Agent skill

Bggg Creator Image2psd

by ninehills in ninehills/skills

把一张或多张图片整理成 PSD 图层文件的创作与转换 skill。当用户需要 image2psd、图片转 PSD、 多张图片拼成 PSD、海报/设计稿拆成多个图层、白底转透明、颜色聚类拆层、把 Codex/AI 生图结果拆成元素图再合成 PSD、 或希望输出 layered PSD、可在 Photoshop/Photopea 中编辑的分层栅格文件时,应该使用此 skill。

MITAuto-check passedMedia & Creative

Install Bggg Creator Image2psd

skills CLI
$ npx skills add ninehills/skills --skill bggg-creator-image2psd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ninehills/skills bggg-creator-image2psd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ninehills/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/bggg-creator-image2psd .claude/skills/bggg-creator-image2psd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
bggg-creator-image2psd
GitHub stars
280
Used in
1 other repo
Token cost
~1.3k tokens
SKILL.md length
247 words
Files
13 (incl. scripts, references, assets)
Skills in repo
38
Repo updated
First seen
Licence
MIT

At a glance

把一张或多张图片整理成 PSD 图层文件的创作与转换 skill。当用户需要 image2psd、图片转 PSD、 多张图片拼成 PSD、海报/设计稿拆成多个图层、白底转透明、颜色聚类拆层、把 Codex/AI 生图结果拆成元素图再合成 PSD、 或希望输出 layered PSD、可在 Photoshop/Photopea 中编辑的分层栅格文件时,应该使用此 skill。

  • Works in 7 steps: 判断任务类型 → 创建… → 确定画布尺寸。优先沿用源图尺寸;海报类任务需要明确宽高。 → …
  • Tasks that involve Image generation
  • SKILL.md covers Codex 适配默认策略, 项目目录约定, 工作流 and 常用命令, plus 5 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Bggg Creator Image2psd is an agent skill from ninehills/skills. 把一张或多张图片整理成 PSD 图层文件的创作与转换 skill。当用户需要 image2psd、图片转 PSD、 多张图片拼成 PSD、海报/设计稿拆成多个图层、白底转透明、颜色聚类拆层、把 Codex/AI 生图结果拆成元素图再合成 PSD、 或希望输出 layered PSD、可在 Photoshop/Photopea 中编辑的分层栅格文件时,应该使用此 skill。 在 Codex 中使用时,默认结合 imagegen skill:先用 Codex 视觉/生图能力理解、补齐或重建元素,再用本 skill 的脚本落地 PSD。

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including scripts, reference files and assets (for example `README.md`, `README_EN.md` and `assets/sample-manifest.json`).

It sits in Media & Creative, covering Image generation. The licence is MIT.

When your agent uses it

  • Tasks that involve Image generation

Example prompts

  • “/bggg-creator-image2psd”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. 判断任务类型
  2. 创建 projects/YYYYMMDD_slug/,把源图和所有输出放进去。默认用脚本初始化
  3. 确定画布尺寸。优先沿用源图尺寸;海报类任务需要明确宽高。
  4. 处理透明
  5. 运行脚本输出 PSD、预览 PNG、可选的单层 PNG 目录/zip。
  6. 验证输出:检查脚本 JSON 摘要里的 layer_count、预览 PNG、PSD 文件大小;用 Pillow 或 Photoshop/Photopea 检查 PSD 可读性。
  7. 写 process_notes.md,记录图层、路径、验证和限制。

What it can do on your machine

Read from SKILL.md and the folder at commit f3e82a7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Bggg Creator Image2psd loads about 1.3k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 73 tokens; SKILL.md has 247 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from ninehills/skills at commit f3e82a7, republished under its MIT licence (© ninehills). 247 words, ~1,273 tokens.

Download SKILL.mdSave it as .claude/skills/bggg-creator-image2psd/SKILL.md (or your agent's skills folder). This skill also uses 12 other files; get the full folder from GitHub.
name
bggg-creator-image2psd
description
把一张或多张图片整理成 PSD 图层文件的创作与转换 skill。当用户需要 image2psd、图片转 PSD、 多张图片拼成 PSD、海报/设计稿拆成多个图层、白底转透明、颜色聚类拆层、把 Codex/AI 生图结果拆成元素图再合成 PSD、 或希望输出 layered PSD、可在 Photoshop/Photopea 中编辑的分层栅格文件时,应该使用此 skill。 在 Codex 中使用时,默认结合 imagegen skill:先用 Codex 视觉/生图能力理解、补齐或重建元素,再用本 skill 的脚本落地 PSD。

