Visual Design
aws-samples/sample-strands-agent-with-agentcore
Use this skill any time the user needs a visual output as an image or PDF — charts, diagrams, posters, infographics, abstract artwork, or any visual design.
Generates clean static SVG diagrams for book chapters and formal articles, such as architecture, flow and hierarchy figures, embedded in Markdown and checked against review gates.
SKILL.md written in Chinese; this summary is our English description.
$ npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cat-xierluo/legal-skills svg-book-illustrator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/svg-book-illustrator .claude/skills/svg-book-illustrator && rm -rf skills-srcUse ~/.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/
Install the "svg-book-illustrator" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/svg-book-illustrator into .claude/skills/svg-book-illustrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "svg-book-illustrator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cat-xierluo/legal-skills/tree/main/skills/svg-book-illustratorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cat-xierluo/legal-skills svg-book-illustrator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/svg-book-illustrator .agents/skills/svg-book-illustrator && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "svg-book-illustrator" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/svg-book-illustrator into .agents/skills/svg-book-illustrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "svg-book-illustrator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cat-xierluo/legal-skills svg-book-illustrator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/svg-book-illustrator .cursor/skills/svg-book-illustrator && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "svg-book-illustrator" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/svg-book-illustrator into .cursor/skills/svg-book-illustrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "svg-book-illustrator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cat-xierluo/legal-skills.git --path skills/svg-book-illustrator--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cat-xierluo/legal-skills svg-book-illustrator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/svg-book-illustrator .gemini/skills/svg-book-illustrator && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "svg-book-illustrator" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/svg-book-illustrator into .gemini/skills/svg-book-illustrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "svg-book-illustrator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cat-xierluo/legal-skills svg-book-illustratorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/svg-book-illustrator .github/skills/svg-book-illustrator && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "svg-book-illustrator" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/svg-book-illustrator into .github/skills/svg-book-illustrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "svg-book-illustrator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cat-xierluo/legal-skills svg-book-illustrator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/svg-book-illustrator .opencode/skills/svg-book-illustrator && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "svg-book-illustrator" agent skill from https://github.com/cat-xierluo/legal-skills/tree/main/skills/svg-book-illustrator into .opencode/skills/svg-book-illustrator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "svg-book-illustrator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
svg-book-illustratorGenerates clean static SVG diagrams for book chapters and formal articles, such as architecture, flow and hierarchy figures, embedded in Markdown and checked against review gates.
The skill reads a chapter in Markdown, finds places where a diagram would help (architecture, process, comparison, hierarchy, cycle, ecosystem, multi-dimension scoring, timeline or cross-tab descriptions) and inserts numbered figure placeholders. It then picks a layout template, such as flow, layer, matrix, hub, tree, cycle, radar, skill-card, timeline-lane, matrix-grid or three-col, and writes SVG following a style guide, with a unique figure ID on each root element and a caption below. The SVGs are static with transparent backgrounds, suited to print publishing.
Finished figures are extracted into separate files with scripts/extract_svgs.py, and generator scripts exist for radar, matrix-grid, skill-card, three-col and timeline-lane figures. A review stage applies gates, including a figure density check (at least 0.7 figures per section and 0.8 per ten thousand characters), a check that each figure matches the argument of its section, and a calculated text-width and coordinate check that runs before visual inspection. A render script and a consistency scanner are bundled too.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit f844ebe. It shows what the files ask for, not the result of running them.
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.
Ships 9 files in scripts/ (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
python3nodepythonnpmFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
SVG Book Illustrator loads about 3k tokens when it runs, and up to ~26k if it reads all its reference files. Until then it costs about 32 tokens; SKILL.md has 834 words of instructions outside code blocks.
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.
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.
The full file from cat-xierluo/legal-skills at commit f844ebe, republished under its MIT licence (© cat-xierluo). 834 words, ~3,009 tokens.
