logo-semantic-fusion
Develop and evaluate logo concepts when the explicit design problem is semantic fusion: two or more brand meanings must share a…
Generate new raster assets that must contain native pixel transparency, then verify the untouched PNG or WebP before delivery. Use for transparent stickers, sprites, character cutouts, product assets, and furry or fine-edged subjects where background removal would be
$ npx -y skills add zseven-w/craft-skills --skill native-transparent-imagegen --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/native-transparent-imagegenContext preview
The summary Claude sees to decide when to auto-load this skill.
Generate new raster assets that must contain native pixel transparency, then verify the untouched PNG or WebP before delivery. Use for transparent stickers, sprites, character cutouts, product assets, and furry or fine-edged subjects where background removal would be
name: native-transparent-imagegen description: "Generate new raster assets that must contain native pixel transparency, then verify the untouched PNG or WebP before delivery. Use for transparent stickers, sprites, character cutouts, product assets, and furry or fine-edged subjects where background removal would be unacceptable. Do not use to remove a background from an existing opaque image, repair an opaque generation by masking or chroma key, or create ordinary opaque images."
Generate the asset with native alpha. Treat a visible checkerboard, a prompt that says "transparent," and a successful tool call as unverified until the original file passes alpha inspection.
transparency.
user explicitly requests an edit.
alpha synthesis to rescue an opaque output.
background-extraction workflow and disclose that it is an edit, not native generation.
1. Preserve the user's subject, identity, style, composition, and text constraints. 2. Add one concise output requirement: return a PNG or WebP whose area outside the subject is genuine pixel transparency with a real alpha channel. 3. With a prompt-only built-in image tool, issue native-alpha deliverables one at a time. Do not parallelize unless the current tool exposes an explicit per-request background control and concurrent native-alpha behavior has been verified. 4. When the user explicitly chooses an API path that exposes output controls, request `background: "transparent"` and `output_format: "png"` or `"webp"`. 5. Preserve the original returned bytes. Validation must not rewrite, optimize, composite, resize, or otherwise alter the deliverable.
Read [references/prompting-and-retry.md](references/prompting-and-retry.md) when preparing a prompt, retrying a failed output, generating more than one asset, or reporting limitations.
Install the validator dependency only when it is missing:
python3 -m pip install -r \
"${CODEX_HOME:-$HOME/.codex}/skills/native-transparent-imagegen/scripts/requirements.txt"Run the read-only validator on every requested deliverable:
python3 \
"${CODEX_HOME:-$HOME/.codex}/skills/native-transparent-imagegen/scripts/validate_alpha.py" \
--require-transparent-corners \
/path/to/original-output.pngThe file passes the technical gate only when:
Then inspect the actual edges against contrasting viewer backgrounds. Alpha metadata cannot prove that fine fur is clean or that the image lacks a broad translucent haze. Reject visible checkerboards, matte halos, colored fog, unintended shadows, clipped strands, or missing details even when the metadata gate passes.
output instruction.
more.
explicit API route only when available and authorized; never silently change models or use background extraction.
For every accepted asset, report:
Keep `generated`, `alpha-validated`, `edge-inspected`, `user-accepted`, and `published` as separate states.
面向 AI Agent 的研究驱动、评测驱动型 Skill 集合。 Craft Skills 把可迁移的专业方法提炼成聚焦的工作流,并为每个 Skill 明确触发边界、退出条件、原创案例与前向测试。它不是视频摘要库、提示词合集, 也不是模仿创作者风格的素材仓库。 由 Fini Yang 创建并策划, ZSeven 维护。
Develop and evaluate logo concepts when the explicit design problem is semantic fusion: two or more brand meanings must share a…
为 Qwen-Image 编写和改写生图提示词,区分局部编辑与参考主体创作,处理同人物系列、画幅及原图验收;用户要求生成时连接其已有的 Qwen 图像工作流。不用于下载权重、通用模型运维或其他图像模型。
Create, audit, and repair short page-native diary comics around an existing authorized recurring character, with story-directed…
将 3–5 步线性流程制作成单张完整、非宫格的微缩剧场成品。适用于流程故事封面、制作过程图、软件交付旅程与科普式微缩场景;以单一路径、可追踪载体、可辨识动作和题材匹配的材质表达顺序。不用于需要精确分支和数据尺度的流程图、实际操作规程或普通城市微缩景观。