrets.

✓ Persistence & Privilege

always is false (normal). The skill does not modify other skills or system configuration; it only writes output files to the current working directory when generating outlines.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install paper-writing-workflow
安装完成后，直接呼叫该 Skill 的名称或使用 /paper-writing-workflow 触发
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

Complete paper writing workflow with 6 stages: topic selection, literature review, outline design, draft writing, figure generation, and polishing. Supports Scientific Data/Nature/IEEE/PNAS templates.

元数据

Slug paper-writing-workflow

版本 1.0.0

许可证 MIT-0

累计安装 7

当前安装数 7

历史版本数 1

常见问题