Aigc Detector
free-revalution/AIGC-Detector-Pro
Academic paper AI content detection, rewriting, and thesis writing assistant.
Guides the writing of a Chinese master's thesis and generates the Word file from a template, only when you invoke it by name.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Jinze-Lee/codex-skills-workbench master-thesis-studio-skill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Jinze-Lee/codex-skills-workbench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/master-thesis-studio-skill .claude/skills/master-thesis-studio-skill && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "master-thesis-studio-skill" agent skill from https://github.com/Jinze-Lee/codex-skills-workbench/tree/main/skills/master-thesis-studio-skill into .claude/skills/master-thesis-studio-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "master-thesis-studio-skill", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Jinze-Lee/codex-skills-workbench/tree/main/skills/master-thesis-studio-skillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Jinze-Lee/codex-skills-workbench master-thesis-studio-skill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Jinze-Lee/codex-skills-workbench.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/master-thesis-studio-skill .agents/skills/master-thesis-studio-skill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "master-thesis-studio-skill" agent skill from https://github.com/Jinze-Lee/codex-skills-workbench/tree/main/skills/master-thesis-studio-skill into .agents/skills/master-thesis-studio-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "master-thesis-studio-skill", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Jinze-Lee/codex-skills-workbench master-thesis-studio-skill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Jinze-Lee/codex-skills-workbench.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/master-thesis-studio-skill .cursor/skills/master-thesis-studio-skill && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "master-thesis-studio-skill" agent skill from https://github.com/Jinze-Lee/codex-skills-workbench/tree/main/skills/master-thesis-studio-skill into .cursor/skills/master-thesis-studio-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "master-thesis-studio-skill", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Jinze-Lee/codex-skills-workbench.git --path skills/master-thesis-studio-skill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Jinze-Lee/codex-skills-workbench master-thesis-studio-skill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Jinze-Lee/codex-skills-workbench.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/master-thesis-studio-skill .gemini/skills/master-thesis-studio-skill && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "master-thesis-studio-skill" agent skill from https://github.com/Jinze-Lee/codex-skills-workbench/tree/main/skills/master-thesis-studio-skill into .gemini/skills/master-thesis-studio-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "master-thesis-studio-skill", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Jinze-Lee/codex-skills-workbench master-thesis-studio-skillInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Jinze-Lee/codex-skills-workbench.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/master-thesis-studio-skill .github/skills/master-thesis-studio-skill && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "master-thesis-studio-skill" agent skill from https://github.com/Jinze-Lee/codex-skills-workbench/tree/main/skills/master-thesis-studio-skill into .github/skills/master-thesis-studio-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "master-thesis-studio-skill", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Jinze-Lee/codex-skills-workbench master-thesis-studio-skill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Jinze-Lee/codex-skills-workbench.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/master-thesis-studio-skill .opencode/skills/master-thesis-studio-skill && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "master-thesis-studio-skill" agent skill from https://github.com/Jinze-Lee/codex-skills-workbench/tree/main/skills/master-thesis-studio-skill into .opencode/skills/master-thesis-studio-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "master-thesis-studio-skill", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
master-thesis-studio-skillGuides the writing of a Chinese master's thesis and generates the Word file from a template, only when you invoke it by name.
This opt-in skill splits thesis work into two layers. The writing layer interviews you about topic, outline, chapter plan, asset list and writing limits, and drafts in Chinese academic style. The Word and XML layer uses bundled Python scripts to write chapter Markdown into Flat OPC XML and build a new DOCX. It activates only when you name it explicitly, not for general thesis, formatting or Word requests.
The rules in the excerpt: new titles, headings and body text default to Chinese; the agent must not invent references, results, sample sizes or data sources and writes placeholders such as 'to be added' instead; the original Word template is never overwritten, new DOCX files go to `10_output/` and XML intermediates to `09_state/`. The built-in template is `examples/Template.docx`, and your own `.docx` or `.dotx` can be passed with `--template`. Each thesis lives in its own project folder, and chapters, placeholders, references, figures and state files are checked for consistency before anything is written back to Word.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 7aa34a5. It shows what the files ask for, not the result of running them.
