Agent skill

Thesis Creator

by Stars-OC in Stars-OC/thesis-creator

Walks Chinese undergraduates through writing a graduation thesis from topic to Word export, with text-similarity reduction and AI-text rate rewriting and checks.

MITAuto-check passedEducation

SKILL.md written in Chinese; this summary is our English description.

Install Thesis Creator

skills CLI
$ npx skills add Stars-OC/thesis-creator --skill thesis-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Stars-OC/thesis-creator thesis-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
thesis-creator
GitHub stars
230
Token cost
~2.8k tokens
SKILL.md length
685 words
Files
189 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Walks Chinese undergraduates through writing a graduation thesis from topic to Word export, with text-similarity reduction and AI-text rate rewriting and checks.

  • Works in 5 steps: Step 0 初始化后:必须先运行 python… → Step 3 大纲确认后:必须先询问用户文献数量(20-30 / 30-50 /… → Step 4 每章写作时:必须先完成 Stage 1… → …
  • Writing an undergraduate graduation thesis from topic to final draft
  • SKILL.md covers 核心原则, 触发条件, 工作流程概览 and 继续与暂停点规则, plus 8 more sections
  • Calls python

What it does

This is a Chinese-language workflow for undergraduate graduation theses. It works inside a thesis-workspace/ folder in your project and moves through numbered steps: initialize the workspace, prepare, outline, write chapters, merge, review and polish, generate figures and export to Word. Trigger phrases map to steps, so asking for an outline runs only the early steps, a similarity-reduction request runs only step 5, and an AI-rate request runs step 6.

Quality gates make the flow strict. A continue reply does not skip an unfinished check, the outline must be confirmed before a literature search builds a reference pool, each chapter is planned and confirmed before it is expanded, duplicate citations block the AIGC check, and a failed check sends the text back to rewriting. Figures come from dot, mmd and puml source files rendered to PNG by scripts. Progress is kept in a JSON status file, with Python scripts for the lifecycle and a YAML config. The description also lists local AIGC detection.

When your agent uses it

  • Writing an undergraduate graduation thesis from topic to final draft
  • Reducing text similarity in a passage before submission
  • Rewriting a passage to lower its AIGC rate
  • Generating a thesis outline or abstract
  • Exporting a finished thesis to Word

Example prompts

  • “帮我写论文,主题是校园二手交易平台的设计与实现”
  • “Generate an outline for my thesis on a campus second-hand marketplace app.”
  • “Lower the AIGC rate of this paragraph and show your plan before rewriting.”
  • “Export the finished thesis to Word.”

Requirements

  • Python, for the bundled workspace and chart scripts
  • A project directory where a thesis-workspace/ folder can be created

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Step 0 初始化后:必须先运行 python scripts/core/lifecycle.py --workspace thesis-workspace/ --check-workspace,并检查…
  2. Step 3 大纲确认后:必须先询问用户文献数量(20-30 / 30-50 / 15-20),并展示搜索耗时预估后,进入 Step 3→4 之间的“文献搜索与建池”阶段;该阶段不是独立 Step,但后续在 Step 4/6/7…
  3. Step 4 每章写作时:必须先完成 Stage 1 要点规划,待用户确认后才能进入 Stage 2 扩写;如果当前仍停留在 Stage 1,用户回复「继续」只能视为确认本章要点,不能跳过更早的未完成门禁。
  4. Step 7 合并检测后:若同一 ref_id 在终稿中重复出现,必须硬阻断并回退修正,禁止带重复引用进入 AIGC 检测;若 AIGC 检测未通过,必须回退到 Step 5/6 继续改写与审校,禁止进入 Step 8 图片生成或 Step 9 导出。
  5. Step 8 图片生成前:必须按“抽取图片需求 → 准备源码文件 → 大模型填写 .dot/.mmd/.puml → 渲染 PNG → 回填 [image_N] → 完整性验证”执行;使用…

What it can do on your machine

Read from SKILL.md and the folder at commit edf95df. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Thesis Creator loads about 2.8k tokens when it runs, and up to ~12k if it reads all its reference files. Until then it costs about 24 tokens; SKILL.md has 685 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~2.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~12k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from Stars-OC/thesis-creator at commit edf95df, republished under its MIT licence (© Stars-OC). 685 words, ~2,773 tokens.

