Skip to content

Yuan1z0825/nature-skills / skills/nature-image2ppt

nature-image2ppt

Flagged

Reconstruct slide images, screenshots, scanned PDFs, or image-only PPTX files as object-level editable PowerPoint. Use for 图片转可编辑PPT、截图还原PPT and diagram reconstruction; not authoring a new deck from research notes.

FileKindSize
.gitignoreother573 B
LICENSEother1.1 KB
README.mdmarkdown4.0 KB
README_EN.mdmarkdown4.3 KB
SKILL.mdskill md9.8 KB
agents/openai.yamlconfig272 B
cli/image2ppt/__init__.pyscript22 B
cli/image2ppt/cli.pyscript698 B
cli/image2ppt/runtime/__init__.pyscript69 B
cli/image2ppt/runtime/_input_normalization.pyscript15.9 KB
cli/image2ppt/runtime/_page_artifacts.pyscript4.5 KB
cli/image2ppt/runtime/build_pptx_from_manifest.pyscript54.0 KB
cli/image2ppt/runtime/configure_image_backend.pyscript5.8 KB
cli/image2ppt/runtime/deck_run_state.pyscript5.6 KB
cli/image2ppt/runtime/deck_text_hints.pyscript6.8 KB
cli/image2ppt/runtime/finalize_deck_run.pyscript3.1 KB
cli/image2ppt/runtime/formula_renderer.pyscript9.6 KB
cli/image2ppt/runtime/image_gen.pyscript37.1 KB
cli/image2ppt/runtime/main.pyscript39.7 KB
cli/image2ppt/runtime/make_page_contact_sheet.pyscript1.1 KB
cli/image2ppt/runtime/paddle_text_hints.pyscript10.7 KB
cli/image2ppt/runtime/page_job_status.pyscript2.1 KB
cli/image2ppt/runtime/page_text_metrics.pyscript11.6 KB
cli/image2ppt/runtime/prepare_deck_run.pyscript7.3 KB
cli/image2ppt/runtime/process_asset_sheet.pyscript6.0 KB
cli/image2ppt/runtime/record_imagegen_result.pyscript5.9 KB
cli/image2ppt/runtime/record_page_dispatch.pyscript2.8 KB
cli/image2ppt/runtime/record_page_result.pyscript4.6 KB
cli/image2ppt/runtime/remove_chroma_key.pyscript13.5 KB
cli/image2ppt/runtime/reset_page_job.pyscript2.6 KB
cli/image2ppt/runtime/runtime_env.pyscript18.8 KB
cli/image2ppt/runtime/split_alpha_components.pyscript9.2 KB
cli/image2ppt/runtime/text_hints.pyscript14.0 KB
cli/image2ppt/runtime/validate_pptx.pyscript38.7 KB
cli/pyproject.tomlmanifest570 B
config.example.yamlconfig1.0 KB
manifest.yamlconfig480 B
prompts/page-worker-base.mdmarkdown7.4 KB
prompts/page-worker.mdmarkdown5.1 KB
references/assets-provenance-contract.mdmarkdown2.9 KB
references/cli-helper.mdmarkdown17.8 KB
references/manifest-arrow-extension.mdmarkdown2.5 KB
references/manifest-schema.mdmarkdown19.9 KB
references/object-routing.mdmarkdown3.4 KB
references/ocr-text-hints-contract.mdmarkdown3.0 KB
references/page-decision-tree.mdmarkdown21.7 KB
references/qa-contract.mdmarkdown5.4 KB
references/region-decomposition.mdmarkdown6.5 KB
references/runtime-dependencies.mdmarkdown2.5 KB
references/workflow.mdmarkdown6.7 KB
requirements.txtmanifest176 B
schemas/page-manifest-v2.schema.jsonconfig2.9 KB
scripts/build_page_worker_prompt.pyscript4.1 KB
scripts/inspect_arrow_atomicity.pyscript7.3 KB
scripts/inspect_region_decomposition.pyscript18.1 KB
scripts/postprocess_manifest_arrows.pyscript18.4 KB
scripts/render_image2ppt_qa.pyscript11.1 KB
scripts/run_final_image2ppt_qa.pyscript9.0 KB
scripts/run_image2ppt_qa.pyscript9.5 KB
scripts/runtime_paths.pyscript4.0 KB
scripts/visual_review_evidence.pyscript5.4 KB
tests/support.pyscript6.4 KB
tests/test_console_portability.pyscript1021 B
tests/test_deck_slide_size.pyscript1.1 KB
tests/test_dispatch_concurrency.pyscript2.9 KB
tests/test_formula_renderer.pyscript4.3 KB
tests/test_independence.pyscript2.2 KB
tests/test_input_normalization_alpha.pyscript2.3 KB
tests/test_input_normalization_opc_targets.pyscript1.9 KB
tests/test_isolated_lifecycle.pyscript9.5 KB
tests/test_manifest_arrows.pyscript8.6 KB
tests/test_migration_parity.pyscript3.2 KB
tests/test_multi_agent_backend.pyscript80.8 KB
tests/test_ocr_http.pyscript16.7 KB
tests/test_paddle_result_url_safety.pyscript3.2 KB
tests/test_page_hints.pyscript10.4 KB
tests/test_path_confinement.pyscript7.5 KB
tests/test_pdf_backend.pyscript4.3 KB
tests/test_project_metadata.pyscript4.7 KB
tests/test_quality_contracts.pyscript9.1 KB
tests/test_region_decomposition.pyscript6.2 KB
tests/test_render_guard.pyscript2.4 KB
tests/test_runtime_config.pyscript2.6 KB
tests/test_runtime_paths.pyscript2.2 KB
tests/test_script_inventory.pyscript2.1 KB
tests/test_slide_layout.pyscript9.3 KB
tests/test_state_e2e.pyscript7.8 KB
tests/test_structure_reconstruction.pyscript12.5 KB
tests/test_thin_profile.pyscript4.0 KB
tests/test_visual_review_evidence.pyscript2.3 KB
tests/test_visual_review_runtime.pyscript2.9 KB