BGGG Creator Image2PSD

用这个 skill 把图片资产组织成可编辑的 PSD 栅格图层。核心脚本是 scripts/image2psd.py,它不依赖 Photoshop 或 ImageMagick,能独立写出带图层名、透明通道和合成预览的 PSD。

Codex 适配默认策略

在 Codex 里处理图片转 PSD 时,默认配合 imagegen skill 的能力:

  • 先用 Codex 的视觉理解能力判断图层结构、主体/背景/文字/装饰的边界、以及哪些区域需要重建背景。
  • 如果用户要求从描述生成、补齐缺失元素、移除对象后补背景、或拆出更干净的独立商品/主体图,优先使用 imagegen skill 的内置生图/编辑能力生成项目内资产,再交给本 skill 组装 PSD。
  • 如果用户明确要求“不改变相对位置”“直接在 Photoshop 拼接”,优先保留原图像素:每个图层输出为同尺寸全画布透明 PNG,只改变 alpha,不重绘内容。只有背景擦除/补洞可使用 inpaint 或 imagegen 辅助。
  • 不要把 imagegen 的默认输出留在 $CODEX_HOME。项目要用的图片必须复制到本 skill 的项目目录。

项目目录约定

每次处理图片都创建独立项目目录,放在本 skill 文件夹下:

text
bggg-creator-image2psd/
└── projects/
    └── YYYYMMDD_slug/
        ├── original_reference.png
        ├── manifest.json
        ├── layer_sources/
        ├── psd_full_canvas_layers/
        ├── output.psd
        ├── output.preview.png
        ├── psd_full_canvas_layers.zip
        └── process_notes.md

命名规则:

  • YYYYMMDD_slug 使用当前日期和简短英文/拼音任务名,例如 20260503_lifestyle_product.
  • original_reference.png 是本次处理的源图副本。
  • layer_sources/ 保存用于组装的透明图层源。
  • psd_full_canvas_layers/ 保存 Photoshop 可直接按原位叠放的全画布 PNG 图层。
  • process_notes.md 记录图层划分、是否使用 imagegen、验证结果和已知限制。

工作流

  1. 判断任务类型:

    • 多张元素图已经存在:复制到项目目录,用 assemble,按图层顺序写 manifest。
    • 只有一张平面图且要保留相对位置:做语义/区域拆层,每层保持原图同尺寸;背景层用 inpaint 或 imagegen 辅助清理被拆出的区域。
    • 只有一张平面图且只要粗拆:用 split-colors 按颜色聚类拆层,并说明它不是语义对象拆层。
    • 用户要从描述生成 PSD:先用 Codex imagegen 分别生成背景、主体、文字/装饰等项目资产,再用 assemble 合成 PSD。
  2. 创建 projects/YYYYMMDD_slug/,把源图和所有输出放进去。默认用脚本初始化:

    bash
    python3 bggg-creator-image2psd/scripts/init_project.py lifestyle_product \
      --source 用户附件.png \
      --date 20260503

    如果使用了 imagegen,先把 $CODEX_HOME 下的生成结果复制到该项目的 imagegen_assets/,再进入拆层或合成流程。

  3. 确定画布尺寸。优先沿用源图尺寸;海报类任务需要明确宽高。

  4. 处理透明:

    • 背景层用 remove_background: none。
    • Logo、文字、装饰图常用 remove_background: white。
    • 白帆、白色产品、浅色主体这类容易被白底吞掉的元素用 remove_background: white-preserve。
    • 非白色纯底用 corner 或 color。
  5. 运行脚本输出 PSD、预览 PNG、可选的单层 PNG 目录/zip。

  6. 验证输出:检查脚本 JSON 摘要里的 layer_count、预览 PNG、PSD 文件大小;用 Pillow 或 Photoshop/Photopea 检查 PSD 可读性。

  7. 写 process_notes.md,记录图层、路径、验证和限制。

常用命令

从 manifest 合成:

bash
python3 bggg-creator-image2psd/scripts/image2psd.py assemble \
  --manifest work/manifest.json \
  --output work/output.psd \
  --preview work/output.preview.png \
  --save-layers work/layers \
  --zip-layers work/layers.zip

直接把多张图合成,第一张为背景:

bash
python3 bggg-creator-image2psd/scripts/image2psd.py assemble bg.png title.png logo.png \
  --first-is-background \
  --names "Background,Title,Logo" \
  --output output.psd \
  --save-layers layers

把单张平面图按颜色拆成 PSD 图层:

bash
python3 bggg-creator-image2psd/scripts/image2psd.py split-colors poster.png \
  --output poster-color-layers.psd \
  --num-colors 10 \
  --ignore-color white \
  --save-layers poster-color-layers

