Add style presets, Mermaid, and AIGC workflow support

Author: Jonnys-Li

README.md

@@ -1,6 +1,6 @@
 # software-thesis-docx
 
-Build and refine software-thesis DOCX workflows from real project repositories.
+Build and refine thesis-ready `DOCX` workflows from real software project repositories.
 
 Chinese documentation: [README.zh-CN.md](README.zh-CN.md)
 
@@ -29,11 +29,21 @@ After installing, restart Codex to pick up new skills.
 ## Try It
 
 ```text
-Use $software-thesis-docx to turn my software project repo into a structured thesis manifest and generate a DOCX.
-Use $software-thesis-docx to replace thesis figures by caption without changing Word layout.
-Use $software-thesis-docx to normalize in-text citations and terminology in an existing DOCX.
+Use $software-thesis-docx to turn my project repo into a structured thesis manifest and generate a DOCX with the built-in academic preset.
+Use $software-thesis-docx to read my school Word template, extract a custom style preset, and build the thesis in that format.
+Use $software-thesis-docx to generate Mermaid architecture and sequence diagrams for my thesis from the repository structure.
+Use $software-thesis-docx to run an AIGC risk check on my thesis DOCX and only rewrite the flagged single-run paragraphs if I approve it.
 ```
 
+## What It Adds
+
+- A built-in academic formatting preset derived from a real thesis layout sample, without shipping the original private document
+- Runtime extraction of custom style presets from uploaded or provided `.docx` templates
+- Manifest-driven DOCX build with optional `formatting` config
+- Mermaid request contracts for architecture, sequence, ER, state, gantt, class, and mind-map diagrams
+- Optional rigorous-writing subagent mode for complex thesis tasks, default off
+- Local AIGC risk checking and conservative paragraph-level reduction workflow, default off
+
 ## Compatibility
 
 - Codex: supported now
@@ -44,8 +54,14 @@ Use $software-thesis-docx to normalize in-text citations and terminology in an e
 
 - Root-level distribution files: `README`, release notes, and one-click installers
 - The actual reusable skill at `skills/software-thesis-docx/`
-- Three parameterized DOCX tools for build, figure replacement, and paragraph rewrites
-- Public examples and methodology docs for adapting the workflow to another thesis project
+- Five reusable DOCX-oriented scripts:
+  - `build_docx_from_manifest.py`
+  - `extract_docx_style_preset.py`
+  - `replace_images_by_caption.py`
+  - `rewrite_paragraphs.py`
+  - `check_aigc_risk.py`
+- Public examples for manifests, workflow options, Mermaid requests, image maps, and paragraph rewrites
+- Reference docs for formatting presets, Mermaid planning, option intake, AIGC review, and repo-to-thesis workflow
 
 ## Repository Layout
 
@@ -71,35 +87,41 @@ Inside that folder you will find:
 - `SKILL.md`
 - `agents/openai.yaml`
 - `assets/examples/`
+- `assets/presets/`
 - `references/`
 - `scripts/`
 - `requirements.txt`
 
 ## Documentation
 
 - [Codex quick start](docs/codex-quickstart.md)
+- [v0.3.0 release notes](docs/releases/v0.3.0.md)
 - [v0.2.0 release notes](docs/releases/v0.2.0.md)
 - [v0.1.0 release notes](docs/releases/v0.1.0.md)
 
 ## Design Principles
 
 - Ground the thesis in repository facts before drafting prose
 - Keep content in structured inputs instead of hardcoding thesis text in Python
+- Separate formatting from content through built-in or extracted style presets
 - Prefer caption-based figure replacement over position-based image replacement
 - Prefer exact paragraph rewrites when Word layout fidelity matters
-- Validate visually after meaningful DOCX mutations
+- Keep Mermaid generation and AIGC review opt-in, not forced defaults
 
 ## Limits
 
+- Mermaid support currently generates code and file outputs, not rendered images or automatic DOCX insertion
 - The paragraph rewrite tool only handles exact full-paragraph matches
 - Mixed-format, multi-run paragraphs should be inspected before automated edits
-- Institution-specific formatting rules may require manifest or style extensions
+- The AIGC checker is a local heuristic pass, not a guarantee of any third-party score
+- Institution-specific formatting rules may still require manifest or preset extensions
 
 ## Roadmap
 
-- Add an OpenCode-compatible packaging and installation path
-- Add a Claude Code-compatible prompt and repository layout guide
-- Add cross-runtime smoke tests across Codex, OpenCode, and Claude Code
+- Add OpenCode-compatible packaging and installation paths
+- Add Claude Code-compatible prompt and repository layout guidance
+- Add shared smoke tests across Codex, OpenCode, and Claude Code
+- Expand style extraction for more complex school templates with richer front matter
 