scripts/inspect_arrow_atomicity.py

View on GitHub
#!/usr/bin/env python3
"""Verify one manifest arrow maps to one named PowerPoint object."""

from __future__ import annotations

import argparse
import json
import re
import zipfile
from pathlib import Path
from typing import Any
from xml.etree import ElementTree as ET

from postprocess_manifest_arrows import (
    CONNECTOR_PRESETS,
    NS,
    arrow_end_value,
    arrow_items,
    load_run_manifests,
    normalized,
    read_json,
    slide_sort_key,
    write_json,
)
from runtime_paths import resolve_inside


def local_name(tag: str) -> str:
    return tag.rsplit("}", 1)[-1]


def object_map(xml: bytes) -> dict[str, list[ET.Element]]:
    root = ET.fromstring(xml)
    sp_tree = root.find(".//p:spTree", NS)
    result: dict[str, list[ET.Element]] = {}
    if sp_tree is None:
        return result
    for child in list(sp_tree):
        marker = child.find(".//p:cNvPr", NS)
        if marker is None:
            continue
        result.setdefault(str(marker.get("name") or ""), []).append(child)
    return result


def object_text(obj: ET.Element) -> str:
    paragraphs: list[str] = []
    for paragraph in obj.findall(".//a:p", NS):
        paragraphs.append("".join(node.text or "" for node in paragraph.findall(".//a:t", NS)))
    return "\n".join(paragraphs)


def inspect_arrow(obj: ET.Element, item: dict[str, Any], role: str) -> tuple[dict[str, Any], list[str]]:
    errors: list[str] = []
    geometry = obj.find(".//a:prstGeom", NS)
    preset = geometry.get("prst") if geometry is not None else None
    details: dict[str, Any] = {
        "kind": local_name(obj.tag),
        "preset": preset,
        "text": object_text(obj),
    }
    if role == "connector":
        connector = str(item.get("connector") or "straight").lower()
        expected_preset = CONNECTOR_PRESETS.get(connector)
        line = obj.find(".//a:ln", NS)
        head = line.find("a:headEnd", NS) if line is not None else None
        tail = line.find("a:tailEnd", NS) if line is not None else None
        details.update(
            {
                "connector": connector,
                "start_arrow": head.get("type") if head is not None else None,
                "end_arrow": tail.get("type") if tail is not None else None,
            }
        )
        if details["kind"] != "cxnSp":
            errors.append("connector is not one p:cxnSp object")
        if preset != expected_preset:
            errors.append(f"connector preset is {preset!r}, expected {expected_preset!r}")
        expected_start = arrow_end_value(item.get("start_arrow"))
        expected_end = arrow_end_value(item.get("end_arrow"))
        if details["start_arrow"] != expected_start:
            errors.append(f"start arrowhead is {details['start_arrow']!r}, expected {expected_start!r}")
        if details["end_arrow"] != expected_end:
            errors.append(f"end arrowhead is {details['end_arrow']!r}, expected {expected_end!r}")
    else:
        expected_preset = str(item.get("preset") or "")
        if details["kind"] != "sp":
            errors.append("filled arrow is not one p:sp AutoShape")
        if normalized(preset) != normalized(expected_preset):
            errors.append(f"filled arrow preset is {preset!r}, expected {expected_preset!r}")
        if "text" in item and details["text"] != str(item.get("text") or ""):
            errors.append(f"embedded arrow text is {details['text']!r}, expected {item.get('text')!r}")
    return details, errors