Manifest 格式

用 manifest 管理复杂 PSD。图层数组按从底到顶排列。

json
{
  "canvas": {
    "width": 1122,
    "height": 1402,
    "composite_background": "#ffffff"
  },
  "output": "poster.psd",
  "preview": "poster.preview.png",
  "save_layers_dir": "layers",
  "layers": [
    {
      "name": "Background",
      "file": "assets/background.png",
      "fit": "cover",
      "remove_background": "none"
    },
    {
      "name": "Ship and Waves",
      "file": "assets/ship.png",
      "remove_background": "white-preserve"
    },
    {
      "name": "Title",
      "type": "text",
      "text": "AI Commerce Summit",
      "x": 80,
      "y": 120,
      "font_size": 72,
      "color": "#41270d",
      "max_width": 900
    }
  ]
}

图层字段要点:

  • file/path/src: 图片路径,manifest 相对路径从 manifest 所在目录解析。
  • type: "text": 用 PIL 渲染成独立栅格文字层,不是 Photoshop 可编辑文字对象。
  • x, y: 图片或文字层左上角偏移。
  • fit: none、contain、cover、stretch。
  • remove_background: none、white、white-preserve、corner、color。
  • opacity: 0 到 1。

生图到 PSD

在 Codex 中,默认把 imagegen 当成补强工具,而不是唯一处理方式。把设计拆成独立元素来生成或编辑,而不是只生成一张完整海报:

  • 背景:完整画布,通常不去底。
  • 主体/产品/人物/船/道具:白底或透明背景,合成时用 white 或 white-preserve 去底。
  • Logo、标题、日程、装饰:尽量单独生成或用 manifest 的 text 层重建。
  • 每个元素的提示词要包含画布尺寸、视角、边缘干净、不要阴影污染背景等约束。

如果生图只得到一张完整图,先用 split-colors 做可编辑性最低限度拆层,再按用户需求补生关键元素。

单图语义拆层经验

复盘成功案例后,单张图转 PSD 优先采用这个顺序:

  1. 复制源图到项目目录,保持原始尺寸。
  2. 先列出图层清单,按“背景/主体/装饰/文字/阴影或光效”分组。
  3. 每个可移动对象输出全画布透明 PNG,位置不裁切,便于 Photoshop 直接叠放。
  4. 背景层用被拆出图层的 union mask 做 inpaint,必要时二次扩大遮罩清理残影。
  5. 预览图与原图做像素差异或肉眼对比;发现文字/主体边缘被裁时,优先扩大 mask 框而不是移动图层。
  6. 如果源图没有本地文件,先要求用户提供源文件路径;不要用 imagegen 重绘图冒充原始拆层。

何时读参考

  • 修改核心脚本前,读 references/implementation-notes.md。
  • 需要追溯外部项目启发时,读 references/source-projects.md。
  • 不要把 reference/ 下克隆的外部仓库作为运行依赖;它们只是开发参考。

输出要求

交付时至少说明:

  • PSD 路径。
  • 预览 PNG 路径。
  • 图层数量和主要图层名。
  • 是否生成了单层 PNG/zip。
  • 项目目录路径。
  • 如果没有验证 Photoshop 打开效果,要明确说验证限于脚本和预览。

© ninehills, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 12 other files (scripts, references, assets) in bggg-creator-image2psd of ninehills/skills.

  • SKILL.md
  • .gitignore
  • LICENSE
  • README.md
  • README_EN.md
  • assets/sample-manifest.json
  • evals/evals.json
  • projects/.gitkeep
  • references/implementation-notes.md
  • references/source-projects.md
  • scripts/image2psd.py
  • scripts/init_project.py
  • scripts/requirements.txt

Open the folder on GitHubat commit f3e82a7

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in ninehills/skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Bggg Creator Image2psd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Bggg Creator Image2psd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bggg Creator Image2psd this skillninehills/skills2801 repos~1.3kAutomated safety check: PassMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
Structured Image Generationbytedance/deer-flow84k4 repos~2.9kAutomated safety check: PassMIT
Canghe Comicfreestylefly/canghe-skills4618 repos~3.2kAutomated safety check: PassNone
Generate Imageynulihao/AgentSkillOS61810 repos~1.7kAutomated safety check: NotesNone
GPT Image Generation CLIwuyoscar/GPT-Image2-Skill5.7k—~2.5kAutomated safety check: NotesMIT

Similar skills

  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Structured Image Generation

    bytedance/deer-flow

    Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.

    84k GitHub starsUsed in 4 repos~2.9k tokens
    Media & CreativeAuto-check passed
  • Canghe Comic

    freestylefly/canghe-skills

    Knowledge comic creator supporting multiple art styles and tones.

    461 GitHub starsUsed in 8 repos~3.2k tokens
    Media & CreativeAuto-check passed
  • Generate Image

    ynulihao/AgentSkillOS

    Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.

    618 GitHub starsUsed in 10 repos~1.7k tokens
    Media & CreativeAuto-check: notes
  • GPT Image Generation CLI

    wuyoscar/GPT-Image2-Skill

    Generates and edits images with GPT Image 2 or 2.5 through a packaged CLI and a prompt gallery, after settling which model fits the request.

    5.7k GitHub stars~2.5k tokensUpdated 11 days ago
    Media & CreativeAuto-check: notes
  • Minimal Zine Poster Generator

    LiamGvchi/gc-minimal-zine-poster

    Creates or analyzes quiet, paper-texture zine posters with big negative space, one color accent and experimental type, returning an image prompt and the generated poster.

    7.3k GitHub stars~2.9k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed

More from ninehills/skills

All 38 skills in this repo
  • Alphaear Predictor

    ninehills/skills

    Market prediction skill using Kronos. An agent skill from ninehills/skills.

    280 GitHub starsUsed in 1 repo~531 tokens
    Auto-check passed
  • Alphaear Signal Tracker

    ninehills/skills

    Track finance investment signal evolution and update logic based on new finance market information.

    280 GitHub starsUsed in 1 repo~459 tokens
    Auto-check passed
  • Fireworks Tech Graph

    ninehills/skills

    A skill your agent uses when the user wants to create any technical diagram - architecture, data flow, flowchart, sequence, agent/memory, or concept map - and export as SVG+PNG.

    280 GitHub starsUsed in 2 repos~8k tokens
    Auto-check passed
  • Alphaear Sentiment

    ninehills/skills

    Analyze finance text sentiment using FinBERT or LLM. An agent skill from ninehills/skills.

    280 GitHub starsUsed in 1 repo~499 tokens
    Auto-check passed
  • Bggg Creator Image2ppt

    ninehills/skills

    把图片、截图、海报、PPT 页面截图、HTML 或 SVG 设计稿转换成可编辑 PPTX 的 Codex skill. An agent skill from ninehills/skills.

    280 GitHub starsUsed in 1 repo~1.2k tokens
    Auto-check passed
  • Read

    ninehills/skills

    Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work.

    280 GitHub stars~2.1k tokensUpdated 3 mo ago
    Auto-check: warnings

Questions about Bggg Creator Image2psd

What does Bggg Creator Image2psd do?

把一张或多张图片整理成 PSD 图层文件的创作与转换 skill。当用户需要 image2psd、图片转 PSD、 多张图片拼成 PSD、海报/设计稿拆成多个图层、白底转透明、颜色聚类拆层、把 Codex/AI 生图结果拆成元素图再合成 PSD、 或希望输出 layered PSD、可在 Photoshop/Photopea 中编辑的分层栅格文件时,应该使用此 skill。. Bggg Creator Image2psd is an agent skill from ninehills/skills.

When should I use Bggg Creator Image2psd?

Bggg Creator Image2psd fits situations like: tasks that involve Image generation.

How do I install Bggg Creator Image2psd in Claude Code?

Run `npx skills add ninehills/skills --skill bggg-creator-image2psd -a claude-code`. Or copy the skill folder (bggg-creator-image2psd in ninehills/skills) into .claude/skills/bggg-creator-image2psd in your project. Claude Code loads it when a task matches its description.

How do I install Bggg Creator Image2psd in Codex?

Run `npx skills add ninehills/skills --skill bggg-creator-image2psd -a codex`. Or copy the skill folder (bggg-creator-image2psd in ninehills/skills) into .agents/skills/bggg-creator-image2psd in your project. Codex loads it when a task matches its description.

Can I use Bggg Creator Image2psd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ninehills/skills --skill bggg-creator-image2psd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bggg-creator-image2psd, .gemini/skills/bggg-creator-image2psd, .github/skills/bggg-creator-image2psd and .opencode/skills/bggg-creator-image2psd in your project.

What does Bggg Creator Image2psd need to run?

Going by SKILL.md and its folder, Bggg Creator Image2psd needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Bggg Creator Image2psd access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bggg Creator Image2psd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Bggg Creator Image2psd use?

Bggg Creator Image2psd is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Bggg Creator Image2psd use?

About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.

What are the alternatives to Bggg Creator Image2psd?

Skills that share tags, products or a category with Bggg Creator Image2psd: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Structured Image Generation (bytedance/deer-flow, 84k stars), Canghe Comic (freestylefly/canghe-skills, 461 stars) and Generate Image (ynulihao/AgentSkillOS, 618 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bggg Creator Image2psd?

ninehills (a GitHub user) maintains it in ninehills/skills, which has 280 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on June 22, 2026.

Source: ninehills/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.