.claude/skills/svg-book-illustrator/SKILL.md (or your agent's skills folder). This skill also uses 22 other files; get the full folder from GitHub.为书籍章节和正式文章生成简洁专业的 SVG 技术配图。
本 Skill 生成静态 SVG,直接嵌入 Markdown 文件(
<svg>标签),风格为简洁专业、透明背景 + 按模板语义分类配色(v1.7.0:层级类 layer/tree/金字塔走 G1-G4 灰度梯度;多样性类 flow/matrix/hub/cycle 走 P1-P8 多色调色板),适合纸质出版。
/svg-book-illustrator @path/to/chapter.mdreferences/diagram-catalog.md 有当前章节的预定义插图,匹配之[[FIG:N:简要描述]](N 从 1 开始编号)插图密度:每章「一节一张」为基准,数万字章节 6-8 张,宁精勿滥;纯 walkthrough / 总结节可省图避免冗余。密度指标:图/节 ≥ 0.7、图/万字 ≥ 0.8,低于判「偏少」并提示补图位置(详见第四阶段 + references/review-checklist.md)。
完成插图规划后,逐张生成:
references/layout-templates.md 获取模板规范references/style-guide.md 的设计规范生成 SVG 代码<svg> 根写入当前项目唯一的 data-figure-id="fig-chNN-sN-NN";模板中的 fig-template-* 仅为示例,落稿前必须替换<svg> 标签嵌入 Markdown,替换对应占位符**图 N-X:图标题**生成完成后,提取所有 SVG 到独立文件:
python scripts/extract_svgs.py path/to/chapter.md --output output/figures/生成 + 嵌入后,逐章过审查门禁,详见 references/review-checklist.md:
① 配图密度审查:图/节 ≥ 0.7、图/万字 ≥ 0.8;低于判「偏少」,列出可补图的小节。跨章均衡——相邻章密度不宜骤变(认知/入门篇图密度不应远低于方法/实战篇)。
② 图-正文论点一致性审查:每张图回溯所在小节,核对节点数 / 层级名 / 流程方向 / 对比维度 与正文表述一致;替换 mermaid / ASCII 图时原信息(节点、关系、标注)不丢失;图注准确概括图内容,不夸大不遗漏。
③ 字宽/坐标硬算自检(v1.8.5+,先于视觉目检):生成器产出后,按 CJK≈Fpx/字、Latin≈0.55Fpx/字 估算文字宽度 ≤ 容器宽,相邻元素 y 差 ≥ 20px,viewBox H 足够——计算闸,防视觉目检对"轻微溢出/贴近"漏检(v1.8.5 radar 图例重叠、three-col 子卡片溢出两例均靠此抓出)。详见 references/review-checklist.md §③。
④ 视觉目检(多模态渲染后眼检):SVG 用受控字体渲染为 PNG(快速预览运行 python3 scripts/render_svg.py input.svg output.png;高 DPI 运行 node scripts/svg2png.js input.svg output.png 300)后,用多模态模型逐张查——文字不溢出容器、框不重叠(间距 ≥24px)、箭头落位方向正确、语义线未被误删、分叉连续、标签卡与编号清楚、字号可读(节点≥16px 副≥12px)、黑白可辨、整体美观留白合理。发现问题回改 SVG 坐标,复检直到目检通过。
多模态生产提示:若环境支持图像理解,④ 必须真正"看"渲染图,不能只靠 xmllint / rsvg 无警告间接验证——语法通过 ≠ 布局美观,溢出/重叠/箭头错位只有肉眼(或多模态模型)能发现。但视觉目检对"轻微溢出/贴近"易判 OK,故须先过 ③ 字宽硬算自检。
形状包含窄语义(v1.8.10+):默认把 shape/shape 包含或重叠当作待修布局问题,先改坐标,不得用 data-overlap-role="decoration"、data-allow-overlap 或任意自造 role 掩盖。只有外层 area shape 确实承担“面板承载内层信息卡”等容器语义时,才在外层写单图唯一的安全原生 id、data-overlap-role="container"、明示承载关系的 data-overlap-note 与可静态证明非透明的 hex/rgb/hsl fill;namespaced 假属性、透明/继承/paint server/零 opacity 容器和孤立 note 都无效。该声明只是让意图可审计,不证明几何正确;最终必须由 writing-reviewer v0.16+ render gate 以真实浏览器几何复核,并在 evidence 中记录实际命中的 outer / inner / reason。详见 references/style-guide.md §六与 references/review-checklist.md §⓪/④。
