Report Writing
GAIK-project/gaik-toolkit
Converts scattered documents and media (recordings, notes, diagrams, PDFs, spreadsheets) into structured MS Word reports.
用于撰写、补写、压缩、仿写、规范化交付中文毕业论文、毕业设计论文、技术报告和课程设计论文。用户提到论文、样文、学校模板、参考文献、摘要、图表、截图、Word 成稿、查重口吻优化,或需要基于真实项目代码生成论文正文时必须使用。本技能内置样文结构学习、样式提取、章节控字、参考文献筛选、Mermaid/PlantUML 图表处理、Chrome MCP 页面截图工作流,以及 doc/docx Word…
$ npx skills add Doryoku1223/lunwen-skill --skill lunwen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Doryoku1223/lunwen-skill lunwen --agent claude-codeProject 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/
Install the "lunwen" agent skill from https://github.com/Doryoku1223/lunwen-skill/tree/main into .claude/skills/lunwen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lunwen", 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.
$ npx skills add Doryoku1223/lunwen-skill --skill lunwen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Doryoku1223/lunwen-skill lunwen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lunwen" agent skill from https://github.com/Doryoku1223/lunwen-skill/tree/main into .agents/skills/lunwen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lunwen", 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 Doryoku1223/lunwen-skill --skill lunwen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Doryoku1223/lunwen-skill lunwen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "lunwen" agent skill from https://github.com/Doryoku1223/lunwen-skill/tree/main into .cursor/skills/lunwen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lunwen", 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.
$ npx skills add Doryoku1223/lunwen-skill --skill lunwen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Doryoku1223/lunwen-skill lunwen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "lunwen" agent skill from https://github.com/Doryoku1223/lunwen-skill/tree/main into .gemini/skills/lunwen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lunwen", 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 Doryoku1223/lunwen-skill lunwenInstalls 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 Doryoku1223/lunwen-skill --skill lunwen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "lunwen" agent skill from https://github.com/Doryoku1223/lunwen-skill/tree/main into .github/skills/lunwen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lunwen", 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 Doryoku1223/lunwen-skill --skill lunwen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Doryoku1223/lunwen-skill lunwen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "lunwen" agent skill from https://github.com/Doryoku1223/lunwen-skill/tree/main into .opencode/skills/lunwen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lunwen", 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.
lunwen用于撰写、补写、压缩、仿写、规范化交付中文毕业论文、毕业设计论文、技术报告和课程设计论文。用户提到论文、样文、学校模板、参考文献、摘要、图表、截图、Word 成稿、查重口吻优化,或需要基于真实项目代码生成论文正文时必须使用。本技能内置样文结构学习、样式提取、章节控字、参考文献筛选、Mermaid/PlantUML 图表处理、Chrome MCP 页面截图工作流,以及 doc/docx Word…
Lunwen is an agent skill from Doryoku1223/lunwen-skill. 用于撰写、补写、压缩、仿写、规范化交付中文毕业论文、毕业设计论文、技术报告和课程设计论文。用户提到论文、样文、学校模板、参考文献、摘要、图表、截图、Word 成稿、查重口吻优化,或需要基于真实项目代码生成论文正文时必须使用。本技能内置样文结构学习、样式提取、章节控字、参考文献筛选、Mermaid/PlantUML 图表处理、Chrome MCP 页面截图工作流,以及 doc/docx Word 成稿交付工作流。
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 53 other files, including reference files (for example `.claude/agents/lunwen-writer.md`, `.claude/commands/lunwen.md` and `.trae/agents/lunwen-writer.md`).
It sits in Documents & Office, covering Word documents and Diagrams. It works with Microsoft Word, Mermaid and Model Context Protocol. The repository describes itself as: 面向本科计科学生的一键论文初稿 Skill,支持样文/开题报告/模板驱动生成,并补全流程图、ER 图和项目截图. The licence is MIT.
8 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit b8dd108. 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.
No scripts in the folder and no shell commands in SKILL.md.
From 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.
Lunwen loads about 1.7k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 54 tokens; SKILL.md has 488 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); files beside SKILL.md are not scanned.
The full file from Doryoku1223/lunwen-skill at commit b8dd108, republished under its MIT licence (© Doryoku1223). 488 words, ~1,687 tokens.
