Skip to content

Yuan1z0825/nature-skills / skills/nature-paper-to-patent

nature-paper-to-patent

Flagged

Turn 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.

FileKindSize
README.mdmarkdown2.9 KB
README_EN.mdmarkdown3.3 KB
SKILL.mdskill md4.5 KB
agents/openai.yamlconfig248 B
evals/evals.jsonconfig1.5 KB
manifest.yamlconfig3.1 KB
references/cn-patent-drafting-guide.mdmarkdown8.0 KB
references/corpus-derived-patterns.mdmarkdown3.5 KB
references/corpus-pair-audit.mdmarkdown2.9 KB
references/disclosure/correction_handler.mdmarkdown2.8 KB
references/disclosure/disclosure_builder.mdmarkdown12.1 KB
references/disclosure/disclosure_preview.mdmarkdown917 B
references/disclosure/disclosure_self_check.mdmarkdown5.9 KB
references/disclosure/intake.mdmarkdown943 B
references/disclosure/iteration_context.mdmarkdown4.3 KB
references/disclosure/merger.mdmarkdown3.4 KB
references/disclosure/patent-disclosure-skill-MIT-LICENSE.txtmarkdown1.0 KB
references/disclosure/patent_points_analyzer.mdmarkdown951 B
references/disclosure/prior_art_search.mdmarkdown10.4 KB
references/disclosure/project_scan.mdmarkdown3.6 KB
references/disclosure/template_reference.mdmarkdown9.2 KB
references/disclosure/tooling.mdmarkdown16.2 KB
references/draft-schema.mdmarkdown9.0 KB
references/patent-figure-guide.mdmarkdown2.9 KB
requirements.txtmanifest121 B
scripts/audit_claims.pyscript6.4 KB
scripts/build_patent_package.pyscript6.5 KB
scripts/disclosure/cnipa_epub_crawler.pyscript10.7 KB
scripts/disclosure/cnipa_epub_parse.pyscript8.8 KB
scripts/disclosure/cnipa_epub_search.pyscript5.9 KB
scripts/disclosure/docx_to_md.pyscript3.7 KB
scripts/disclosure/iteration_dialog_log.pyscript3.2 KB
scripts/disclosure/math_render.pyscript12.7 KB
scripts/disclosure/md_to_docx.pyscript32.2 KB
scripts/disclosure/mermaid_render.pyscript15.2 KB
scripts/disclosure/package-lock.jsonmanifest84.4 KB
scripts/disclosure/package.jsonmanifest279 B
scripts/disclosure/pptx_to_md.pyscript4.9 KB
scripts/disclosure/requirements-cnipa.txtmarkdown172 B
scripts/extract_pdf_text.pyscript2.3 KB
scripts/init_patent_project.pyscript3.1 KB
scripts/math_to_omml.pyscript4.8 KB
scripts/render_flowchart_svg.pyscript14.3 KB
scripts/render_patent_docx.pyscript10.3 KB
scripts/validate_patent_draft.pyscript14.6 KB
static/core/output-contract.mdmarkdown2.0 KB
static/core/principles.mdmarkdown1016 B
static/core/workflow.mdmarkdown3.8 KB
static/fragments/invention/algorithm-software.mdmarkdown366 B
static/fragments/invention/apparatus-system.mdmarkdown288 B
static/fragments/invention/mixed.mdmarkdown255 B
static/fragments/invention/process-material.mdmarkdown278 B
static/fragments/source/mixed-project.mdmarkdown369 B
static/fragments/source/pasted-text.mdmarkdown316 B
static/fragments/source/pdf-text.mdmarkdown290 B
static/fragments/source/scanned-pdf.mdmarkdown272 B
static/fragments/task/claim-set.mdmarkdown249 B
static/fragments/task/disclosure-analysis.mdmarkdown236 B
static/fragments/task/disclosure-iteration.mdmarkdown1005 B
static/fragments/task/full-draft.mdmarkdown247 B
static/fragments/task/paper-patent-audit.mdmarkdown280 B
static/fragments/task/technical-disclosure.mdmarkdown1.5 KB
tests/test_audit_claims.pyscript1.6 KB
tests/test_inline_math_paren.pyscript1.7 KB
tests/test_math_to_omml_superscript.pyscript2.2 KB
tests/test_md_to_docx_source_overwrite.pyscript1.4 KB
tests/test_mermaid_render.pyscript2.3 KB
tests/test_validation.pyscript6.0 KB
tests/test_validation_figure_node_ids.pyscript614 B

references/draft-schema.md

View on GitHub
# Structured Draft Schema

## Contents

- [Purpose](#purpose)
- [Rules](#rules)


