Skip to content

JuneYaooo/gpt-image2-ppt-skills

gpt-image2-ppt

Verified

Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<collection>/STYLE_ID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx. Use when the user asks to make a presentation, slides, deck, pitch deck, investor PPT, magazine-style PPT, or 做一份 PPT / 生成幻灯片 / 用 gpt-image 生成 PPT / 按这个模板生成 PPT.

FileKindSize
SKILL.mdskill md56.8 KB
agents/openclaw.yamlconfig1006 B
examples/README.mdmarkdown2.8 KB
examples/book-sharing/recipe.mdmarkdown787 B
examples/book-sharing/slides_plan.mdmarkdown1.8 KB
examples/courseware/recipe.mdmarkdown725 B
examples/courseware/slides_plan.mdmarkdown2.0 KB
examples/editable-pptx-poc/demo1-cover.scene.jsonconfig912 B
examples/editable-pptx/case05-summer-poster/README.mdmarkdown4.1 KB
examples/editable-pptx/case05-summer-poster/clean-plate.pngbinary2.5 MB
examples/editable-pptx/case05-summer-poster/edge-check-black.pngbinary697.7 KB
examples/editable-pptx/case05-summer-poster/edge-check-white.pngbinary695.4 KB
examples/editable-pptx/case05-summer-poster/editable.pptxbinary3.3 MB
examples/editable-pptx/case05-summer-poster/layers/mascot-icecream-group.pngbinary813.1 KB
examples/editable-pptx/case05-summer-poster/original.pngbinary2.4 MB
examples/editable-pptx/case05-summer-poster/quality-report.jsonconfig355 B
examples/editable-pptx/case05-summer-poster/rendered.pngbinary3.7 MB
examples/editable-pptx/case05-summer-poster/slide-01.scene.jsonconfig3.3 KB
examples/investor-pitch/recipe.mdmarkdown803 B
examples/investor-pitch/slides_plan.mdmarkdown2.5 KB
examples/product-launch/recipe.mdmarkdown841 B
examples/product-launch/slides_plan.mdmarkdown1.8 KB
examples/thesis-defense/recipe.mdmarkdown806 B
examples/thesis-defense/slides_plan.mdmarkdown2.4 KB
examples/weekly-report/recipe.mdmarkdown771 B
examples/weekly-report/slides_plan.mdmarkdown1.6 KB
scripts/codex_backend.pyscript9.1 KB
scripts/editable_pptx/__init__.pyscript398 B
scripts/editable_pptx/layers.pyscript2.0 KB
scripts/editable_pptx/masking.pyscript3.8 KB
scripts/editable_pptx/poc.pyscript5.7 KB
scripts/editable_pptx/provider.pyscript2.7 KB
scripts/editable_pptx/renderer.pyscript6.0 KB
scripts/editable_pptx/scene.pyscript4.8 KB
scripts/editable_pptx/workflow.pyscript6.0 KB
scripts/generate_ppt.pyscript162.9 KB
scripts/image_generator.pyscript26.0 KB
scripts/md_to_plan.pyscript5.9 KB
scripts/render_template.pyscript21.7 KB
scripts/runtime_profile.pyscript6.3 KB
scripts/template_analyzer.pyscript42.9 KB

scripts/editable_pptx/workflow.py

View on GitHub
"""Build opt-in editable PPTX decks from per-slide scene manifests."""

from __future__ import annotations

import copy
import json
import re
from dataclasses import dataclass
from pathlib import Path
from typing import Iterable

from render_template import check_render_backend, render_pptx_to_pngs

from .renderer import render_editable_deck
from .scene import EditableScene


@dataclass(frozen=True)
class EditableBuildResult:
    pptx_path: Path
    report_path: Path
    render_dir: Path
    scene_files: tuple[Path, ...]


def require_editable_render_backend() -> tuple[str, ...]:
    """Fail early unless editable PPTX output can be rendered back to images."""
    ok, messages = check_render_backend()
    if ok:
        return tuple(messages)
    details = "\n".join(f"  {message}" for message in messages)
    raise RuntimeError(
        "可编辑模式需要可执行的 PPTX 回渲染后端,才能把生成结果转成图片并由多模态 agent 人工验收。\n"
        "支持 Windows PowerPoint、macOS Keynote 或 LibreOffice。\n"
        f"探测结果:\n{details}\n"
        "可安装 LibreOffice 后重试:\n"
        "  Windows: winget install LibreOffice.LibreOffice\n"
        "  macOS:   brew install --cask libreoffice(或安装 Keynote)\n"
        "  Linux:   sudo apt-get install -y libreoffice"
    )