Download SKILL.mdSave it as .claude/skills/thesis-creator/SKILL.md (or your agent's skills folder). This skill also uses 188 other files; get the full folder from GitHub.
name
thesis-creator
description
面向中国本科生的毕业论文全流程写作辅助系统。支持从选题到交稿的端到端工作流,包含降重优化、AIGC 降低和本地检测功能。用户说「帮我写论文」或「帮我降重」等时触发。

论文创作 Agent 系统

面向中国本科生的毕业论文全流程写作辅助系统。


核心原则

[!IMPORTANT] 工作区隔离原则:AI 始终在用户项目目录下的 thesis-workspace/ 工作。所有产出文件都在用户工作区内。


触发条件

触发语执行动作
「帮我写论文,主题是…」全流程(Step 0-9)
「帮我降重这段文字:…」仅 Step 5
「降低这段的 AIGC 率:…」仅 Step 6:必须输出“处理前计划 → 改写文本 → 清单自检”,并按场景化重写、自然承接、轻冗余控制和高密度句拆解处理,不得只给改写结果
「检测这段文字的 AIGC 率」AIGC 检测
「帮我生成论文大纲」Step 0-3
「初始化工作区」Step 0(工作区不存在直接初始化)
「继续」仅在当前步骤的强制交互点、前置校验和质量门禁均已满足后继续流程
「生成摘要」Step 4(仅摘要部分)
「生成图片」「生成图表」Step 8
「导出 Word」「导出文档」Step 9
「一键导出」Step 8+9

工作流程概览

mermaid
flowchart LR
    A[Step 0: 初始化] --> B[Step 1-2: 准备]
    B --> C[Step 3: 大纲]
    C --> D[Step 3→4: 文献搜索与建池]
    D --> E[Step 4: 撰写]
    E --> F[Step 5-6: 降重]
    F --> G[Step 7: 合并检测]
    G --> H[Step 8: 图片生成]
    H --> I[Step 9: 导出Word]

⚠️ 流程顺序:大纲确认 → 文献搜索与建池 → 正文写作 → 合并 → 图片生成 → 导出 Word 状态文件路径:thesis-workspace/.thesis-status.json 若文件不存在,status_manager.py 会自动创建。

推荐统一入口:scripts/core/lifecycle.py(整合日志 + 状态管理)


继续与暂停点规则

[!IMPORTANT] 「继续」不是跳过按钮。 若当前流程仍存在强制交互点、前置校验或质量门禁未完成,则必须先完成对应动作,再允许进入下一步。

不可跳过的暂停点
  1. Step 0 初始化后:必须先运行 python scripts/core/lifecycle.py --workspace thesis-workspace/ --check-workspace,并检查 thesis-workspace/references/prompt/background.md 是否已补全;工作区必须通过脚本初始化并从 config/.thesis-config.yaml 复制生成 thesis-workspace/.thesis-config.yaml,同时生成 thesis-workspace/.thesis-status.json、thesis-workspace/logs/、thesis-workspace/scripts/charts/render.py、thesis-workspace/workspace/final/images/sources 与 thesis-workspace/workspace/references/images.yaml;未完成时只能提示用户编辑,禁止直接推进到 Step 1/3。
  2. Step 3 大纲确认后:必须先询问用户文献数量(20-30 / 30-50 / 15-20),并展示搜索耗时预估后,进入 Step 3→4 之间的“文献搜索与建池”阶段;该阶段不是独立 Step,但后续在 Step 4/6/7 中如发现文献不足、语种比例失衡或文献失效,必须允许回流补池后再继续写作或检测。
  3. Step 4 每章写作时:必须先完成 Stage 1 要点规划,待用户确认后才能进入 Stage 2 扩写;如果当前仍停留在 Stage 1,用户回复「继续」只能视为确认本章要点,不能跳过更早的未完成门禁。
  4. Step 7 合并检测后:若同一 ref_id 在终稿中重复出现,必须硬阻断并回退修正,禁止带重复引用进入 AIGC 检测;若 AIGC 检测未通过,必须回退到 Step 5/6 继续改写与审校,禁止进入 Step 8 图片生成或 Step 9 导出。
  5. Step 8 图片生成前:必须按“抽取图片需求 → 准备源码文件 → 大模型填写 .dot/.mmd/.puml → 渲染 PNG → 回填 [image_N] → 完整性验证”执行;使用 scripts/charts/manifest_builder.py、source_writer.py、render.py、markdown_updater.py、validate.py,最终已渲染 AI 图片不得残留 [image_N]。