.claude/skills/lunwen/SKILL.md (or your agent's skills folder). This skill also uses 44 other files; get the full folder from GitHub.这个技能用于把“真实项目事实 + 样文/模板 + 文献约束 + 图表截图 + Word 成稿要求”稳定转化为一篇可交付的中文论文。目标不是把论文写厚,而是按样文体量、真实项目能力和版式规则,输出结构完整、字数可控、图表齐全的 .docx 成稿。
以下规则是硬约束:
smart-lab-thesis、final、draft 这类通用名。.docx 外,必须额外交付一个“附件 .docx”,用于收录正文中的 Mermaid / PlantUML 图源码、数据库 E-R 图源码、关键流程图源码等不渲染版本。本技能默认按以下状态机执行:
intake_only
只收资料,不写正文。sample_analysis_done
已完成样文 / 模板 / 任务书分析,但未开写。outline_confirmed
用户已确认目录、字数和样式方案。writing_allowed
允许开始正文写作。delivery_done
已生成主论文、附件和校验产物。状态约束:
outline_confirmed 前,禁止写正文。sample_analysis_done。writing_allowed 后,才允许生成主论文 .md / .docx。先确认以下输入并确定优先级:
首次响应论文请求时,必须主动告诉用户可以直接提供模板、历届样文、开题报告、任务书或封面要求的本地路径,示例格式如:
D:\论文模板.docxD:\论文样文1.docxD:\开题报告.pdf并且必须明确说明:
如果模板、样文和默认规则冲突,必须列出冲突项并让用户选择。样式冲突细则见:
prompts/intake.mdprompts/style_extractor.mdreferences/default-style.md先读项目代码和文档,再提炼固定的项目事实底稿。后续各章只能基于这份底稿扩写。
冻结事实时,必须明确区分:
如果三者不一致,必须在设计回传阶段提前告诉用户,不得等正文写完后再修正。
事实提取细则见:
prompts/fact_extractor.md如果用户提供样文或模板,必须同时分析:
对应资源:
prompts/sample_analyzer.mdprompts/style_extractor.mdtools/analyze_sample_pdf.pytools/analyze_docx.py模板和样文分析结束后,必须先把以下内容回传给用户确认:
回传时,默认必须结构化为 4 张表:
必须明确等待用户确认目录和样式;若用户提出新的修改意见,以用户最后确认的版本为准,再进入正文写作。
如果用户后续又补充了新样文、模板或任务书,必须中断正文写作流程,回到本步骤重新分析,不得沿用旧设计继续写。
写正文前必须生成目标章节字数表。默认优先贴近样文体量,不默认写厚。写完一章就统计一次,超出就压缩。
对应资源:
prompts/chapter_writer.mdtools/count_chapter_words.pyreferences/chapter-patterns.md图表默认要求:
E-R 图规则:
截图默认要求:
代码默认要求:
第 3 章设计图最低要求:
第 4 章截图最低要求:
如果存在 mermaid / plantuml,优先渲染为真实图片;若无法渲染,再退回源码或占位。
仓库内置 Playwright 截图链路。默认先用本仓库脚本自动抓取系统页面,不再要求用户额外安装浏览器 skill。
如果宿主环境提供 Chrome CDP / Chrome MCP 连接地址,可以作为增强路径复用当前浏览器会话;否则默认由仓库自举 Playwright Chromium。
对应资源:
tools/render_mermaid.pytools/ensure_thesis_assets.pytools/extract_screenshot_placeholders.pytools/build_screenshot_plan.pytools/capture_thesis_screenshots.py默认约束:
必须优先真实可核验文献,不确定就不用。
文献工作流必须分 5 步执行:
默认文献质量规则:
文献交付产物默认至少包括:
references-verified.json 文献核验清单文献核验清单默认字段:
对应资源:
prompts/reference_selector.mdtools/build_reference_pool.py如果环境具备 doc / docx 能力,必须生成 .docx 成稿,而不是只停留在 Markdown。
交付物必须至少包括:
.md.docx.docx文件名规则:
智慧实验室管理系统的设计与实现.docx智慧实验室管理系统的设计与实现-附件.docxsmart-lab-thesis、paper-final、doc1 等通用名派生文件也应统一命名:
论文标题.md论文标题.docx论文标题-附件.docx论文标题-image-map.json论文标题-文献核验清单.json附件 .docx 默认内容:
默认样式规则:
对应资源:
prompts/docx_formatter.mdtools/generate_thesis_docx.pytools/analyze_docx.pyreferences/default-style.md交付前必须检查:
.docx 是否真实存在.docx 是否真实存在正文语言默认遵循以下风格约束:
最终检查细则见:
prompts/final_checker.md项目输入与冲突决策:prompts/intake.md
样文结构分析:prompts/sample_analyzer.md
样式提取:prompts/style_extractor.md
项目事实提取:prompts/fact_extractor.md
章节写作与控字:prompts/chapter_writer.md
参考文献筛选:prompts/reference_selector.md
Word 格式化:prompts/docx_formatter.md
最终检查:prompts/final_checker.md
默认版式:references/default-style.md
章节模式:references/chapter-patterns.md
统计章节字数:tools/count_chapter_words.py
分析样文 PDF:tools/analyze_sample_pdf.py
分析样文 DOCX:tools/analyze_docx.py
检查参考文献池:tools/build_reference_pool.py
生成文献核验清单模板:tools/write_reference_verification_template.py
图表与截图补全检查:tools/ensure_thesis_assets.py
提取截图占位符:tools/extract_screenshot_placeholders.py
生成图源码附件 DOCX:tools/generate_diagram_appendix_docx.py
生成截图计划:tools/build_screenshot_plan.py
自动抓取页面截图:tools/capture_thesis_screenshots.py
渲染 Mermaid:tools/render_mermaid.py
生成 DOCX:tools/generate_thesis_docx.py
© Doryoku1223, 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 44 other files (references) in the repository root of Doryoku1223/lunwen-skill.