 ## License
 

README.zh-CN.md

@@ -29,11 +29,21 @@ irm https://raw.githubusercontent.com/Jonnys-Li/software-thesis-docx-skill/main/
 ## 快速试用
 
 ```text
-Use $software-thesis-docx to turn my software project repo into a structured thesis manifest and generate a DOCX.
-Use $software-thesis-docx to replace thesis figures by caption without changing Word layout.
-Use $software-thesis-docx to normalize in-text citations and terminology in an existing DOCX.
+Use $software-thesis-docx to turn my project repo into a structured thesis manifest and generate a DOCX with the built-in academic preset.
+Use $software-thesis-docx to read my school Word template, extract a custom style preset, and build the thesis in that format.
+Use $software-thesis-docx to generate Mermaid architecture and sequence diagrams for my thesis from the repository structure.
+Use $software-thesis-docx to run an AIGC risk check on my thesis DOCX and only rewrite the flagged single-run paragraphs if I approve it.
 ```
 
+## 这次新增了什么
+
+- 一个内置的学术论文编排 preset，来源于真实排版样本，但不公开原始私有文档
+- 运行时从用户提供的 `.docx` 模板中抽取自定义样式 preset
+- 支持 `formatting` 配置的 manifest 驱动 DOCX 构建
+- 面向论文插图的 Mermaid 请求契约，支持架构图、时序图、ER 图、状态图、甘特图、类图和脑图
+- 可选的严谨写作 subagent 模式，默认关闭
+- 本地 AIGC 风险检查与保守的定向降重流程，默认关闭
+
 ## 兼容性
 
 - Codex：当前已适配
@@ -44,8 +54,14 @@ Use $software-thesis-docx to normalize in-text citations and terminology in an e
 
 - 根目录分发文件：`README`、版本说明、一键安装脚本
 - 真实可复用的 skill：`skills/software-thesis-docx/`
-- 3 个参数化 DOCX 工具：生成、按图注换图、精确段落改写
-- 公开示例与方法论文档，便于迁移到其他论文项目
+- 5 个可复用脚本：
+  - `build_docx_from_manifest.py`
+  - `extract_docx_style_preset.py`
+  - `replace_images_by_caption.py`
+  - `rewrite_paragraphs.py`
+  - `check_aigc_risk.py`
+- 公开示例：manifest、workflow options、Mermaid 请求、图片映射、段落改写
+- 方法论文档：格式 preset、Mermaid、交互 intake、AIGC 评估、repo-to-thesis 工作流
 
 ## 仓库结构
 
@@ -71,35 +87,41 @@ https://github.com/Jonnys-Li/software-thesis-docx-skill/tree/main/skills/softwar
 - `SKILL.md`
 - `agents/openai.yaml`
 - `assets/examples/`
+- `assets/presets/`
 - `references/`
 - `scripts/`
 - `requirements.txt`
 
 ## 文档
 
 - [Codex 快速上手](docs/codex-quickstart.zh-CN.md)
+- [v0.3.0 版本说明](docs/releases/v0.3.0.md)
 - [v0.2.0 版本说明](docs/releases/v0.2.0.md)
 - [v0.1.0 版本说明](docs/releases/v0.1.0.md)
 
 ## 方法原则
 
 - 先基于代码仓库事实，再组织论文内容
 - 把内容放进结构化输入，而不是把正文硬编码进 Python
+- 通过内置或抽取出的 style preset 把内容和排版分离
 - 图片替换优先按图注定位，不按“第几张图”这种脆弱逻辑
 - 文本改写优先整段精确匹配，减少对 Word 格式的破坏
-- 每次重要 DOCX 变更后都做一次可视化校验
+- Mermaid 与 AIGC 评估都是显式开关，不默认强制开启
 
 ## 使用边界
 
+- Mermaid 当前只负责生成代码或 `.mmd` 文件，不负责自动渲染图片或自动插入 DOCX
 - 段落改写脚本只适合“整段全文精确命中”的场景
 - 多 `run`、混合格式、修订痕迹较多的段落需要先人工检查
-- 学校格式要求如果更特殊，通常需要扩展 manifest 或样式逻辑
+- AIGC 检测是本地启发式评估，不承诺对齐第三方平台分值
+- 学校格式要求如果更特殊，通常需要扩展 manifest 或 preset 逻辑
 
 ## 下一步
 
 - 增加 OpenCode 兼容的打包与安装方式
 - 增加 Claude Code 的接入方式与提示词约定
 - 增加跨运行时 smoke test，覆盖 Codex、OpenCode、Claude Code
+- 增强复杂学校模板的样式抽取与前置页支持
 
 ## 许可证
 

docs/codex-quickstart.md

@@ -30,28 +30,41 @@ The installed skill directory should contain:
 
 - `SKILL.md`
 - `agents/openai.yaml`
-- `scripts/`
-- `references/`
 - `assets/examples/`
+- `assets/presets/`
+- `references/`
+- `scripts/`
 - `requirements.txt`
 
 The important part is that `SKILL.md` stays at the root of the installed skill.
 