详细步骤(按需加载)

步骤说明详细文档
Step 0工作区初始化workflows/step_0_init.md
Step 3生成论文大纲workflows/step_3_outline.md
Step 4分章节撰写workflows/step_4_writing.md
Step 6审校润色workflows/step_6_review_polish.md
Step 7合并与检测workflows/step_7_merge_detect.md
Step 8图片生成与渲染(ER图默认读取 background.md,优先输出教科书风格 DOT,信息不足时尽量生成并 warning)workflows/step_8_image.md
Step 9文档导出workflows/step_9_export.md
参考文献文献池管理workflows/reference_workflow.md

参考文献(独立存放)

核心改进:文献池独立存放在 workspace/references/verified_references.yaml 文献校验状态:verified_doi / verified_metadata_only / broken_doi_metadata_ok / missing_doi_unverified / invalid_reference 规则说明:无 DOI 不等于假文献;允许通过元数据验证的真实文献继续进入文献池。

图片需求清单
  • 正文图片占位符统一使用 [image_1]、[image_2] 等格式
  • 图片需求清单统一记录到 workspace/references/images.yaml
  • workspace/references/images.yaml 必须采用结构化字段,至少包含 id、title、chapter、section、source、diagram_type、engine、purpose、fact_source、placement、status、description、source_file、output_file、render_status;可选 prompt_hint 用于指导大模型生成源码,dot_mode 可用于单图覆盖 ER 的 DOT 子模式
  • Step 4 只负责记录 [image_N] 与 image-requirement 图片需求块,Step 8 再生成 images.yaml、准备源码文件、由大模型填写 .dot/.mmd/.puml、渲染 PNG 并回填 Markdown 图片引用
  • 架构图、模块图、流程图、ER 图等 AI 图片必须先有 manifest 记录;用户提供图片必须在清单中标明 source=user 和待补状态
  • 图表引擎按图类型明确映射,不自由摇摆:流程图/活动图/用例图/时序图/类图 → PlantUML (.puml);ER 图由 .thesis-config.yaml 的 er_modeling.graph_type 决定,默认 Graphviz DOT (.dot) 教科书 Chen 风格,erd 时输出 Mermaid erDiagram;diagram_type=overall_er 必须第一个展示,且仅展示实体、联系与 1:1 / 1:N 基数,关系菱形节点必须结合外键字段或实体语义命名,如“拥有”“包含”,不得统一写成“关联”,且不展示字段;diagram_type=entity_er 可通过 .thesis-config.yaml 的 er_modeling.dot_mode=textbook-single-entity-ring 或 images.yaml 单图 dot_mode 启用单实体字段环绕 DOT,优先级为单图覆盖全局;架构图 → 用户自行生成/GPT image 后补入 (source=user);模块图 → Mermaid (.mmd);用户截图 → user
  • 仅当流程图使用 PlantUML 生成时,必须附加固定提示词模板,并将其中主题替换为当前图表标题或用途描述:
text
请生成一个用于毕业论文的PlantUML流程图,主题为“{{图表主题}}”。要求:

- 使用activity diagram
- 所有节点使用中文
- 起止节点使用“开始”“结束”
- 逻辑严谨,体现完整业务流或上下文流转机制
- 包含必要循环(如存在用户持续操作、重试或追问)
- 避免语法歧义(防止被解析为class diagram)
- 图结构简洁,不超过3层嵌套
- 判断分支连线必须明确标注 Y/N
- 全图只保留一个最终结束节点,所有分支和普通路径最终汇入该结束节点
- 适合论文插图展示

只输出PlantUML代码。
  • 不再默认使用 Mermaid 流程图;普通流程图同样优先走 PlantUML。
  • 生成测试图或单独响应“生成流程图”类指令时,默认行为是将源码写入 thesis-workspace/workspace/final/images/sources/ 对应 .puml/.dot/.mmd 文件,而不是在控制台直接输出完整图表源码;仅在用户明确要求“只输出代码”时,才直接返回源码文本。
流程
  1. Step 3 大纲确认后询问文献数量(默认 20-30 篇)
  2. 多源搜索:Semantic Scholar + CrossRef + OpenAlex
  3. DOI 验证:判断 4xx 错误状态码
  4. 合并去重:多源结果合并,按相关度选出最相关 x 篇(scripts/references/reference_merger.py)
  5. 写作时从文献池选取未占用引用
  6. 文献搜索与建池阶段可回流复用:在 Step 4/6/7 任一阶段,如果当前章节缺少可用未占用文献、文献验证失败、语种比例不达标或引用密度不足,必须回到该阶段补充搜索,并增量更新 workspace/references/verified_references.yaml
  7. 单篇文献整篇仅允许引用一次:一旦某个 ref_id 被正文使用一次,就必须标记为已占用,后续章节不得重复使用;Step 7 发现重复 ref_id 必须硬阻断
  8. 中文文献质量不足时提示人工补充:若自动源无法满足中文文献占比 >65%,必须提示用户从 CNKI、万方、学校图书馆等外部高质量来源人工补充真实中文文献,禁止伪造
  9. 文献 YAML 输出必须安全可解析:标题含英文冒号、中文冒号、括号等特殊字符时,仍必须能被 yaml.safe_load() 读取

详见 workflows/reference_workflow.md


用户工作区目录结构

thesis-workspace/
├── README.md                  # 工作区使用说明
├── .thesis-config.yaml        # 配置文件
├── references/                # 参考资料(用户放入)
│   ├── templates/             # 学校模板
│   ├── examples/              # 范文
│   ├── guidelines/            # 规范
│   └── prompt/background.md   # 论文背景(必填)
├── workspace/                 # 论文产出
│   ├── outline.md             # 大纲
│   ├── references/                # 参考文献池(独立)⭐
│   │   ├── verified_references.yaml  # 已验证文献池
│   ├── cited_references.json  # 引用记录(每章引用的ref_id)⭐
│   ├── drafts/                # 初稿(仅含临时引用编号,无参考文献列表)⭐
│   │   ├── 参考文献.md         # 合并阶段生成的参考文献(独立MD文件,GB/T 7714格式)⭐
│   ├── final/                 # 终稿
│   │   ├── 论文终稿.md         # 终稿(引用编号已重排)
│   │   ├── 论文终稿.docx
│   │   └── images/            # 图片
│   └── reports/               # 报告
├── logs/                      # 日志
└── .thesis-status.json        # 状态

⭐ 标记为本次更新新增或变更的文件


Markdown 标题输出硬约束(Markdown→Word 映射)

[!IMPORTANT] 生成的 Markdown 必须能被 Pandoc / python-docx / markdown-it / Typora / VSCode Markdown 正确识别,并映射为 Word Heading 1~4,支持自动目录、导航窗格、标题折叠和大纲视图。

标题生成规则
Markdown 语法Word 映射说明
# 标题名称Heading 1章级标题(摘要、第N章、结论等)
## 标题名称Heading 2节级标题(1.1、4.2 等)
### 标题名称Heading 3小节级标题(1.2.1、4.4.1 等)
#### 标题名称Heading 4段级标题(5.2.1 等)

格式硬约束:标题符号 # 后必须保留一个空格。正确:## 研究背景;错误:##研究背景。

禁止行为(标题模拟禁令)