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.
Ships 5 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Master Thesis Studio loads about 3.5k tokens when it runs, and up to ~9.8k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 744 words of instructions outside code blocks.
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.
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.
The full file from Jinze-Lee/codex-skills-workbench at commit 7aa34a5, republished under its MIT licence (© Jinze-Lee). 744 words, ~3,484 tokens.
.claude/skills/master-thesis-studio-skill/SKILL.md (or your agent's skills folder). This skill also uses 29 other files; get the full folder from GitHub.Most instructions in this skill are Chinese and all Markdown/JSON files are UTF-8. If Chinese text appears garbled, do not edit or reason from the garbled output. Re-read files with an explicit UTF-8 command:
python -c "from pathlib import Path; import sys; sys.stdout.reconfigure(encoding='utf-8'); print(Path('SKILL.md').read_text(encoding='utf-8'))"For short targeted reads, prefer Python over PowerShell Get-Content:
python -c "from pathlib import Path; p=Path('references/writing_workflow.md'); print(p.read_text(encoding='utf-8'))"Load only the needed reference file. Do not bulk-read every Markdown file unless the task is a full Skill audit.
This skill is opt-in only.
$master-thesis-studio-skill, or explicitly says to use the master-thesis-studio-skill / Master Thesis Studio skill..docx, academic writing, formatting, or document generation.这是一个面向中文硕士论文写作与 Word 自动生成的显式调用 Skill。它把论文写作流程拆成两层:
除非用户明确要求快速演示,否则必须先确认项目事实和写作边界,再写正文或生成 Word。
01_template/original_template.docx。examples/Template.docx;用户模板支持 .docx 和 .dotx。examples/Template.docx;如果用户提供模板路径,必须把该路径传给 --template。10_output/。XML 中间态只写入 09_state/。.;调用脚本时使用 Skill 中 scripts/ 的绝对路径,或明确从 Skill 根目录传入项目绝对路径。references/ 文件。第一次使用本 Skill 时,不要直接写论文。先用简短问题确认:
examples/Template.docx,还是用户上传/指定的 Word .docx 或 .dotx 模板。确认结果必须同步写入:
00_project/project_manifest.md00_project/thesis_master_index.md00_project/decisions_log.md09_state/project_state.json| 阶段 | 先阅读什么 | 更新或生成什么 | 执行什么脚本 |
|---|---|---|---|
| 0. 判断项目状态 | 项目根目录、00_project/、09_state/project_state.json、03_chapters/ | 判断是新项目、续写项目还是只需导出;如果是新项目,先创建独立项目文件夹并进入该文件夹 | 无 |
| 1. 初始化工作区 | 用户给定模板路径;未给定时默认模板 examples/Template.docx | 在当前论文项目文件夹内生成 00_project/、01_template/、03_chapters/、04_figures/、05_tables/、06_code/、07_data/、08_refs/、09_state/、10_output/ | 在项目文件夹内运行:python <skill_dir>/scripts/init_thesis_workspace.py .,或使用用户模板:python <skill_dir>/scripts/init_thesis_workspace.py . --template <word_template.docx> |
| 1A. 可选反解析已有 Word | 用户确认该 Word 是已有论文内容且希望抽取内容 | 03_chapters/ 章节草稿、04_figures/ 真实图片、05_tables/ 表格 .md/.csv、09_state/reverse_parse_assets.json、反解析报告 | python <skill_dir>/scripts/reverse_parse_docx.py <project_dir> --docx <user.docx> |