Open the folder on GitHubat commit b8dd108
Lunwen 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 |
|---|---|---|---|---|---|---|
| Lunwen this skillDoryoku1223/lunwen-skill | 652 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Report WritingGAIK-project/gaik-toolkit | 100 | — | ~4.9k | Automated safety check: Pass | MIT | |
| MineruNebutra/MinerU-Skill | 123 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Adeu Redliningdealfluence/adeu | 167 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Knowledgeguaardvark/guaardvark | 257 | — | ~642 | Automated safety check: Pass | MIT | |
| Document ConverterBlackBeltTechnology/pi-agent-dashboard | 315 | — | ~999 | Automated safety check: Pass | MIT |
GAIK-project/gaik-toolkit
Converts scattered documents and media (recordings, notes, diagrams, PDFs, spreadsheets) into structured MS Word reports.
Nebutra/MinerU-Skill
An AI-Native skill for parsing PDF / Office / image files into clean Markdown with MinerU — a fast, zero-config document parser for AI agents.
dealfluence/adeu
A skill your agent uses when reviewing, editing, redlining, or negotiating an existing Microsoft Word document (.docx) — including proposing edits as tracked changes, accepting or rejecting existing…
guaardvark/guaardvark
Answer from the user's own indexed documents with Guaardvark's local RAG, browse and read indexed files section by section, remember facts across sessions, and process or fetch new material.
BlackBeltTechnology/pi-agent-dashboard
Convert documents bidirectionally via the pi-doc-engine facade: ingest PDF/DOCX/PPTX/XLSX to provenance-stamped Markdown (with OCR), and produce templated DOCX/PDF from Markdown with diagrams, TOC…
athola/claude-night-market
Converts documents and URLs to markdown via tiered fallback (MCP markitdown, native tools, user notice).
Categories
用于撰写、补写、压缩、仿写、规范化交付中文毕业论文、毕业设计论文、技术报告和课程设计论文。用户提到论文、样文、学校模板、参考文献、摘要、图表、截图、Word 成稿、查重口吻优化,或需要基于真实项目代码生成论文正文时必须使用。本技能内置样文结构学习、样式提取、章节控字、参考文献筛选、Mermaid/PlantUML 图表处理、Chrome MCP 页面截图工作流,以及 doc/docx Word…. Lunwen is an agent skill from Doryoku1223/lunwen-skill.
Lunwen fits situations like: tasks that involve Word documents; tasks that involve Diagrams.
Run `npx skills add Doryoku1223/lunwen-skill --skill lunwen -a claude-code`. Or copy the skill folder (the Doryoku1223/lunwen-skill repository) into .claude/skills/lunwen in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Doryoku1223/lunwen-skill --skill lunwen -a codex`. Or copy the skill folder (the Doryoku1223/lunwen-skill repository) into .agents/skills/lunwen 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 Doryoku1223/lunwen-skill --skill lunwen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lunwen, .gemini/skills/lunwen, .github/skills/lunwen and .opencode/skills/lunwen in your project.
SKILL.md names no scripts, command-line tools or credentials: Lunwen is instructions for the agent only.
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. Review the folder before installing.
Lunwen 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 1.7k tokens (SKILL.md is roughly 6.7k 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 324 tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Lunwen: Report Writing (GAIK-project/gaik-toolkit, 100 stars), Mineru (Nebutra/MinerU-Skill, 123 stars), Adeu Redlining (dealfluence/adeu, 167 stars) and Knowledge (guaardvark/guaardvark, 257 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Doryoku1223 (a GitHub user) maintains it in Doryoku1223/lunwen-skill, which has 652 GitHub stars. The repository was last updated on April 5, 2026.
Source: Doryoku1223/lunwen-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.