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-psdgit 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-psd)<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.
<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>- 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 | $0.00067 | $0.02149 |
| Opus 5.5 | $0.00027 | $0.00860 |
| Sonnet 5.5 | $0.00013 | $0.00430 |
| Haiku 4.5 | $0.00007 | $0.00215 |
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.
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 — 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。
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.
- references/requirements.txt 375 B
- references/setup.md 8.5 KB
- scripts/__init__.py 44 B runs code
- scripts/art_text.py 11 KB runs code
- scripts/bg_model.py 42 KB runs code
- scripts/component_contracts.py 42 KB runs code
- scripts/component_quality.py 53 KB runs code
- scripts/component_underlay.py 25 KB runs code
- scripts/fetch_skill_source.py 3.6 KB runs code
- scripts/fg_extract.py 47 KB runs code
- scripts/font_match.py 10 KB runs code
- scripts/image_to_ppt.py 225 KB runs code
- scripts/image_to_psd.py 7.0 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 19 KB runs code
- scripts/page_routing.py 6.8 KB runs code
- scripts/performance_trace.py 5.6 KB runs code
- scripts/psd_assemble.py 4.3 KB runs code
- scripts/runtime_model_paths.py 5.4 KB runs code
- scripts/sam_worker.py 76 KB runs code
- scripts/skill_environment.py 5.3 KB runs code
- scripts/text_context.py 11 KB runs code
- scripts/text_detect.py 53 KB runs code
- scripts/text_runs.py 3.9 KB runs code
- scripts/verify_skill_runtime.py 2.9 KB runs code
- scripts/visual_compare_qa.py 3.6 KB runs code
- scripts/visual_segment.py 88 KB runs code
- scripts/visual_worker.py 14 KB runs code
- scripts/worker_pool.py 17 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.
- 1mo ago Changed · -12 lines · -2 tokens per session 596101fb505c
- 1mo ago Changed · -3 lines · -6 tokens per session bd13eeb9a211
- 1mo ago First seen · 132 lines · 75 tokens per session scan A 253f400ca7b5
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.
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…
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…
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…
frontend-patterns
CSS design system principles -- token usage, semantic layering, mobile-first, component isolation.
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…
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…