生产器契约回归(v1.8.9+):修改 scripts/gen-*.py 或 references/layout-templates.md 后,必须运行:
python3 -m unittest discover -s scripts/tests -p 'test_*.py' -v只有退出码为 0 才能进入合并候选。该测试实际执行全部生成器,并检查模板文档中的全部 SVG 代码块;viewBox 必须严格为 0 0 720 H,根 width 必须为 720、height 必须等于 H;data-figure-id 必须存在、格式安全且在同一批产物中不重复;XML、<style>、元素 style=、任一元素的 font-family、class/CSS 变量和背景矩形任一不合规都会失败。任何 data-overlap-role 也必须严格满足上面的 container + 单图唯一原生 id + 明示承载关系的 note + 外层 area shape + 非透明 hex/rgb/hsl fill 窄契约;namespaced 属性、孤立 note、继承/透明/paint server fill、decoration 与自造 role 直接失败。
生产身份契约(v1.8.9+):下游 review / render inventory 以 SVG 根的 data-figure-id 绑定跨轮 finding 与渲染证据,不能再依赖“第几张图”或文件遍历顺序。5 个生成器默认从输出文件 stem 取稳定 ID,也支持显式指定:
python3 scripts/gen-radar.py figures/fig-ch03-s2-01.svg --figure-id fig-ch03-s2-01安全值只允许 1–128 位字母、数字、点、下划线或连字符。写入书稿前必须使用项目内唯一的 fig-chNN-sN-NN;默认 stem 只是便捷值,不能替代项目级唯一性检查。fig-template-* 只用于模板自身,禁止原样进入书稿。本契约只约束 v1.8.9+ 新生成或新落稿的 SVG,不要求回改历史书稿;历史资产是否迁移由项目单独决策。
仓库内 .github/workflows/svg-book-producer-contract.yml 会在本 Skill 或工作流自身发生 PR 改动,以及相关改动推入 main 时自动运行同一命令。没有明确通过的 Source producer contract check,不应把生产器改动视为可合并。该 CI 只证明源 SVG 生产契约,不替代受控字体渲染、像素等价验证或多模态视觉目检。
受控字体渲染(v1.8.9+):源 SVG 为保证 Markdown/Obsidian 兼容,不嵌 <style> 或字体栈;导出工具统一读取单一权威源 assets/render-fonts.css:
# 快速预览(librsvg;固定外部 CSS + 宽 720,不指定高度)
python3 scripts/render_svg.py input.svg output.png
# 高 DPI(Puppeteer/Chrome;注入同一外部 CSS)
node scripts/svg2png.js input.svg output.png 300
# 修改字体接线、身份元数据或 SVG 生成器后:逐像素比对两类基线
python3 scripts/verify_render_font_equivalence.py禁止用裸 rsvg-convert 结果作为验收证据:它会按环境默认字体渲染,已实测产生 serif 退化和像素漂移。浏览器预览可继承宿主字体,但正式导出/验收必须走上述受控入口。像素等价脚本同时比较“旧内嵌字体 vs 外部字体”和“无 ID vs 有 ID”两组基线;它是本地渲染回归证据,需要机器已有 rsvg-convert 与 ImageMagick,不属于只校验源码契约的 GitHub Actions check,也不替代逐图视觉目检。
13 种布局模板(11 种基础 + 2 种组合),详见 references/layout-templates.md。
| 模板 | 适用场景 | 典型元素数 |
|---|---|---|
| flow | 流程图、步骤图、管道图 | 3-5 个节点(水平≤4) |
| layer | 层次架构、分层堆叠 | 3-4 层 |
| matrix | 前后对比、并排比较 | 2 列 |
| hub | 中心辐射、生态关系 | 1 核心 + 4-8 外围 |
| tree | 层级结构、组织图、金字塔 | 3 层 |