| 2. 转换模板 | 01_template/original_template.docx | 01_template/template.flat.xml | python scripts/flat_opc_converter.py toxml <input.docx> <output.xml> |
| 3. 解析模板结构 | references/xml_mapping_spec.md、01_template/template.flat.xml | 09_state/parsed_structure.json | python scripts/parse_template_xml.py <template.flat.xml> <parsed_structure.json> |
| 4. 生成项目控制文件 | references/writing_workflow.md、assets/project_state.schema.json | 00_project/*.md、初始 03_chapters/chXX_plan.md、03_chapters/chXX_draft.md、09_state/project_state.json | python scripts/generate_planning_files.py <project_dir> |
| 5. 启动问诊和资产盘点 | references/writing_workflow.md、已有 00_project/*.md、各资产 manifest | 更新 project manifest、master index、decisions log、figures/tables/code/data manifest | 通常无脚本,必要时手动编辑 Markdown |
| 6. 章节计划 | references/writing_workflow.md 的章节计划规则、00_project/thesis_master_index.md、相关资产 | 03_chapters/chXX_plan.md | 通常无脚本 |
| 7. 章节正文 Markdown | 03_chapters/chXX_plan.md、references/writing_workflow.md、references/placeholders.md、相关 08_refs/、06_code/、07_data/、04_figures/、05_tables/ | 03_chapters/chXX_draft.md 或兼容命名的 ch*.md | 通常无脚本 |
| 8. 参考文献处理 | references/reference_rules.md、08_refs/ | 规范化引用占位符和参考文献对象 | python scripts/reference_tools.py format <refs.json> --style "GB/T 7714" |
| 9. Markdown 写入 XML | references/placeholders.md、references/xml_mapping_spec.md、03_chapters/、09_state/project_state.json | 09_state/current_working.xml、XML 快照、09_state/current_content_manifest.json | python scripts/apply_markdown_to_xml.py <project_dir> --out 09_state/current_working.xml |
| 10. 生成 Word | 09_state/current_working.xml | 10_output/thesis_draft_v1.docx 或用户指定文件名 | python scripts/build_new_docx.py <project_dir> --name thesis_draft_v1.docx |
| 11. 校验输出 | references/xml_mapping_spec.md、09_state/current_working.xml、10_output/ | 确认 XML 是 Flat OPC、章节数正确、DOCX 可重建 | python scripts/validate_xml_docx.py <project_dir> |
00_project/project_manifest.md:项目事实、写作模式、用户状态、资产、缺失项和假设。00_project/thesis_master_index.md:总大纲、章节状态、术语表、开放问题。00_project/decisions_log.md:用户确认、重要假设、写作边界和变更记录。03_chapters/:章节计划和章节正文 Markdown。04_figures/figures_manifest.md:图片文件、图题、来源、章节映射、状态。05_tables/tables_manifest.md:表格/数据来源、表题、章节映射、状态。06_code/code_manifest.md:代码资产、可支撑的方法描述、实现细节和实验流程。07_data/data_manifest.md:数据集、实验结果、指标、日志和可支撑结论。08_refs/:参考文献、文献笔记、检索记录和引用元数据。09_state/project_state.json:脚本写回使用的结构化项目状态。09_state/current_working.xml:当前可生成 DOCX 的 Flat OPC XML。09_state/reverse_parse_assets.json:可选反解析生成的真实图、表资源清单和可用性标记。10_output/:最终生成的 DOCX。references/writing_workflow.md。[[FIG:...]]、[[TBL:...]]、[[EQ:...]]、[[SYM:...]]、[[REF:...]]、[[REF_FIG:...]]、[[REF_TBL:...]] 时,先读 references/placeholders.md。references/reference_rules.md。references/xml_mapping_spec.md。09_state/project_state.json 时,先读 assets/project_state.schema.json。推荐命名:
03_chapters/ch01_plan.md03_chapters/ch01_draft.md03_chapters/ch02_plan.md03_chapters/ch02_draft.md兼容命名:
03_chapters/ch1_intro.md03_chapters/ch2_literature.md03_chapters/ch3_method.md03_chapters/ch4_experiments.md03_chapters/ch5_conclusion.mdscripts/apply_markdown_to_xml.py 的读取规则:
03_chapters/ch*_draft.md。_draft.md,读取 03_chapters/ch*.md,但排除 *_plan.md。#、##、### 重建一级、二级、三级标题结构。# 第X章 标题 只作为文件导航,写入 Word 时不会作为正文段落重复写入。新生成章节正文时使用中文标题,结构如下:
# 第1章 绪论
<!-- chapter_id: ch_1 -->
## 1.1 研究背景
这里写中文正文。正文应说明问题背景、研究意义和已有材料依据。
## 1.2 国内外研究现状
这里写中文正文。需要引用但暂无文献时,使用 [[REF:KEYWORD_PLACEHOLDER: 关键词]]。
### 1.2.1 某类方法
这里写三级小节正文。
## 1.3 本文主要工作
- 使用中文列出本文工作。
- 不写没有依据的实验指标。章节 Markdown 的规则:
Chapter 1 Introduction 这类英文标题,除非用户明确要求英文论文。##,三级标题使用 ###。不要在正文段落里伪造标题。第1章、1.1 方便阅读;写入 Word 时默认去掉手动编号,避免模板自动编号重复。chXX_draft.md。章节目标、素材、待补问题写入 chXX_plan.md,不要混在正文草稿里。写正文时使用这些占位符,不要硬编码编号:
[[FIG:图的稳定描述]]:生成图片占位和图题。[[TBL:表的稳定描述]]:生成表题和真实 Word 表格。[[EQ:公式]]:生成显示公式和章内编号。[[SYM:公式或符号]]:生成行内数学符号。[[REF:n]]:生成参考文献交叉引用。[[REF:KEYWORD_PLACEHOLDER: 关键词]]:文献未补齐时的临时引用。[[REF_FIG:图的稳定描述]]:正文中引用图。[[REF_TBL:表的稳定描述]]:正文中引用表。[[CODE:路径或说明]]:标记代码资产需求。[[DATA:路径或说明]]:标记数据资产需求。[[TABLE:...]]、[[FIGURE:...]]、[[EQUATION:...]] 可以被脚本兼容为 [[TBL:...]]、[[FIG:...]]、[[EQ:...]],但新写内容必须使用标准形式。
references/writing_workflow.md,确认题目、方法、创新点、真实性边界,再生成大纲、计划和中文初稿。03_chapters/、04_figures/、05_tables/ 后,再决定续写、润色、补章节或导出。06_code/、07_data/、04_figures/、05_tables/ 和 manifest,确认资产含义,再转写为方法、实验或结果分析。examples/Template.docx,文件格式是 Word .docx。它来自东南大学风格论文模板的改造版本。.docx 和 .dotx;不传 --template 时自动使用内置 examples/Template.docx。python <skill_dir>/scripts/init_thesis_workspace.py . --template <user_template.docx>。--template 初始化;要抽取正文/图表/公式时,再使用 reverse_parse_docx.py。01_template/original_template.docx,并把来源记录到 09_state/template_source.json 和 09_state/project_state.json。08_refs/、用户笔记和已有论文内容。00_project/project_manifest.md 或对应章节计划。推荐流程:先创建一个新的论文项目文件夹,进入该文件夹,再运行初始化和后续命令。这样 00_project/、03_chapters/、10_output/ 等目录都会生成在这个项目文件夹里。
脚本需要 Python 包 lxml。如果当前 python 缺少 lxml,先改用已经安装 lxml 的 Python 解释器,或在目标解释器中安装 lxml 后再运行。
mkdir <project_dir>
cd <project_dir>
python <skill_dir>/scripts/init_thesis_workspace.py .默认命令会使用内置 examples/Template.docx。如果用户选择自己的 Word 模板,传入用户模板路径:
python <skill_dir>/scripts/init_thesis_workspace.py . --template <user_template.docx>如果用户提供的是已有论文内容,并且明确希望解析它,可以直接运行可选反解析入口:
python <skill_dir>/scripts/reverse_parse_docx.py <project_dir> --docx <user_thesis.docx>反解析完成后先让用户选择下一步:只查看资产、继续写作、修订润色、补缺失章节、重新导出 Word,或执行 round-trip 校验。不要默认立刻重写全文。
在项目文件夹内运行时,项目参数使用 .,脚本路径使用 Skill 的绝对路径:
python <skill_dir>/scripts/flat_opc_converter.py toxml 01_template/original_template.docx 01_template/template.flat.xml
python <skill_dir>/scripts/parse_template_xml.py 01_template/template.flat.xml 09_state/parsed_structure.json
python <skill_dir>/scripts/generate_planning_files.py .
