Yuan1z0825/nature-skills / skills/nature-paper-to-patent
nature-paper-to-patent
FlaggedTurn research papers or inventor materials into evidence-grounded Chinese invention patent drafts and technical disclosures. Use for 技术交底书、专利撰写、现有技术对比 and Chinese DOCX patent packages; not general manuscript writing.
references/disclosure/iteration_context.md
View on GitHub# 迭代上下文(进入 merger / correction 前必读)
## 本文作用
约定**迭代时先干什么、产出什么**,避免 Agent 只读了合并/纠正模板却转去跑 **Step 3–4 专利点分析**或空泛「更新分析」而不落盘新稿。
---
## 何时读本文
用户明显在**已有交底书或上一轮交付稿**上继续工作时(补材料、改章节、纠错、调保护点表述等),在 **`Read` `merger.md` 或 `correction_handler.md` 之前**先读本文,再读对应迭代模板。
| 意图 | 下一步模板 |
|------|------------|
| 补充文档、扩展方案、合并新材料 | `merger.md` |
| 指出错误、与事实/参数不符、风格或保护点调整 | `correction_handler.md` |
| 用户已按 `disclosure_builder.md` §7.6 声明侧重点,仅需 **第五章权利要求书式强化**(取向须与本稿已有材料及第五、三章已写观点一致,**禁止**为交互而编造新场景) | `merger.md`(以最近定稿为基准,合并范围以第五章为主,必要时微调第四章与第五章衔接句) |
---
## 输入与输出
**输入**
- 对话中的本轮说明;用户 **@** 的文件或粘贴片段。
- **`Read`** 当前作为基准的交底书 `.md`(路径由用户给出或对话中已出现)。
**输出**
- 合并或纠正后的全文写入**新文件**,不得默认覆盖旧稿:
**`{规范化案件名}_{YYYYMMDDHHmmss}.md`** + **`mermaid_render.py` 生成的同名 `.docx`**。
- 与 **Step 7 首次定稿**为**同一命名规则**(凡落盘交付均带时间戳),详见 **`disclosure_builder.md` §7.3 第 5 点**。
- 旧版 `.md`/`.docx` 保留在同目录,便于对照(用户明确要求覆盖时再覆盖)。
版本历史依赖**同目录下多个带时间戳的文件**,不需要 `iterations/` 子目录或快照脚本。
### 修订对话记录(单独 Markdown,必做)
每完成一轮 **合并**或**纠正**并在磁盘上写出新 `.md`/`.docx` 后,须在**案件产出目录**(与本轮交付文件同一目录,如 `outputs/{案件标识}/`)维护**一个固定文件**:
- **文件名**:`交底书修订对话记录.md`(默认;若环境对中文路径敏感,可用 `--log-name disclosure_revision_log.md` 调用脚本)。
**每条记录须含**:
1. **记录时间**:**本地时间**与 **UTC**(脚本自动生成;手工追加时两者都写)。
2. **类型**:合并迭代 / 纠正迭代。
3. **用户说明摘要**:本轮用户意图、要点(可含 @ 文件名称)。
4. **本轮交付文件**:新时间戳 `.md`、`.docx` 文件名。
5. **合并/纠正摘要摘录**:与当轮对话中「合并摘要(留档)」「纠正摘要(留档)」一致或为其缩写。
**推荐**:在写出交付文件并生成 Word 之后,执行 **`Bash`**:
```text
python3 scripts/disclosure/iteration_dialog_log.py --case-dir "{案件目录}" --kind merge --user "{用户说明摘要}" --summary "{摘要摘录}" --artifacts "{案件名_时间戳.md},{案件名_时间戳.docx}"
```
`--kind` 纠正时用 `correct`。若无法执行脚本,须 **`Read`** 已有 `交底书修订对话记录.md`(若无则 **`Write`** 创建),再 **`StrReplace`** 或等价方式在文末**追加**与上表结构相同的一条(时间须真实)。
**禁止**:完成迭代交付却**完全不**更新该对话记录文件。
---
## 建议执行顺序(短清单)
1. 读本文 → 按上表选 `merger.md` 或 `correction_handler.md` 并 **`Read`**。
2. **`Read`** 基准稿 + 本轮补充材料。
3. 在稿内完成合并或纠正逻辑(自检 **8.2、8.3** 见 `disclosure_self_check.md`)。
4. **`Write`** 新时间戳 `.md` → 运行 **`mermaid_render.py -o`** 写出定稿图与 **`.docx`**。
5. 追加 **`交底书修订对话记录.md`**(**`iteration_dialog_log.py`** 或手工),见上文「修订对话记录」。
6. 在回复中写明新文件路径,并输出该模板要求的 **「合并摘要(留档)」**或 **「纠正摘要(留档)」**。
---
## 禁止
- 已判定为迭代意图时,**不**经合并/纠正流程、不把结果写入**新时间戳文件**,却去跑全文专利点挖掘或仅输出分析段落。
- 例外:用户**明确要求**「重新挖掘专利点 / 从头再走查新」时,可走主流程 Step 3 起。Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| pptxanthropics/skillsUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |