image-to-psd

image-to-psd is a skill for Claude Code from DSY-Xueai/image2editable. It costs 67 tokens per session (2,149 once invoked), scanned A, original, MIT.

A skill that reconstructs images as editable, layered Photoshop files. It separates the repaired background, visual components, and text into layers instead of leaving the page as one flat image.

In plain words
What is it for?
Use it with PNG, JPEG, BMP, TIFF, or WebP images to create PSD files with transparent visual components and editable text layers. It does not handle PDFs or PowerPoint files.
Why use it?
It helps when a finished image needs to be edited as individual parts. Quality checks stop the process if the result does not meet the required layer structure.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the image2editable plugin — 2 skills shipped together

Good fit Use it with PNG, JPEG, BMP, TIFF, or WebP images to create PSD files with transparent visual components and editable text layers. It does not handle PDFs or PowerPoint files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dsy-xueai/image2editable/image-to-psd
Install

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.

Any agent
npx skills add DSY-Xueai/image2editable --skill image-to-psd
Clone the repo
git clone --depth 1 https://github.com/DSY-Xueai/image2editable

Made for: Claude Code.

Or install image2editable, the plugin that ships this one along with the rest of its 2 skills.

Wrote 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.

agentmods badge for image-to-psd

README.md
[![agentmods](https://agentmods.dev/badge/skills/dsy-xueai/image2editable/image-to-psd/github.svg)](https://agentmods.dev/skills/dsy-xueai/image2editable/image-to-psd)
Your own site
<a href="https://agentmods.dev/skills/dsy-xueai/image2editable/image-to-psd"><img src="https://agentmods.dev/badge/skills/dsy-xueai/image2editable/image-to-psd/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.

agentmods 80×15 button for image-to-psd

Your own site · 80×15
<a href="https://agentmods.dev/skills/dsy-xueai/image2editable/image-to-psd"><img src="https://agentmods.dev/badge/skills/dsy-xueai/image2editable/image-to-psd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,149 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.02149
Opus 5.5 $0.00027 $0.00860
Sonnet 5.5 $0.00013 $0.00430
Haiku 4.5 $0.00007 $0.00215

Measured 1mo ago against content hash 596101fb505c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

image-to-psd 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 1mo ago.

The scan reads SKILL.md. This mod also ships 32 executable files (scripts/__init__.py, scripts/art_text.py, scripts/bg_model.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/image-to-psd/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Image to PSD

把图片重建为分层 PSD。文字只由可编辑文字图层贡献一次;视觉组件和背景不得残留文字像素。质量检查未通过时继续针对性修复并复检,不把整页图片伪装成分层结果。

全部文字包括艺术字均须可编辑,保留原有曲线、描边及多色;不得用文字截图、转曲轮廓或透明文字覆盖冒充。复用有效识别和组件资产,避免重复推理;只有实际渲染和编辑验收通过才能作为成品交付。

局部 OCR 找回文字后,先验证源图、manifest、资产哈希和文字增量依赖。可证明安全时只更新受影响像素及背景,保留其余有效组件;并行路径也必须使用新增文字清理后的图像。重建范围覆盖实际文字清理边缘,不能仅依据原 OCR 框。

输入与授权

识别阶段复用 text-context-cache 中匹配像素、语言和 OCR 实现的整行复核结果,避免重复处理相同冲突;不同栏位的文字不得因宽检测结果而丢失独立位置与样式。共享 OCR 的 words/runs 元数据不代表 PSD 已具备对应的艺术字渲染能力,必须核验实际文字图层效果。

  • 仅支持 PNG、JPEG、BMP、TIFF 和 WebP。
  • 单图输出一个 .psd;多图输出到目录,同名文件使用稳定序号区分。
  • 每个 PSD 包含修复背景、按 z-order 排列的透明视觉组件和可编辑文字图层。
  • PSD 写入依赖已授权的 Aspose.PSD。模型推理前必须设置 ASPOSE_PSD_LICENSE;授权缺失或无效时立即停止。

Windows PowerShell:

$env:ASPOSE_PSD_LICENSE="C:\path\to\Aspose.PSD.lic"