python <skill_dir>/scripts/apply_markdown_to_xml.py . --out 09_state/current_working.xml
python <skill_dir>/scripts/build_new_docx.py . --name thesis_draft_v1.docx
python <skill_dir>/scripts/validate_xml_docx.py .
python <skill_dir>/scripts/reference_tools.py format <refs.json> --style "GB/T 7714"也可以在 Skill 根目录运行脚本,但必须把 <project_dir> 写成论文项目文件夹的绝对路径,不要省略项目路径。
可选命令:
python scripts/embed_figures_docx.py <input.docx> <output.docx> <figure1.svg> [figure2.svg ...]
python scripts/reverse_parse_docx.py <project_dir> --docx <user_thesis.docx>不要直接运行 scripts/word_xml_core.py,它是公共脚本导入的内部 Word/XML 引擎。
运行 apply_markdown_to_xml.py 前检查:
03_chapters/ 至少有可读取的章节正文 Markdown。chXX_plan.md 和 chXX_draft.md 责任分明,计划不混入最终正文。references/placeholders.md。[[REF:KEYWORD_PLACEHOLDER: 关键词]]。09_state/reverse_parse_assets.json 中图、表是否为 usable=true;只把可用资源当作真实资产。09_state/project_state.json 结构合法,必要时参考 assets/project_state.schema.json。运行 apply_markdown_to_xml.py 后检查:
09_state/current_content_manifest.json 中的 draft_files 不是空数组。09_state/current_working.xml 存在,且是 Flat OPC XML。python scripts/validate_xml_docx.py <project_dir> 输出的章节数符合预期。运行 build_new_docx.py 后检查:
10_output/。original_template.docx。09_state/current_content_manifest.json 的 draft_files 是否为空。draft_files 为空,检查章节正文是否命名为 ch*.md,且不是 *_plan.md。09_state/project_state.json 是否仍是模板解析出的旧结构;重新运行 apply_markdown_to_xml.py 会根据当前 Markdown 重建章节结构。[[TBL:...]] 或 Markdown 表格。reverse_parse_docx.py;正常结果应是 [[EQ:真实公式]] 或 [[SYM:真实符号]],不应只有 [[EQ:公式]]。[[REF:n]] 或 [[REF:KEYWORD_PLACEHOLDER: 关键词]],并阅读 references/reference_rules.md。references/placeholders.md 支持的有限 LaTeX 语法。01_template/original_template.docx。09_state/current_working.xml 已存在,保留时间戳快照。project_state.json 和上一个 XML 快照。w:updateFields=true 和 dirty field 标记刷新。© Jinze-Lee, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 29 other files (scripts, references, assets) in skills/master-thesis-studio-skill of Jinze-Lee/codex-skills-workbench.
Open the folder on GitHubat commit 7aa34a5
Master Thesis Studio 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Master Thesis Studio this skillJinze-Lee/codex-skills-workbench | 109 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Aigc Detectorfree-revalution/AIGC-Detector-Pro | 141 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Academic Paper ComposerAAASS554/codex-academic-paper-skills | 539 | 1 repos | ~3.2k | Automated safety check: Pass | MIT | |
| Thesis DOCXcatlog22/maestro-flow | 564 | 1 repos | ~2.5k | Automated safety check: Pass | MIT | |
| Chinese Thesis WorkbenchZyhSechub/chinese-thesis-workbench-skill | 577 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Master Thesis Studiodarksider-9/master-thesis-studio-skill | 129 | — | ~3.1k | Automated safety check: Pass | MIT |
free-revalution/AIGC-Detector-Pro
Academic paper AI content detection, rewriting, and thesis writing assistant.