-## 3. Use The Skill In Codex
+## 3. What The Skill Now Supports
+
+- manifest-driven thesis DOCX generation
+- caption-based image replacement
+- exact paragraph rewrites for layout-safe terminology or citation cleanup
+- built-in academic style preset
+- custom style preset extraction from `.docx` templates
+- Mermaid planning contracts
+- optional subagent rigorous-writing mode
+- optional AIGC risk checking and conservative reduction workflow
+
+## 4. Use The Skill In Codex
 
 Ask Codex to use the skill explicitly:
 
 ```text
-Use $software-thesis-docx to generate a thesis-ready DOCX workflow from my software project repository.
+Use $software-thesis-docx to build my thesis DOCX workflow from my software repository and ask me whether to use the default preset, Mermaid generation, subagents, and AIGC checks.
 ```
 
 Typical prompts:
 
-- `Use $software-thesis-docx to turn my project repo into a structured thesis manifest and generate a DOCX.`
-- `Use $software-thesis-docx to replace thesis figures by caption without changing Word layout.`
-- `Use $software-thesis-docx to normalize in-text citations and terminology in an existing DOCX.`
+- `Use $software-thesis-docx to turn my project repo into a structured thesis manifest and generate a DOCX with the built-in preset.`
+- `Use $software-thesis-docx to read my Word template, extract a style preset, and build the thesis in that format.`
+- `Use $software-thesis-docx to generate Mermaid flowchart and sequenceDiagram code for my thesis based on the repo architecture.`
+- `Use $software-thesis-docx to run an AIGC risk review on my thesis DOCX and only rewrite the flagged single-run paragraphs after showing me the report.`
 
-## 4. Optional Dependency Step
+## 5. Optional Dependency Step
 
 If your Python environment does not already include the required libraries:
 
@@ -61,16 +74,41 @@ python3 -m pip install -r "$HOME/.codex/skills/software-thesis-docx/requirements
 
 If you use a custom `CODEX_HOME`, replace the path accordingly.
 
-## 5. Run The Scripts Directly
+## 6. Run The Scripts Directly
 
-Build from a manifest:
+Build from the bundled example manifest:
 
 ```bash
 python3 "$HOME/.codex/skills/software-thesis-docx/scripts/build_docx_from_manifest.py" \
   --manifest "$HOME/.codex/skills/software-thesis-docx/assets/examples/thesis_manifest.example.json" \
   --output /tmp/example-thesis.docx
 ```
 
+Extract a preset from a school template:
+
+```bash
+python3 "$HOME/.codex/skills/software-thesis-docx/scripts/extract_docx_style_preset.py" \
+  --input school-template.docx \
+  --output /tmp/style-preset.json
+```
+
+Build with that preset:
+
+```bash
+python3 "$HOME/.codex/skills/software-thesis-docx/scripts/build_docx_from_manifest.py" \
+  --manifest thesis_manifest.json \
+  --style-preset /tmp/style-preset.json \
+  --output /tmp/custom-thesis.docx
+```
+
+Run the AIGC risk checker:
+
+```bash
+python3 "$HOME/.codex/skills/software-thesis-docx/scripts/check_aigc_risk.py" \
+  --input thesis.docx \
+  --output /tmp/aigc-risk-report.json
+```
+
 Replace images by caption:
 
 ```bash
@@ -89,7 +127,17 @@ python3 "$HOME/.codex/skills/software-thesis-docx/scripts/rewrite_paragraphs.py"
   --replacements "$HOME/.codex/skills/software-thesis-docx/assets/examples/rewrites.example.json"
 ```
 
-## 6. Current Scope
+## 7. Advanced Config Contracts
+
+Bundled examples:
+
+- `assets/examples/thesis_manifest.example.json`
+- `assets/examples/thesis_workflow_options.example.json`
+- `assets/examples/mermaid_requests.example.json`
+- `assets/examples/image_map.example.json`
+- `assets/examples/rewrites.example.json`
+
+## 8. Current Scope
 
 This repository currently ships the Codex-compatible skill layout only.
 
@@ -102,5 +150,7 @@ Planned next steps:
 ## Troubleshooting
 
 - If Codex does not discover the skill, confirm the install path and make sure `SKILL.md` is at the root.
+- If the builder output looks wrong, check whether the manifest is using the right `formatting.mode`.
+- If preset extraction is weak, confirm the source `.docx` actually contains the semantic roles you expect.
 - If image replacement fails, check that each target caption exactly matches the caption text in the DOCX.
 - If paragraph rewriting fails, confirm the paragraph is a single-run exact match.