以下方式视为格式错误,禁止用于模拟标题层级:

禁止方式说明
加粗文本**第一章 绪论** 不是标题
序号+普通段落1.1 研究背景 无 ## 不是标题
列表项- 第一章 绪论 不是标题
表格标题表格内文字不是标题
单纯放大字体HTML <font size> 不是标题
中文符号模拟层级===系统设计=== 不是标题
HTML 标签<h1> 等不是标题
Show full SKILL.md (269 more words)Show less
层级约束

标题必须满足严格层级结构,禁止跨级跳跃:

正确:# → ## → ### → ####
错误:# → ###(跳过 ##)
论文结构标题示例
markdown
# 摘要

# Abstract

# 第一章 绪论

## 1.1 研究背景

## 1.2 国内外研究现状

# 第二章 系统分析

# 第三章 系统设计

# 第四章 系统实现

# 第五章 测试与分析

# 结论

# 参考文献
输出约束
  1. 输出必须是纯 Markdown 正文
  2. 禁止用 markdown 代码块包裹正文内容
  3. 不要输出解释性文字(如"以下是论文内容")
  4. 不要输出提示语
兼容性要求

生成结果必须兼容 Markdown → docx 转换流程,确保通过 pypandoc.convert_file() 或 python-docx 转换后能自动生成 Word 目录。

最终目标

导出的 docx 文档必须满足:

  • Word「引用 → 目录」可自动生成目录
  • Word「导航窗格」可显示章节树
  • 标题可折叠
  • 标题具备大纲级别
  • Heading 1~4 自动识别

防错机制

问题影响处理
缺少规定动作章节致命自动补充
设计实现未分离致命强制拆分
章节顺序错误致命强制调整为:系统分析→系统设计→系统实现→系统测试→总结与展望
使用 LLM 上下文合并文档致命必须使用 merge_drafts.py 脚本
图表不足严重提示补充
数据库表数量不足严重检查 background.md 表定义,确保 ≥11 张表
未执行状态管理脚本致命每个 Step 必须通过 lifecycle.py 或 status_manager.py 记录状态,禁止大模型自行维护状态
日志未通过脚本记录严重所有流程日志必须通过 logger.py 输出,禁止大模型自行生成日志内容
文献链接 404严重合并前执行 reference_validator.py --check-404,404文献必须替换
图片文件缺失严重Step 8 完成后检查 images/ 目录,所有占位符必须有对应 PNG 文件
参考文献虚构严重DOI验证+重生成
参考文献数量超标严重按相关度截取
参考文献缺少中英文严重中文和英文文献都必须包含,缺少则触发补充搜索
参考文献 YAML 解析失败严重reference_merger.py 必须使用安全 YAML 输出,特殊字符标题保存后仍可 yaml.safe_load()
中文文献比例不足严重自动源不足时提示从 CNKI、万方、学校图书馆人工补充真实中文文献,禁止伪造
引用复用同一 ref_id严重同一篇文献整篇仅允许引用一次,发现重复占用必须硬阻断并回流补池改写引用
AI模板词超标中等按 Step 6 的 AIGC 标准流程处理:先做处理前计划,再按”场景化重写 → 结构重组 → 细节注入 → 自然承接与轻冗余 → 高密度句拆句解释 → 语言去模板化”改写,最后输出清单自检;禁止只做同义替换、删词式压缩或只给改写结果
标题未使用 Markdown # 语法致命所有标题必须用 # / ## / ### / ####,禁止加粗文本/序号段落/中文符号模拟标题
标题层级跳跃严重禁止跨级(如 #→###),必须逐级(#→##→###→####)
标题符号后无空格严重#标题 必须修正为 # 标题,符号后必须保留一个空格
AIGC 降低缺少自检清单严重必须补齐处理前计划、改写文本、自检表;自检项出现“未通过”时继续局部修正,不得交付为最终版
章节内自建参考文献列表中等删除,合并阶段统一生成
background.md 为空或未完善致命提示用户编辑 thesis-workspace/references/prompt/background.md,禁止控制台交互式输入
ER 图事实源不一致严重Step 8 的 ER 图默认读取 background.md,仅 ER 图受 thesis-workspace/.thesis-config.yaml 的 er_modeling 配置影响;默认输出教科书 Chen 风格 DOT(实体矩形、属性椭圆、联系菱形),总体 ER 图必须第一个展示,且只展示实体、联系与 1:1 / 1:N 基数;关系菱形节点必须结合外键字段或实体语义命名,如“拥有”“包含”,不得统一写成“关联”;DOT 输出不要显式使用 label=