| cycle | 循环流程、迭代闭环 | 4-6 个节点 |
| radar(v1.8.0) | 多维度数值对比(理论 vs 实际 / 能力评估 / 国内外 / 模型适配) | 6-12 维,1-2 系列 |
| skill-card(v1.8.1) | 单个 Skill 的结构(输入→Skill 三件套+流程→输出) | 1 Skill + 3-5 步 |
| timeline-lane(v1.8.2) | 多角色/多主体时间推进(诉讼多角色时间线/案件流程节点) | 3-5 泳道,每道 2-5 事件 |
| matrix-grid(v1.8.3) | 两维交叉对照(风险×条款 / 特征×产品 / 能力×模型) | N×M 网格(3-6 × 3-7) |
| three-col(v1.8.4) | 三分类/三版本对仗并列(每栏带子卡片) | 3 栏 × 3-4 子卡片 |
| flow+matrix | 递进流程附带阶段对比 | 3-4 阶段 + 对比区 |
| flow+hub | 编排流程中节点展开 | 主流程 + 展开节点 |
详见 references/style-guide.md。核心要点:
--padding 只拦「边距不足」;「留白过大」无法与有意分组留白机械区分,由视觉复审兜底——因此本纪律约束的是删除动作的当下,不是事后清扫。#2D3436/#636E72 保证可读。打印友好约束(文字 vs 所在模块填充色对比 ≥4.5:1 WCAG AA、相邻模块区分度 ≥10%、模块色明度 L*≥80、禁高饱和荧光、CMYK 不偏色、灰度差≥10%)。仅新生成图用新配色,main 上既有 34 张白底单色 SVG 保持稳定不回改。fill/stroke 属性内联——禁 <style> 块定义颜色、禁 <svg> 开标签写 font-family、禁 CSS 变量/class、禁画背景矩形(已验证的 Obsidian 渲染 + 透明背景硬约束,详见 references/style-guide.md §5.4)。references/style-guide.md §5.5):① 深底浅字——深色填充(L* ≤ 50,如 #2C5282/#1A202C/G4 深档/项目 canonical 强调色)的模块内 <text> 必须用 #FFFFFF/#EDF2F7,禁深底深字;② 字色对比度——文字 fill 与所在模块 fill 对比 ≥ 4.5:1(AA,大文本 ≥ 3:1);③ 箭头落点——marker 单 id="arrow" + markerUnits=userSpaceOnUse + orient=auto,落点 x2 = 目标框边 − 4px、方向指向目标节点;④ 文字完整性——每个有标题语义的节点框都有非空 <text>、文字坐标在框内、fill 与模块不同色。源 T134 review 实测:图 7-6 箭头错位 / 图 11-8 字色不可辨 / 图 11-9 深蓝底深字 / 图 7-13/8-3/6-7 框内文字缺失。references/style-guide.md §5.0/§5.1):① 文字色统一深灰二档——图内所有文字仅允许 #2D3436(主)/#636E72(次),深底走 #FFFFFF/#EDF2F7;不再用 #1A202C/#4A5568(收敛二档消除四档混用)。② 项目 canonical 主色(如 #2C5282/#1A365D 蓝)只用于焦点节点填充/描边,禁作文字 fill——以色块承载强调,文字强调改用字重/字号;这是通用纪律,非项目指针(任何项目锁定主色为视觉标识时都适用)。③ 每张结构/流程图 ≥1 焦点节点——layer/tree/flow/hub/cycle/matrix 应至少有 1 个焦点节点(canonical 主色或更深一档填充/描边)承载层次,反对纯灰平铺;纯并列清单无自然焦点时用灰阶递进 + 边框粗细区分。源法律 AI Skill 实战 DEC-114 方案 A 定调(图 1-6 灰阶 + 唯一蓝色焦点 = 层次标杆、零蓝字)。references/style-guide.md §六):有流程 / 反馈 / 复核 / 状态含义的线不因删繁而删除;同一分叉主干与支线连续;相邻层级箭头优先 16–32px 可见线身、超过 48px 先压缩布局。深色标签 + 浅色正文是一张卡时标题栏只留上圆角;步骤编号占独立上方带;图例只说明读者需要理解的关系。data-overlap-role="container",并同时写单图唯一原生 id、明示承载关系的 data-overlap-note 与非透明 hex/rgb/hsl fill。静态契约只审声明,实际几何由 writing-reviewer render gate 审计references/diagram-catalog.md 定义插图目录格式和创建方法。
