Skip to content
AI & Agents
Skill

/layout-library-importer

Add a supplied layout image and bilingual layout prompt to the local handdraw-style layout library and gallery. Use for new SC-* social-card or IG-* infographic layouts; do not use for style-number imports.

From plugin
skill
9.5k127 skills

Claude Code

$ npx -y skills add anbeime/skill --skill layout-library-importer --agent claude-code

SKILL.md

layout-library-importer.SKILL.md
name: layout-library-importer
description: Add a supplied layout image and bilingual layout prompt to the local handdraw-style layout library and gallery. Use for new SC-* social-card or IG-* infographic layouts; do not use for style-number imports.

Layout Library Importer

Use this Skill when the user wants to add a new visual layout/type to the local hand-drawn layout gallery. This is a repository-local workflow: do not commit, push, publish, or install anything externally unless the user separately asks.

Source of truth

Work from the repository root and read the live implementation before editing:

  • `skills/handdraw-style-prompter/references/layouts.json` is the layout index.
  • `skills/handdraw-style-prompter/references/layouts/*.md` is the authoritative bilingual prompt content.
  • `images/layouts/social-cards/`, `images/layouts/infographics/`, `images/layouts/comic-storyboards/`, and `images/layouts/ip-characters/` hold the layout images; canonical assets use WebP.
  • `skills/handdraw-style-prompter/scripts/build_layout_gallery.py` rebuilds the derived gallery.
  • `skills/handdraw-style-prompter/scripts/validate_library.py` is the full validation command.

Preserve unrelated dirty work. Inspect `git status --short` before editing and do not reset, clean, or overwrite files outside the requested layout import.

Import workflow

Batch input mode

Unless the user explicitly asks to rebuild, treat consecutive layout imports as batch input. For each supplied image, convert it to WebP when needed, add its index entry, and create its bilingual prompt file, but do not rebuild `gallery/layouts.html` or run the full validator after each item.

When the user says `重建索引`, rebuild the layout gallery once from the accumulated canonical index and run the full validation and whitespace check. The canonical index is `references/layouts.json`; this request means regenerate and validate its derived gallery, not recreate the index entries already recorded.

1. Determine the next ID from the live index. Use the next number within the requested category: `SC-###` for `social-card`, `IG-###` for `infographic`, `SB-###` for `comic-storyboard`, `IP-###` for `ip-character`. Never reuse an existing ID or infer a number from a filename alone. 2. Treat the user-supplied image as the canonical visual source. The repository asset must always use the `.webp` extension. If the supplied image is already WebP, copy it to the category directory with the new ID. If it is another format, convert it to WebP losslessly using Python:

   python -c "from PIL import Image; img = Image.open(r'<input>'); img.save(r'<target>.webp', format='WEBP', lossless=True)"

Do not delete the source attachment. Do not generate, crop, recolor, or otherwise alter the image content. If the attachment is unavailable as a readable local file, stop before changing the index and ask the user to reattach it. 3. Add one index object to `references/layouts.json` with the ID, exact category, concise Chinese display name, repository-relative WebP image path (`../../../images/layouts/...webp`), prompt path (`layouts/{ID}.md`), and concrete internal keywords. Keep the JSON array ordered by category and numeric ID. 4. Create `references/layouts/{ID}.md` with exactly two non-empty marker blocks:

   <!-- zh -->
   Chinese layout prompt

   <!-- en -->
   English layout prompt

The prompt must describe composition, text hierarchy, placement, whitespace, and other layout constraints supplied by the user. Do not invent subject matter or illustration style. The Chinese and English blocks must express the same constraints. The layout prompt is the single source of truth used by prompt combination. 5. When the user requests a rebuild, rebuild the derived gallery and sync documentation counts:

   python skills/handdraw-style-prompter/scripts/build_layout_gallery.py

The build script automatically regenerates `gallery/layouts.html`, updates `LAYOUTS.md` / `LAYOUTS_en.md`, and synchronizes layout totals and category counts across `README.md`, `README_en.md`, and all `SKILL.md` files. Do not manually edit the generated `gallery/layouts.html`. The gallery must remain browse-only: thumbnail, ID/name information, enlarged preview, and copy-prompt behavior; no input form.

6. Synchronize client caches & mirrors: Always ensure local desktop caches and mirror environments reflect the new layout entry:

  • Copy `references/layouts.json` to `client/cache/layouts.json`.
  • If `.agents/` mirror exists, ensure its `references/` and `gallery/layouts.html` are synchronized.
  • When deploying to static site, verify that `https://handraw-style.com/gallery/layouts.html` returns HTTP 200 and includes the newly added layout ID.

Validation

Run this section after an explicit rebuild request. During batch input mode, only confirm that the current image, index entry, and prompt file exist and agree. For every newly added layout, also confirm that the indexed image path ends in `.webp` and that the WebP file exists. Existing legacy PNG assets are outside this migration step.

Run the full validator and whitespace check:

python skills/handdraw-style-prompter/scripts/validate_library.py
git diff --check

Also verify directly that the new image, index entry, prompt file, generated card, and category count agree. For a social-card import with no infographic entries, the generated page must not show an infographic filter. When an `IG-*` entry is added later, the existing generator should expose that category automatically.

If browser automation is available, reload the existing local `layouts.html` preview and check the new card, full-image display, category filter, enlarged preview, and copy action. If the local `file://` page is blocked by browser policy, report that visual QA was not completed; do not present string or file checks as a substitute for visual conf

Read more
@anbeime
Ships withskill

收录最全、更新最快的AI Agent技能库,涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流等多个领域的精选技能包。 🎁 知易多模型知识管家 · 免费试用预约 — 20+ 模型自由切换、技能市场、四色卡片知识库,留邮箱锁定免费试用名额,每周再收一份知易AI周刊。

9.5k127 skills
Get the whole plugin

Stars on GitHub

Momentum

stars in total
9.5k
Star history of anbeime/skill on GitHub, a chart by star-history.com

Other skills on skill.

doc-parse

doc-parse

将 PDF/PPT/Excel/Word 等多格式文档解析为结构化 Markdown,并输出元数据与解析置信度,作为 RAG 与四色卡片的数据底座。

@anbeime@anbeimeInstall Skill
four-color-cards

four-color-cards

基于解析后的文档与用户意图,生成四色卡片——事实蓝卡、解释绿卡、风险黄卡、行动红卡,是八官署方法论的核心分析输出。

@anbeime@anbeimeInstall Skill
provenance

provenance

收集系统全链路操作日志,生成可追溯的执行证据链与向量索引,是多智能体系统可观测性与安全审计的底座。

@anbeime@anbeimeInstall Skill
security-scan

security-scan

对进入系统的文件或 URL 执行安全与合规扫描,输出 pass/reject 判定与扫描报告,作为所有文档处理的强制前置关卡。

@anbeime@anbeimeInstall Skill
RuiC-card-skill

RuiC-card-skill

Generate interactive 3D holographic collectible-card websites from a user description or reference image, using layered artwork,…

@anbeime@anbeimeInstall Skill
agent-team

agent-team

产品经理与项目管理专家在应对复杂项目时,使用此技能可动态组建包含“执行、指挥、评审”的专属AI团队。实时查看多智能体辩论与决策全过程,共享统一上下文记忆,一键完成从会议决策到系统构建的全流程高效协同!

@anbeime@anbeimeInstall Skill

More skills from other plugins.

1password

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

openclaw2w393k
@openclaw@openclawInstall Skill

Questions about layout-library-importer.

Which coding agents can use layout-library-importer?
layout-library-importer installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.