Prompt 文件(写作时加载)

文件说明加载时机
prompts/writer_guidelines.md写作规范Step 4
prompts/aigc_reducer_prompt.mdAIGC 表达质量优化与深度人工化流程,按场景化重写、自然承接、轻冗余控制和高密度句拆句解释执行Step 6
prompts/humanizer_guidelines.md人工化改写细则与风险边界,约束自然过渡、轻冗余和拆句解释不得破坏学术语体Step 6
prompts/reference_citation_prompt.md引用铁律Step 4
workspace/references/verified_references.yaml文献池必须加载

Script 文件

文件说明
scripts/references/reference_engine.py多源搜索 + DOI验证
scripts/references/reference_merger.py文献合并去重 + 选出最相关 x 篇
scripts/document_exporter/Word导出 + 图片插入
scripts/content/merge_drafts.py章节合并
scripts/aigc/detect.pyAIGC检测
scripts/aigc/technical_detect.py技术论文 AIGC 检测
scripts/charts/manifest_builder.py从正文 [image_N] 与 image-requirement 生成或更新 images.yaml
scripts/charts/source_writer.py根据 images.yaml 准备并校验 .mmd/.dot/.puml 源码文件
scripts/charts/render.py按 Mermaid、Graphviz、PlantUML 渲染 PNG
scripts/charts/markdown_updater.py将已渲染图片回填为 Markdown 图片引用
scripts/charts/validate.py校验源码、PNG、占位符和用户待补截图状态

致谢

致谢生成位于 Step 4(与摘要同阶段),输出文件为 workspace/drafts/致谢.md,由 merge_drafts.py 在合并阶段自动纳入终稿。

注意:致谢不计入七章正文结构,但属于论文交付的必备内容之一。

© Stars-OC, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 188 other files (scripts, references) in the repository root of Stars-OC/thesis-creator.

  • SKILL.md
  • .gitignore
  • .openskills.json
  • CONTRIBUTING.md
  • LICENSE
  • README.md
  • config/.thesis-config.yaml
  • docs/CHANGELOG.md
  • docs/ROADMAP.md
  • docs/images/PaperPass.png
  • docs/images/diff.png
  • docs/images/paperYY.png
  • docs/images/全文朱雀检测.png
  • docs/plans/2026-06-01-docx-toc-design.md
  • docs/plans/2026-06-01-docx-toc.md
  • docs/usage_guide.md
  • prompts
  • … and 172 more

Open the folder on GitHubat commit edf95df

Compare with similar skills

Thesis Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Thesis Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Thesis Creator this skillStars-OC/thesis-creator230—~2.8kAutomated safety check: PassMIT
Aigc Detectorfree-revalution/AIGC-Detector-Pro142—~2.8kAutomated safety check: PassMIT
Canvas Awkward SyntaxX-isdoingreat/canvas-pilot125—~15kAutomated safety check: NotesAGPL-3.0
Autonomous Researchfedericodeponte/opendraft507—~8.2kAutomated safety check: PassApache-2.0
Synthesizeagentii-ai/agentii-investment-intelligence207—~3.2kAutomated safety check: PassApache-2.0
Thesis DOCXcatlog22/maestro-flow5641 repos~2.5kAutomated safety check: PassMIT

Similar skills

  • Aigc Detector

    free-revalution/AIGC-Detector-Pro

    Academic paper AI content detection, rewriting, and thesis writing assistant.