AAASS554/codex-academic-paper-skills
A skill your agent uses when the user needs to turn a real software engineering / computer science project and an existing thesis draft into a submission-ready undergraduate thesis manuscript.
catlog22/maestro-flow
Create, revise, and format thesis or dissertation Word documents with strict academic formatting control.
ZyhSechub/chinese-thesis-workbench-skill
Standardizes, drafts, revises, checks and packages Chinese undergraduate theses from school templates, source code and literature, with evidence traceability and DOCX output.
darksider-9/master-thesis-studio-skill
A skill your agent uses for Southeast University-style master's thesis projects from a Word template or existing draft, including optional reverse parsing of an existing DOCX, user intake, outline…
LeoYeAI/openclaw-master-skills
AI-powered biomedical manuscript generation with docx output.
Jinze-Lee/codex-skills-workbench
Local workflow that searches PubMed, Europe PMC, Crossref and OpenAlex for topic keywords, downloads accessible PDFs into a PDF-only folder and removes duplicates.
Jinze-Lee/codex-skills-workbench
Fix ggplot2 superscript and richtext rendering issues using the bundled note.
Jinze-Lee/codex-skills-workbench
Follow the bundled ecology hypervolume workflow. Use this skill only when the user explicitly invokes `$hypervolume-workflow`. Do not auto-select this skill…
Jinze-Lee/codex-skills-workbench
Follow the bundled literature-synthesis guide. An agent skill from Jinze-Lee/codex-skills-workbench.
Jinze-Lee/codex-skills-workbench
Follow the bundled method-transfer guide. An agent skill from Jinze-Lee/codex-skills-workbench.
Jinze-Lee/codex-skills-workbench
Follow the bundled phylogeny workflow. An agent skill from Jinze-Lee/codex-skills-workbench.
Works with
Categories
Guides the writing of a Chinese master's thesis and generates the Word file from a template, only when you invoke it by name. This opt-in skill splits thesis work into two layers. The writing layer interviews you about topic, outline, chapter plan, asset list and writing limits, and drafts in Chinese academic style.
Master Thesis Studio fits situations like: starting a Chinese master's thesis from topic and outline questions; writing thesis chapters back into a Word template as a new DOCX; continuing a partly written thesis chapter by chapter.
Run `npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a claude-code`. Or copy the skill folder (skills/master-thesis-studio-skill in Jinze-Lee/codex-skills-workbench) into .claude/skills/master-thesis-studio-skill in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a codex`. Or copy the skill folder (skills/master-thesis-studio-skill in Jinze-Lee/codex-skills-workbench) into .agents/skills/master-thesis-studio-skill in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Jinze-Lee/codex-skills-workbench --skill master-thesis-studio-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/master-thesis-studio-skill, .gemini/skills/master-thesis-studio-skill, .github/skills/master-thesis-studio-skill and .opencode/skills/master-thesis-studio-skill in your project.
Going by SKILL.md and its folder, Master Thesis Studio needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python to run the bundled scripts; A Word template (.docx or .dotx), or the built-in example template.
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.
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.
Master Thesis Studio 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.
About 3.5k tokens (SKILL.md is roughly 14k 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 6.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Master Thesis Studio: Aigc Detector (free-revalution/AIGC-Detector-Pro, 141 stars), Academic Paper Composer (AAASS554/codex-academic-paper-skills, 539 stars), Thesis DOCX (catlog22/maestro-flow, 564 stars) and Chinese Thesis Workbench (ZyhSechub/chinese-thesis-workbench-skill, 577 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Jinze-Lee (a GitHub user) maintains it in Jinze-Lee/codex-skills-workbench, which has 109 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on May 2, 2026.
Source: Jinze-Lee/codex-skills-workbench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.