## Purpose

Populate a UTF-8 JSON file with this structure before rendering a DOCX. Empty optional arrays are allowed. Preserve `[TO CONFIRM: ...]` markers where facts remain unresolved.

```json
{
  "schema_version": "2.0",
  "title": "一种……方法、设备及介质",
  "metadata": {
    "source": "paper.pdf",
    "target": "中国发明专利",
    "draft_status": "供发明人及专利代理师复核"
  },
  "source_analysis": {
    "contains_core_formulas": true,
    "formula_count_in_source": 18,
    "contains_methodology_figures": true
  },
  "source_map": [
    {
      "id": "P001",
      "type": "paper-text",
      "locator": "第3页,2.2节,第1段",
      "summary": "公开核心特征提取流程",
      "confidence": "high"
    },
    {
      "id": "E001",
      "type": "equation",
      "locator": "第4页,公式(1)",
      "summary": "类别原型计算",
      "confidence": "high"
    }
  ],
  "terminology_ledger": [
    {
      "concept": "类别原型",
      "canonical_zh": "类别原型",
      "source_terms": ["class prototype", "prototype"],
      "forbidden_aliases": ["类别中心"]
    }
  ],
  "formula_inventory": [
    {
      "source_id": "E001",
      "source_number": "(1)",
      "technical_role": "根据支持集特征计算类别原型",
      "disposition": "specification-equation-1"
    }
  ],
  "figure_inventory": [
    {
      "source_id": "F001",
      "source_number": "Fig. 2",
      "type": "methodology",
      "disposition": "redraw-as-figure-2"
    }
  ],
  "abstract_figure_number": 1,
  "assumptions": [
    "目标法域为中国"
  ],
  "invention_concept": {
    "technical_problem": "……",
    "technical_means": "……",
    "technical_effect": "……"
  },
  "evidence_ledger": [
    {
      "id": "F1",
      "feature": "……",
      "source_ids": ["P001", "E001"],
      "source_location": "第3页,2.2节",
      "technical_role": "……",
      "effect": "……",
      "support_status": "explicit"
    }
  ],
  "claims": [
    {
      "number": 1,
      "text": "一种……方法,其特征在于,包括:……"
    },
    {
      "number": 2,
      "text": "根据权利要求1所述的方法,其特征在于,……"
    }
  ],
  "claim_feature_map": [
    {
      "claim_number": 1,
      "feature": "根据支持集特征计算类别原型",
      "evidence_ids": ["F1"],
      "specification_locations": ["具体实施方式,实施例1"]
    }
  ],
  "figures": [
    {
      "number": 1,
      "title": "方法流程图",
      "type": "flowchart",
      "orientation": "vertical",
      "claim_number": 1,
      "complete_claim_flow": true,
      "source_ids": ["P001"],
      "nodes": [
        {
          "id": "S1",
          "label": "S1:获取并预处理待检测数据",
          "claim_step": "S1"
        },
        {
          "id": "S2",
          "label": "S2:提取多尺度特征",
          "claim_step": "S2"
        }
      ],
      "edges": [
        {
          "from": "S1",
          "to": "S2",
          "label": ""
        }
      ]
    },
    {
      "number": 2,
      "title": "核心方法结构示意图",
      "type": "methodology",
      "orientation": "horizontal",
      "source_ids": ["F001", "P001"],
      "nodes": [
        {
          "id": "input",
          "label": "输入特征"
        },
        {
          "id": "module",
          "label": "核心处理模块"
        },
        {
          "id": "output",
          "label": "输出特征"
        }
      ],
      "edges": [
        {
          "from": "input",
          "to": "module",
          "label": ""
        },
        {
          "from": "module",
          "to": "output",
          "label": ""
        }
      ]
    }
  ],
  "specification": {
    "technical_field": [
      "本发明涉及……"
    ],
    "background": [
      "……"
    ],
    "invention_content": {
      "problem": [
        "……"
      ],
      "solution": [
        "……"
      ],
      "beneficial_effects": [
        "……"
      ]
    },
    "figure_descriptions": [
      "图1为本发明方法流程图。"
    ],
    "equations": [
      {
        "number": 1,
        "source_location": "论文第4页,公式(1)",
        "source_ids": ["E001"],
        "expression": "O_u = (1/|S_u|) Σ_(x_i,y_i∈S_u) h_γ(x_i)",
        "latex": "O_u = \\frac{1}{|S_u|}\\sum_{(x_i,y_i)\\in S_u} h_\\gamma(x_i)",
        "symbols": [
          {"symbol": "O_u", "meaning": "类别u的类别原型"},
          {"symbol": "S_u", "meaning": "类别u的支持集"},
          {"symbol": "h_\\gamma", "meaning": "监督特征提取器"}
        ],
        "technical_role": "对同一类别样本的监督特征求均值以获得类别原型",
        "description": "其中,O_u表示类别u的类别原型,S_u表示类别u的支持集,h_γ表示监督特征提取器。该公式通过对同一类别样本的监督特征求均值获得类别原型。"
      }
    ],
    "embodiments": [
      {
        "heading": "实施例1",
        "paragraphs": [
          "……"
        ]
      }
    ]
  },
  "abstract": "本发明涉及……",
  "audit": {
    "support_findings": [
      "……"
    ],
    "consistency_findings": [
      "……"
    ]
  },
  "quality_assessment": {
    "status": "review-draft",
    "scores": {
      "evidence_support": {"score": 4, "evidence": "每项权利要求特征均映射到证据台账。"},
      "claim_architecture": {"score": 4, "evidence": "独立权利要求形成完整技术链,并设置从属回退层。"},
      "terminology_consistency": {"score": 4, "evidence": "权利要求、说明书和附图使用统一术语。"},
      "enablement_detail": {"score": 3, "evidence": "已说明主要数据流、公式和实施步骤。"},
      "technical_effect_reasoning": {"score": 3, "evidence": "主要效果已关联到对应技术手段。"},
      "formula_coverage": {"score": 4, "evidence": "核心公式均已收录并定义符号。"},
      "figure_alignment": {"score": 4, "evidence": "主流程图与权利要求1步骤一致。"}
    }
  },
  "inventor_questions": [
    "[TO CONFIRM: ……]"
  ]
}
```