Linux/macOS:

export ASPOSE_PSD_LICENSE=/path/to/Aspose.PSD.lic

授权文件、模型权重、OCR 缓存和运行产物都不存放在此 skill 中。

环境准备与图片兼容入口

转换前必须阅读并执行 自动环境准备。完整仓库和仅安装 Skill 在 Windows、macOS、Linux 都自动准备缺少的 Python、Git、项目 Runtime、依赖、OCR 和模型。不得为依赖或模型安装向用户询问确认;遵循宿主实际审批与权限限制。Windows 新安装优先 D 盘,再选其他非 C 本地磁盘,仅在不存在其他本地磁盘时使用 C 盘;macOS/Linux 优先其他已挂载的本地磁盘,否则使用用户目录。使用 scripts/skill_environment.py 统一环境、模型、下载缓存与临时目录。已有可用环境和模型继续复用。

准备后默认使用下文产品 Runtime 的 Agent 流程;下面的 standalone CLI 是图片兼容入口。两者都使用自动安装的模型,不要求使用者手动配置 SAM2_MODEL、LAMA_MODEL 或 GROUNDING_DINO_MODEL。推理不会下载模型或回退 Hugging Face cache;准备阶段先校验 runtime receipt,已有显式模型路径须满足固定身份约束。LaMa 缺失或初始化失败时停止该无效路径并修复环境,不降低修复质量。

检查当前设备后再运行:

python -c "import sys, torch; print({'platform': sys.platform, 'cuda': torch.cuda.is_available(), 'rocm': torch.version.hip})"

CPU 仍使用完整模型和相同质量门,速度会明显慢于 GPU。macOS 在真实 Apple Silicon 回归完成前不自动把 MPS 设为默认。

从 skill 根目录运行 module,不要直接执行脚本文件:

cd skills/image-to-psd
python -m scripts.image_to_psd input.png
python -m scripts.image_to_psd input.png -o output.psd
python -m scripts.image_to_psd img1.png img2.png -o psd-output
python -m scripts.image_to_psd images/ -o psd-output --lang en

standalone CLI 只负责图片重建,不接受 --agent-provider。它先完成全部页面的严格准备,再发布 PSD;任一页面失败时不会留下部分输出。

Read the full file on GitHub · 117 lines

Files

What ships with it

34 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.

Changes

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.

  1. 1mo ago Changed · -12 lines · -2 tokens per session 596101fb505c
  2. 1mo ago Changed · -3 lines · -6 tokens per session bd13eeb9a211
  3. 1mo ago First seen · 132 lines · 75 tokens per session scan A 253f400ca7b5

Subscribe to this mod's changes

image-to-psd is a skill published in the GitHub repository DSY-Xueai/image2editable (59 stars, last pushed 18d ago), licensed MIT. It adds 67 tokens to every session and 2,149 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

Other skills, from other repositories

tastemaker

Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…

codeswithroh/tastemaker · 202 tokens

ideagram

Turn a concept, feature description, blog post, or pitch into a single beautiful, on-brand illustration by matching it to a real unDraw illustration in a local library and recoloring it to the brand accent — genuine illustrator quality, not an AI-drawn approximation. Use whenever the user asks to "make an…

codeswithroh/tastemaker · 142 tokens

compose-ui-builder

Open and edit checked-in .uid designs, compare real renders against references, and implement them in application code. Author and edit a Compose UI design over MCP against a compose-preview serve deployment — create a screen or a Wear widget, insert and edit nodes, and export the Kotlin, PNG or SVG. Also use when no…

yschimke/skills · 141 tokens

frontend-patterns

CSS design system principles -- token usage, semantic layering, mobile-first, component isolation.

Jartan-LLC/grimoire · 21 tokens

design-parity-review

Prove a Compose UI pull request matches its intended design by diffing the rendered code (candidate) against a Figma / Stitch / Claude Design reference and posting a parity verdict. Use when asked to check a PR against a design, wire up a design-parity bot, set up the committed reference cache so runs make zero Figma…

yschimke/skills · 133 tokens

compose-preview-review

Review Compose UI previews and pull requests by rendering base and head, diffing them, and checking catalog design guidelines. Use for a UI design review, a UI PR locally or from a CI agent session (@claude mention), authoring an agent-opened PR that touches UI, or triaging flaky or unstable previews…

yschimke/skills · 98 tokens