出版社通常需要位图版本。scripts/svg2png.js 会读取 assets/render-fonts.css,将 SVG 转为高分辨率 PNG:
# 单张转换(默认 600 DPI)
node scripts/svg2png.js input.svg
# 指定输出文件和 DPI
node scripts/svg2png.js input.svg output.png 300
# 批量转换目录下所有 SVG
find figures/ -name "*.svg" -exec node scripts/svg2png.js {} \;依赖:快速预览 wrapper 需要系统已有 rsvg-convert;高 DPI 导出需要 Puppeteer 和 Chrome/Chromium。缺失时脚本会明确报错,不会自动安装。首次使用高 DPI 功能前由用户自行运行:npm install puppeteer
印刷 DPI 建议:
生成流程之外,对已成稿书稿的全部内联 SVG 跑规则巡检(只报告,不改稿;不替代 writing-reviewer render gate 的几何/视觉审计):
python3 scripts/scan_consistency.py --book-root <书仓根目录> --report <报告输出.md>
# 阈值可调:--padding 40(安全边距 px)、--arrow-gap 8(箭头悬空 px)
# CI 门禁形态:--fail-on hard(存在 hard finding 时退出码 1)规则覆盖(19 条,每条 finding 带规则 ID / 文件 / SVG 序号 / 位置 / 严重度 hard|soft):
data-arrow-role="axis|annotation" + 非空 note 声明的悬空箭头(style-guide §5.5.3 / FIGURES-OUTLINE DEC-128)arrow 的多 marker / 缺 markerUnits="userSpaceOnUse"+orient="auto" / 悬空 url(#id) 引用(v1.6.0)<style> 块、style=、font-family、整幅画布底色矩形、width/height/viewBox 契约(v1.8.9)data-figure-id 缺失(soft,历史不回填口径)/ 格式不安全 / fig-template-* 落稿 / 跨图重复manuscript/**/*_images/<stem>-svg-N.svg 派生缓存内容一致(T261 口径)历史口径:对 v1.8.9 前历史书稿的 SYNTAX/IDENTITY 发现只登记不要求回改(与本 skill「不回改历史书稿」既有口径一致)。v1.9.1 新增 --exemptions <台账.json>:逐项豁免已裁决历史项(键=file/svg_index/rule_id),命中不计 findings、未命中报警防台账漂移、坏台账 fail-closed;整规则豁免被有意排除——新图违规永远照报。与 BLOCKED Task-001(producer 冲突)/ Task-002(shape containment)互不侵入:本 scan 不改 producer、不做包含几何判定。
data-figure-id;无嵌入 font-family、无 <style>/style=、颜色只用 fill/stroke 属性内联、无背景矩形、xmllint well-formed;受控 wrapper 渲染无警告)container 窄声明并由 writing-reviewer render gate 留证fill/stroke 属性内联;既有 34 张白底单色图保持稳定不回改#FFFFFF/#EDF2F7(禁深底深字);文字 vs 所在模块对比 ≥ 4.5:1;箭头落点 x2 = 目标框边 − 4px、方向指向目标;每个有标题语义的节点框都有非空 <text>、坐标在框内、fill 与模块不同色(详见 style-guide §5.5)#2D3436/#636E72(+ 深底浅字 #FFFFFF/#EDF2F7),不再用 #1A202C/#4A5568;项目 canonical 主色只焦点节点填充/描边、禁作文字 fill;每结构/流程图 ≥1 焦点节点(详见 style-guide §5.0/§5.1)源生产契约与受控渲染只是必要不充分条件——保证 SVG 可解析、画布与样式受控,不保证图正确美观。密度 + 一致性 + 目检三道审查才是验收依据(
references/review-checklist.md)。
© cat-xierluo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 22 other files (scripts, references, assets) in skills/svg-book-illustrator of cat-xierluo/legal-skills.