## Rules

- Use integer claim numbers in ascending order.
- Use stable source IDs: `P` for paper text, `E` for equations, `F` for
  source figures, and `C` for code or supplementary evidence.
- Give every `explicit` or `inherent` evidence-ledger item one or more
  `source_ids`.
- Add at least one `claim_feature_map` entry for every formal claim. Map each
  material limitation to evidence-ledger IDs, not merely to a general page.
- Store claim text without repeating the number at its beginning.
- Use arrays for paragraphs to preserve paragraph boundaries.
- Use only `explicit`, `inherent`, `needs-confirmation`, or `unsupported` as evidence status.
- Exclude unsupported features from formal claims.
- Keep internal audit material in the appendix, not in the formal application sections.
- Number figures consecutively from 1.
- Set `abstract_figure_number` to the main figure used as the abstract figure.
- Reuse that exact figure in the specification; do not create a conflicting duplicate.
- The abstract figure should normally be an overall method or system flow that represents the principal independent claim.
- Use `flowchart` as the figure type and `vertical` or `horizontal` as the orientation.
- Use `methodology` for an intermediate architecture, module, feature-flow, or loss-relationship figure.
- A methodology figure does not require `claim_number`, `claim_step`, or `complete_claim_flow`.
- Prefer a paper figure when suitable; otherwise redraw it as a concise black-and-white patent figure.
- Give every node a unique ASCII identifier.
- Keep `claim_step` equal to the corresponding identifier in the method claim, such as `S1`.
- Set `claim_number` to the method claim represented by the figure.
- Set `complete_claim_flow` to `true` for an overall flowchart that must cover every numbered step in that claim.
- Reference every figure in `specification.figure_descriptions`.
- Use concise node labels; put implementation detail in the specification.
- If the paper contains formulas that define core technical operations, populate `specification.equations`.
- Set `source_analysis.contains_core_formulas` after reviewing the paper.
- Number equations consecutively from 1.
- Add a valid `latex` field to every equation; the renderer converts it to editable Office Math.
- Add `source_ids`, structured `symbols`, and `technical_role` to every
  equation.
- Treat `expression` as a readable audit copy, not as the DOCX rendering source.
- Record the paper page and original formula number in `source_location`.
- Define every symbol in `description` and state the technical operation performed by the formula.
- Include formulas in the standalone specification DOCX; do not place them only in an internal appendix.
- Record a disposition for every core source formula and methodology figure.
- Populate `quality_assessment.scores` with a 1-5 score and evidence sentence
  for each dimension required by `static/core/output-contract.md`.
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall
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: 198kUpdated Claude CodeCodexVerifiedInstall