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

cli/image2ppt/runtime/deck_text_hints.py

View on GitHub
#!/usr/bin/env python3
"""Generate text hints for every page of a prepared run.

Runs as part of `image2ppt prepare`, after page directories exist: each
`pages/page_NNN/` receives canonical `text_hints.json` and `text_hints.png`
files so page workers find their text measurements already in place.

Backend selection per run:
- With a PaddleOCR token (PADDLE_OCR_TOKEN env var, or PADDLE_OCR_TOKEN in the
  active config.yaml): an original PDF is submitted as one multi-page job;
  image and PPTX inputs submit each normalized source.png as its own job.
  OCR coordinates are rescaled to each page's actual source.png resolution
  and re-measured locally with the ink metrics.
- Without a token, or when the service fails: the built-in offline detector
  (`text_hints.py`) runs per page, so every page still gets hints.

Hint generation is best-effort: a page that fails is reported and skipped,
and the page worker can regenerate with `image2ppt page hints <page_dir>`.
"""

from __future__ import annotations

import argparse
import json
import os
import sys

if hasattr(sys.stdout, "reconfigure"):
    sys.stdout.reconfigure(encoding="utf-8")
if hasattr(sys.stderr, "reconfigure"):
    sys.stderr.reconfigure(encoding="utf-8")
from pathlib import Path

from PIL import Image

from deck_run_state import load_deck, load_jobs, page_dir_for, run_dir_from_target
from text_hints import draw_overlay, page_text_hints

HINTS_JSON = "text_hints.json"
HINTS_PNG = "text_hints.png"


def paddle_token() -> str:
    token = os.environ.get("PADDLE_OCR_TOKEN", "").strip()
    if token:
        return token
    try:
        from runtime_env import config_path, read_config_file

        return str(read_config_file(config_path()).get("PADDLE_OCR_TOKEN", "")).strip()
    except Exception:
        return ""


def write_hints(page_dir: Path, hints: dict, overlay: bool) -> None:
    (page_dir / HINTS_JSON).write_text(json.dumps(hints, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
    if overlay:
        draw_overlay(Image.open(page_dir / "source.png"), hints["lines"], page_dir / HINTS_PNG)


def builtin_page(page_dir: Path) -> dict:
    hints = page_text_hints(page_dir)
    hints["backend"] = "builtin-ink"
    return hints


def paddle_pages(run_dir: Path, deck: dict, page_dirs: list[Path], token: str, timeout: int) -> dict[Path, dict]:
    """Fetch OCR results without converting normalized images to a PDF."""
    from paddle_text_hints import DEFAULT_MODEL, build_page_hints, submit_and_fetch

    original_pdf = None
    if str(deck.get("input_type", "")) == "pdf":
        input_dir = run_dir / "input"
        candidates = sorted(input_dir.glob("*.pdf")) if input_dir.exists() else []
        original_pdf = candidates[0] if candidates else None

    if original_pdf is not None:
        pages = submit_and_fetch(original_pdf, token, DEFAULT_MODEL, timeout)
        if len(pages) != len(page_dirs):
            raise RuntimeError(f"OCR returned {len(pages)} pages for {len(page_dirs)} page dirs")
        return {page_dir: build_page_hints(page_dir, pruned) for page_dir, pruned in zip(page_dirs, pages)}

    results = {}
    for page_dir in page_dirs:
        pages = submit_and_fetch(page_dir / "source.png", token, DEFAULT_MODEL, timeout)
        if len(pages) != 1:
            raise RuntimeError(f"OCR returned {len(pages)} pages for {page_dir.name}; expected 1")
        results[page_dir] = build_page_hints(page_dir, pages[0])
    return results


def main() -> int:
    parser = argparse.ArgumentParser(description="Generate per-page text hints for a prepared run.")
    parser.add_argument("run", help="Run directory or deck_manifest.json path.")
    parser.add_argument("--timeout", type=int, default=300, help="OCR job timeout in seconds.")
    parser.add_argument("--no-overlay", action="store_true", help="Skip the labeled overlay images.")
    args = parser.parse_args()

    run_dir = run_dir_from_target(args.run)
    deck = load_deck(run_dir)
    jobs = load_jobs(run_dir)
    page_dirs = [page_dir_for(run_dir, page) for page in jobs.get("pages", [])]
    page_dirs = [d for d in page_dirs if (d / "source.png").exists()]
    if not page_dirs:
        print("text-hints: no pages with source.png; skipped", file=sys.stderr)
        return 0

    token = paddle_token()
    results: dict[Path, dict] = {}
    backend = "builtin-ink"
    if not token:
        print(
            "text-hints: no PaddleOCR token configured; falling back to the built-in offline "
            "detector (geometry only — it measures where text is and how large, but cannot read "
            "it). A free PaddleOCR-VL token adds recognized text content and cleaner block "
            "boundaries, noticeably improving text fidelity in the final PPT. The free personal quota "
            "is currently more than enough for this skill, so applying is risk-free with no extra "
            "cost. ASK THE USER once "
            "before reconstructing pages: configure a token now (apply at "
            "https://aistudio.baidu.com/account/accessToken, then `image2ppt config "
            "--paddle-ocr-token <token>` and `image2ppt run hints <run>` to regenerate this run's "
            "hints), or continue with the offline result. Respect their choice and do not ask again.",
            file=sys.stderr,
        )
    if token:
        try:
            results = paddle_pages(run_dir, deck, page_dirs, token, args.timeout)
            backend = "paddleocr-vl"
        except Exception as exc:
            print(f"text-hints: PaddleOCR failed ({exc}); falling back to built-in detector", file=sys.stderr)
            results = {}

    written = 0
    for page_dir in page_dirs:
        try:
            hints = results.get(page_dir) or builtin_page(page_dir)
            # Dense diagrams can defeat the OCR layout model entirely (the
            # whole figure is classified as an image and only a headline
            # survives). When OCR found almost nothing but the offline
            # detector finds plenty, the geometric hints are more useful.
            if hints.get("backend") == "paddleocr-vl" and len(hints["lines"]) <= 2:
                offline = builtin_page(page_dir)
                if len(offline["lines"]) >= 6:
                    print(
                        f"text-hints: {page_dir.name}: OCR found {len(hints['lines'])} text lines but the "
                        f"offline detector found {len(offline['lines'])}; using the offline result for this page",
                        file=sys.stderr,
                    )
                    hints = offline
            write_hints(page_dir, hints, overlay=not args.no_overlay)
            written += 1
        except Exception as exc:
            print(f"text-hints: {page_dir.name} failed ({exc}); worker can run `image2ppt page hints` itself", file=sys.stderr)
    print(f"text-hints: wrote {written}/{len(page_dirs)} pages (backend={backend})")
    return 0


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