Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add DSY-Xueai/image2editable --skill image-to-pptgit clone --depth 1 https://github.com/DSY-Xueai/image2editableWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dsy-xueai/image2editable/image-to-ppt)<a href="https://agentmods.dev/skills/dsy-xueai/image2editable/image-to-ppt"><img src="https://agentmods.dev/badge/skills/dsy-xueai/image2editable/image-to-ppt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dsy-xueai/image2editable/image-to-ppt"><img src="https://agentmods.dev/badge/skills/dsy-xueai/image2editable/image-to-ppt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00098 | $0.04625 |
| Opus 5 | $0.00049 | $0.02312 |
| Sonnet 5 | $0.00020 | $0.00925 |
| Haiku 4.5 | $0.00010 | $0.00462 |
Grade A, and why
image-to-ppt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image to PPT
把输入图片重建为分层 PPTX。保持严格语义拆分;质量校验失败时停止,不要将整页 flatten 为单张图片。
环境
-
使用 Python 3.10–3.12;该范围与当前项目测试和分发契约一致。
-
安装
torch>=2.5.1、torchvision>=0.20.1、Transformers 和 SAM 2.1。运行pip install -r references/requirements.txt。 -
LaMa 由内置的本地 TorchScript adapter 调用,依赖随
references/requirements.txt中的torch>=2.5.1,<3安装。产品安装默认从已验证的 runtime receipt 解析模型;独立 skill 必须通过绝对路径设置LAMA_MODEL,且文件须匹配固定 Big-LaMa 身份。 -
若 OCR 不可用,先让用户选择:PaddleOCR(中文、英文和复杂版面识别通常更好,执行
python -m pip install "paddleocr==3.7.0" "paddlepaddle==3.3.1" "PaddleX==3.7.2" "PyYAML==6.0.2")或 Tesseract(较轻量,但还要安装系统 Tesseract,执行python -m pip install pytesseract)。未经用户确认,不要安装任何 OCR。 -
完整仓库或已安装
image2editable产品包时,OCR 就绪后先让用户确认,再依次运行image2editable models install runtime和image2editable doctor。前者下载并校验固定的 SAM、LaMa、DINO runtime receipt;取消时不得下载。 -
如果用户明确选择
local,再依次运行python -m pip install ".[agent-local]"、image2editable models install agent和image2editable doctor --agent-local;模型下载仍须先获得用户确认,仓库不包含模型权重。 -
纯 standalone 环境中,独立 skill 不假设该包存在,也不运行
image2editable doctor。开始转换前,必须把SAM2_MODEL、LAMA_MODEL和GROUNDING_DINO_MODEL设置为绝对本地路径;SAM2_MODEL、LAMA_MODEL必须指向文件,GROUNDING_DINO_MODEL必须指向目录,并运行最小只读预检:python -c "import os; from pathlib import Path; names=('SAM2_MODEL','LAMA_MODEL','GROUNDING_DINO_MODEL'); raw={name: os.environ.get(name, '') for name in names}; paths={name: Path(value) for name, value in raw.items()}; assert all(raw.values()) and all(path.is_absolute() for path in paths.values()) and paths['SAM2_MODEL'].is_file() and paths['LAMA_MODEL'].is_file() and paths['GROUNDING_DINO_MODEL'].is_dir(); print('runtime model paths: ok')" -
优先使用当前平台已正确安装的硬件加速环境;产品环境须通过
doctor,所有环境须通过下列设备预检。不要仅为 WSL 建议离开已经可用的环境:python -c "import sys, torch; print({'platform': sys.platform, 'cuda': torch.cuda.is_available(), 'rocm': torch.version.hip})" -
Windows/Linux 沿用 PyTorch 的设备接口:PyTorch 报告 CUDA 可用时使用 CUDA,ROCm 环境使用 PyTorch 提供的兼容设备接口。
-
macOS 保持当前受支持的设备选择;在完成真实 Apple Silicon 回归前,不把 MPS 自动设为新默认。
-
CPU 仍运行完整模型和相同质量门禁,包括 SAM 2.1 large,不替换为轻量分割模型,但推理会显著较慢。
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/requirements.txt 1.8 KB
- scripts/__init__.py 44 B runs code
- scripts/bg_model.py 40 KB runs code
- scripts/component_contracts.py 41 KB runs code
- scripts/component_quality.py 53 KB runs code
- scripts/component_underlay.py 19 KB runs code
- scripts/fg_extract.py 47 KB runs code
- scripts/image_to_ppt.py 193 KB runs code
- scripts/initial_diagnostics.py 3.0 KB runs code
- scripts/lama_inpaint.py 7.5 KB runs code
- scripts/lama_worker.py 808 B runs code
- scripts/object_detect.py 11 KB runs code
- scripts/object_worker.py 1.7 KB runs code
- scripts/ocr_worker.py 8.7 KB runs code
- scripts/performance_trace.py 5.4 KB runs code
- scripts/ppt_assemble.py 26 KB runs code
- scripts/runtime_model_paths.py 4.6 KB runs code
- scripts/sam_worker.py 73 KB runs code
- scripts/text_detect.py 38 KB runs code
- scripts/visual_compare_qa.py 3.6 KB runs code
- scripts/visual_segment.py 75 KB runs code
- scripts/visual_worker.py 6.3 KB runs code
- scripts/worker_resources.py 3.1 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 169 lines · 98 tokens per session scan A c19205f0a2b9
image-to-ppt is a skill published in the GitHub repository DSY-Xueai/image2editable (37 stars, last pushed 7d ago), licensed MIT. It adds 98 tokens to every session and 4,625 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
LaTeX工具
A tool for creating, compiling, and checking mathematical modelling papers written in LaTeX, a document system often used for technical writing.
Use 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…
DOCX工具
A tool for creating, editing, checking, and converting Microsoft Word DOCX files. It also handles LaTeX research papers, mathematical formulas, tables, tracked changes, and comments.
Excel工具
A guide for using Excel tools to read, write, and recalculate spreadsheet files. It includes a rule for treating the first row as data when a spreadsheet has no column headings.
thesaurus-get-{word}
Returns synonyms and antonyms for the given word.
docs-patterns
Documentation writing conventions -- style, structure, tone, and quality standards.