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

scripts/disclosure/pptx_to_md.py

View on GitHub
#!/usr/bin/env python3
"""
将 PowerPoint(.pptx)按页导出为 Markdown,并抽取幻灯片中的嵌入图片,便于 Step 2 扫描与 Agent Read。

依赖 python-pptx(见仓库根目录 requirements.txt)。

用法:
  python pptx_to_md.py --input review.pptx --output outputs/case/review.md
  python pptx_to_md.py -i a.pptx -o b/out.md --media-dir b/slide_images

默认图片目录:与输出 .md 同级的「{md 文件名}_media/」。
"""

from __future__ import annotations

import argparse
import sys
from pathlib import Path


def _require_pptx():
    try:
        from pptx import Presentation
        from pptx.enum.shapes import MSO_SHAPE_TYPE
    except ImportError:
        print(
            "缺少依赖 python-pptx。请在技能根目录执行: pip install -r requirements.txt",
            file=sys.stderr,
        )
        sys.exit(1)
    return Presentation, MSO_SHAPE_TYPE


def _walk_shapes(shapes, MSO_SHAPE_TYPE):
    for shape in shapes:
        if shape.shape_type == MSO_SHAPE_TYPE.GROUP:
            yield from _walk_shapes(shape.shapes, MSO_SHAPE_TYPE)
        else:
            yield shape


def _shape_text(shape) -> str:
    if getattr(shape, "has_text_frame", False):
        t = (shape.text_frame.text or "").strip()
        return t
    if getattr(shape, "has_table", False):
        rows = []
        for row in shape.table.rows:
            cells = []
            for cell in row.cells:
                cells.append((cell.text or "").strip().replace("\n", " "))
            rows.append("| " + " | ".join(cells) + " |")
        if rows:
            return "\n".join(rows)
    return ""


def _rel_media_path(out_file: Path, media_file: Path) -> str:
    try:
        return media_file.relative_to(out_file.parent).as_posix()
    except ValueError:
        return media_file.as_posix()


def _run(input_pptx: Path, output_md: Path, media_dir: Path | None) -> int:
    Presentation, MSO_SHAPE_TYPE = _require_pptx()

    if not input_pptx.is_file():
        print(f"输入文件不存在: {input_pptx}", file=sys.stderr)
        return 2
    suf = input_pptx.suffix.lower()
    if suf not in (".pptx", ".ppsx"):
        print("警告: 期望 .pptx / .ppsx(OOXML);旧版 .ppt 不支持。", file=sys.stderr)

    output_md = output_md.resolve()
    output_md.parent.mkdir(parents=True, exist_ok=True)

    if media_dir is None:
        media_dir = output_md.parent / f"{output_md.stem}_media"
    else:
        media_dir = media_dir.resolve()
    media_dir.mkdir(parents=True, exist_ok=True)

    try:
        prs = Presentation(str(input_pptx))
    except Exception as e:
        print(f"无法打开演示文稿: {e}", file=sys.stderr)
        return 3

    lines: list[str] = [
        f"<!-- 由 pptx_to_md.py 自 {input_pptx.name} 转换,勿手改本行元信息 -->\n"
    ]
    img_counter = [0]

    for sn, slide in enumerate(prs.slides, start=1):
        lines.append(f"\n## 第 {sn} 页\n")

        for shape in _walk_shapes(slide.shapes, MSO_SHAPE_TYPE):
            if shape.shape_type == MSO_SHAPE_TYPE.PICTURE:
                try:
                    img = shape.image
                    ext = (img.ext or "png").lower()
                    if ext == "jpeg":
                        ext = "jpg"
                    img_counter[0] += 1
                    fname = f"slide{sn:02d}_img{img_counter[0]:04d}.{ext}"
                    out_img = media_dir / fname
                    out_img.write_bytes(img.blob)
                    rel = _rel_media_path(output_md, out_img)
                    lines.append(f"\n![]({rel})\n")
                except Exception as e:
                    print(f"警告: 第 {sn} 页抽取图片失败: {e}", file=sys.stderr)
                continue

            block = _shape_text(shape)
            if block:
                lines.append(block)
                lines.append("\n\n")

        try:
            nf = slide.notes_slide.notes_text_frame
            note_txt = (nf.text or "").strip() if nf is not None else ""
            if note_txt:
                lines.append("\n**备注**:\n\n")
                lines.append(note_txt)
                lines.append("\n\n")
        except (AttributeError, ValueError):
            pass

    body = "".join(lines).rstrip() + "\n"
    output_md.write_text(body, encoding="utf-8")

    print(f"已写入: {output_md}")
    print(f"图片目录: {media_dir}")
    return 0


def main() -> int:
    p = argparse.ArgumentParser(description="PowerPoint (.pptx) → Markdown + 抽取图片")
    p.add_argument("-i", "--input", required=True, type=Path, help="输入 .pptx / .ppsx 路径")
    p.add_argument("-o", "--output", required=True, type=Path, help="输出 .md 路径")
    p.add_argument(
        "--media-dir",
        type=Path,
        default=None,
        help="图片输出目录(默认:与 .md 同级的 {md 主名}_media)",
    )
    args = p.parse_args()
    return _run(args.input, args.output, args.media_dir)


if __name__ == "__main__":
    raise SystemExit(main())
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