    142 GitHub stars~2.8k tokensUpdated 4 mo ago
    EducationAuto-check passed
  • Canvas Awkward Syntax

    X-isdoingreat/canvas-pilot

    Direct-commit syntactically-marked rewrite humanizer. An agent skill from X-isdoingreat/canvas-pilot.

    125 GitHub stars~15k tokensUpdated 2 mo ago
    EducationAuto-check: notes
  • Autonomous Research

    federicodeponte/opendraft

    An 18-agent pipeline that turns one topic line into a drafted research paper, literature review, or thesis chapter.

    507 GitHub stars~8.2k tokensUpdated 8 days ago
    Research & ScienceAuto-check passed
  • Synthesize

    agentii-ai/agentii-investment-intelligence

    Thesis report synthesis — turn a thesis's markdown artifacts into its letter-size thesis-report.html, then OPTIMIZE it against real page renders.

    207 GitHub stars~3.2k tokensUpdated 11 days ago
    EducationAuto-check passed
  • Thesis DOCX

    catlog22/maestro-flow

    Create, revise, and format thesis or dissertation Word documents with strict academic formatting control.

    564 GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed
  • Latex Thesis Zh

    brycewang-stanford/Auto-Empirical-Research-Skills

    Chinese LaTeX thesis assistant for existing .tex degree thesis projects (XeLaTeX/LuaLaTeX/latexmk).

    4.6k GitHub stars~1.5k tokensUpdated 5 days ago
    Documents & OfficeAuto-check passed

Questions about Thesis Creator

What does Thesis Creator do?

Walks Chinese undergraduates through writing a graduation thesis from topic to Word export, with text-similarity reduction and AI-text rate rewriting and checks. This is a Chinese-language workflow for undergraduate graduation theses. It works inside a thesis-workspace/ folder in your project and moves through numbered steps: initialize the workspace, prepare, outline, write chapters, merge, review and polish, generate figures and export to Word.

When should I use Thesis Creator?

Thesis Creator fits situations like: writing an undergraduate graduation thesis from topic to final draft; reducing text similarity in a passage before submission; rewriting a passage to lower its AIGC rate; generating a thesis outline or abstract.

How do I install Thesis Creator in Claude Code?

Run `npx skills add Stars-OC/thesis-creator --skill thesis-creator -a claude-code`. Or copy the skill folder (the Stars-OC/thesis-creator repository) into .claude/skills/thesis-creator in your project. Claude Code loads it when a task matches its description.

How do I install Thesis Creator in Codex?

Run `npx skills add Stars-OC/thesis-creator --skill thesis-creator -a codex`. Or copy the skill folder (the Stars-OC/thesis-creator repository) into .agents/skills/thesis-creator in your project. Codex loads it when a task matches its description.

Can I use Thesis Creator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Stars-OC/thesis-creator --skill thesis-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/thesis-creator, .gemini/skills/thesis-creator, .github/skills/thesis-creator and .opencode/skills/thesis-creator in your project.

What does Thesis Creator need to run?

Going by SKILL.md and its folder, Thesis Creator needs the command-line tools its instructions call (python). Our summary lists: Python, for the bundled workspace and chart scripts; A project directory where a thesis-workspace/ folder can be created.

Does Thesis Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Thesis Creator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Thesis Creator use?

Thesis Creator is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Thesis Creator use?

About 2.8k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.2k tokens, read only when the agent opens those files.

What are the alternatives to Thesis Creator?

Skills that share tags, products or a category with Thesis Creator: Aigc Detector (free-revalution/AIGC-Detector-Pro, 142 stars), Canvas Awkward Syntax (X-isdoingreat/canvas-pilot, 125 stars), Autonomous Research (federicodeponte/opendraft, 507 stars) and Synthesize (agentii-ai/agentii-investment-intelligence, 207 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Thesis Creator?

Stars-OC (a GitHub user) maintains it in Stars-OC/thesis-creator, which has 230 GitHub stars. The repository was last updated on June 2, 2026.

Source: Stars-OC/thesis-creator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.