def inspect(manifests: list[dict[str, Any]], pptx: Path) -> dict[str, Any]:
    errors: list[str] = []
    inspected: list[dict[str, Any]] = []
    with zipfile.ZipFile(pptx) as archive:
        slide_names = sorted(
            [name for name in archive.namelist() if re.fullmatch(r"ppt/slides/slide\d+\.xml", name)],
            key=slide_sort_key,
        )
        if len(slide_names) != len(manifests):
            errors.append(f"PPTX has {len(slide_names)} slides but {len(manifests)} manifests were supplied")
        for slide_index, (slide_name, manifest) in enumerate(zip(slide_names, manifests), start=1):
            objects = object_map(archive.read(slide_name))
            seen_ids: set[str] = set()
            for shape_index, item, role in arrow_items(manifest):
                object_id = str(item.get("id") or "").strip()
                if not object_id:
                    errors.append(f"slide {slide_index} shapes[{shape_index}] has no arrow id")
                    continue
                if object_id in seen_ids:
                    errors.append(f"slide {slide_index} repeats arrow id {object_id!r}")
                    continue
                seen_ids.add(object_id)
                matches = objects.get(object_id, [])
                if len(matches) != 1:
                    errors.append(
                        f"slide {slide_index} arrow {object_id!r} maps to {len(matches)} PowerPoint objects; expected exactly one"
                    )
                    continue
                details, object_errors = inspect_arrow(matches[0], item, role)
                errors.extend(f"slide {slide_index} {object_id}: {error}" for error in object_errors)
                inspected.append(
                    {
                        "slide_index": slide_index,
                        "shape_index": shape_index,
                        "id": object_id,
                        "role": role,
                        "pptx_object": details,
                    }
                )
    expected = sum(len(arrow_items(manifest)) for manifest in manifests)
    return {
        "schema_version": "image2ppt-manifest-arrow-inspection-v1",
        "passed": not errors and len(inspected) == expected,
        "pptx": str(pptx.resolve()),
        "errors": errors,
        "summary": {
            "expected_arrows": expected,
            "inspected_arrows": len(inspected),
            "connectors": sum(item["role"] == "connector" for item in inspected),
            "filled_arrows": sum(item["role"] == "filled" for item in inspected),
            "fragmented_or_missing": len(errors),
        },
        "arrows": inspected,
    }


def main() -> int:
    parser = argparse.ArgumentParser(description="Inspect Image2PPT arrows in an image2ppt-built PPTX")
    parser.add_argument("pptx", type=Path)
    source = parser.add_mutually_exclusive_group(required=True)
    source.add_argument("--manifest", type=Path)
    source.add_argument("--run", type=Path)
    parser.add_argument("--out", type=Path, required=True)
    args = parser.parse_args()
    if args.run:
        scope = args.run.expanduser().resolve()
        paths, _default = load_run_manifests(scope)
    else:
        manifest = args.manifest.expanduser().resolve()
        scope = manifest.parent
        paths = [manifest]
    try:
        pptx = resolve_inside(scope, args.pptx)
        out = resolve_inside(scope, args.out)
    except ValueError as exc:
        raise SystemExit(f"arrow inspection paths must stay inside {scope}") from exc
    try:
        report = inspect([read_json(path) for path in paths], pptx)
    except Exception as exc:
        report = {
            "schema_version": "image2ppt-manifest-arrow-inspection-v1",
            "passed": False,
            "errors": [repr(exc)],
            "summary": {"fragmented_or_missing": 1},
        }
    write_json(out, report)
    print(json.dumps(report, ensure_ascii=True, indent=2))
    return 0 if report["passed"] else 2


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