def render_editable_preview(
    pptx_path: Path | str,
    output_dir: Path | str,
    expected_slide_count: int,
) -> Path:
    """Render editable output and verify that every slide produced a PNG."""
    require_editable_render_backend()
    render_dir = Path(output_dir) / "editable_renders"
    rendered = render_pptx_to_pngs(pptx_path, out_dir=render_dir, force=True)
    pages = sorted(rendered.glob("page-*.png"))
    if len(pages) != expected_slide_count:
        raise RuntimeError(
            "可编辑 PPTX 回渲染页数不匹配:"
            f"预期 {expected_slide_count} 页,实际 {len(pages)} 页({rendered})"
        )
    return rendered


def discover_scene_files(scene_dir: Path | str, slide_numbers: Iterable[int]) -> tuple[Path, ...]:
    directory = Path(scene_dir)
    numbers = sorted({int(number) for number in slide_numbers})
    if not numbers:
        raise ValueError("可编辑模式至少需要一个 slide scene")
    if not directory.is_dir():
        raise ValueError(f"editable scene 目录不存在: {directory}")
    files: list[Path] = []
    missing: list[str] = []
    for number in numbers:
        path = directory / f"slide-{number:02d}.scene.json"
        if path.is_file():
            files.append(path)
        else:
            missing.append(path.name)
    if missing:
        raise ValueError(f"可编辑模式缺少 scene: {', '.join(missing)}(目录: {directory})")
    return tuple(files)


def _resolve_scene_paths(data: dict, base_dir: Path) -> dict:
    resolved = copy.deepcopy(data)
    for key in ("clean_plate", "visual_master", "repair_mask"):
        value = resolved.get(key)
        if value and not Path(str(value)).is_absolute():
            resolved[key] = str((base_dir / str(value)).resolve())
    for element in resolved.get("elements") or []:
        asset = element.get("asset")
        if asset and not Path(str(asset)).is_absolute():
            element["asset"] = str((base_dir / str(asset)).resolve())
    return resolved


def load_scene_file(path: Path | str) -> EditableScene:
    scene_path = Path(path).resolve()
    data = json.loads(scene_path.read_text(encoding="utf-8"))
    return EditableScene.from_dict(_resolve_scene_paths(data, scene_path.parent))


def inventory_scenes(scenes: Iterable[EditableScene]) -> dict[str, int]:
    counts = {
        "native_text_count": 0,
        "image_layer_count": 0,
        "native_shape_count": 0,
        "connector_count": 0,
    }
    for scene in scenes:
        for element in scene.elements:
            key = f"{element.type}_count"
            if key in counts:
                counts[key] += 1
    return counts


def _safe_title(title: str) -> str:
    return re.sub(r"[^\w\u4e00-\u9fff\-]+", "_", title)[:60] or "deck"


def build_editable_output(
    scene_dir: Path | str,
    slide_numbers: Iterable[int],
    output_dir: Path | str,
    title: str,
) -> EditableBuildResult:
    scene_files = discover_scene_files(scene_dir, slide_numbers)
    scenes = tuple(load_scene_file(path) for path in scene_files)
    declared = [scene.slide_number for scene in scenes]
    if len(declared) != len(set(declared)):
        raise ValueError(f"editable scene 的 slide_number 重复: {declared}")

    for path, scene in zip(scene_files, scenes):
        match = re.fullmatch(r"slide-(\d+)\.scene\.json", path.name)
        expected_number = int(match.group(1)) if match else None
        if expected_number != scene.slide_number:
            raise ValueError(
                f"editable scene 文件名与 slide_number 不一致: {path.name} -> {scene.slide_number}"
            )

    output = Path(output_dir)
    output.mkdir(parents=True, exist_ok=True)
    pptx_path = output / f"{_safe_title(title)}-editable.pptx"
    render_editable_deck(scenes, pptx_path)
    render_dir = render_editable_preview(pptx_path, output, len(scenes))

    report = {
        "status": "rendered_pending_manual_review",
        "mode": "editable",
        "slide_count": len(scenes),
        **inventory_scenes(scenes),
        "picture_count": len(scenes) + sum(
            1 for scene in scenes for element in scene.elements if element.type == "image_layer"
        ),
        "scene_files": [str(path) for path in scene_files],
        "pptx": str(pptx_path),
        "render_dir": str(render_dir),
        "rendered_pages": [str(path) for path in sorted(render_dir.glob("page-*.png"))],
        "manual_visual_review_required": True,
    }
    report_path = output / "editable-quality-report.json"
    report_path.write_text(json.dumps(report, ensure_ascii=False, indent=2), encoding="utf-8")
    return EditableBuildResult(
        pptx_path=pptx_path,
        report_path=report_path,
        render_dir=render_dir,
        scene_files=scene_files,
    )
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