Open the folder on GitHubat commit f844ebe
SVG Book Illustrator 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| SVG Book Illustrator this skillcat-xierluo/legal-skills | 721 | — | ~3k | Automated safety check: Pass | MIT | |
| Visual Designaws-samples/sample-strands-agent-with-agentcore | 195 | — | ~1.5k | Automated safety check: Pass | MIT | |
| Smart Illustratoraxtonliu/smart-illustrator | 564 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Chart Image Generator for WeChat ArticlesSpaceZephyr/creator-buddy | 1.6k | — | ~1.7k | Automated safety check: Pass | None | |
| Article Illustration Batch GeneratorSpaceZephyr/design-buddy | 176 | — | ~1k | Automated safety check: Pass | None | |
| Microsim Generatordmccreary/ibook-skills | 105 | — | ~11k | Automated safety check: Pass | None |
aws-samples/sample-strands-agent-with-agentcore
Use this skill any time the user needs a visual output as an image or PDF — charts, diagrams, posters, infographics, abstract artwork, or any visual design.
axtonliu/smart-illustrator
Generates article illustrations, batch slide infographics and cover images from your text, using Gemini, Mermaid or Excalidraw engines and a prompt-only mode.
SpaceZephyr/creator-buddy
Draws chart images such as flowcharts, architecture diagrams, ER diagrams and SWOT boards for WeChat official account articles, in one of six visual styles.
SpaceZephyr/design-buddy
Splits a Markdown article by heading, drafts an image prompt for each section, then generates diagrams with the Gemini API and embeds them in the note.
dmccreary/ibook-skills
Creates interactive educational MicroSims, routing to the best-matched generator - p5.js, Chart.js, Plotly, Mermaid, vis-network, timelines, maps, Venn, causal-loop/feedback-loop diagrams (CLD)…
stevenflanagan1/social-ai-team
Social Media Publisher. An agent skill from stevenflanagan1/social-ai-team.
cat-xierluo/legal-skills
Converts a lawyer's ordinary complaint or a described case into the Supreme People's Court's elements-style Word template, with layout checks on the result.
cat-xierluo/legal-skills
Analyzes raw lecture transcripts for verbal tics, pacing, time use and promise follow-through, with optional slide-by-slide comparison and cross-session tracking.
cat-xierluo/legal-skills
Detects and rewrites machine-sounding patterns in the body text of Chinese articles while keeping the author's facts, headings and legal terms intact.
cat-xierluo/legal-skills
Finds GitHub projects mentioned in articles or screenshots and stars them, tracks updates to your starred repos, and builds an HTML dashboard to browse them.
cat-xierluo/legal-skills
Sets up or incrementally updates AGENTS.md and CLAUDE.md for legal professionals, with a minimal safety baseline and a check that a new session loads and follows the rules.
cat-xierluo/legal-skills
Chinese-language skill that organizes a case file into a multi-role mock trial with judge, parties and clerk, producing a transcript, issue review and a to-strengthen list.
Works with
Categories
Generates clean static SVG diagrams for book chapters and formal articles, such as architecture, flow and hierarchy figures, embedded in Markdown and checked against review gates. The skill reads a chapter in Markdown, finds places where a diagram would help (architecture, process, comparison, hierarchy, cycle, ecosystem, multi-dimension scoring, timeline or cross-tab descriptions) and inserts numbered figure placeholders. It then picks a layout template, such as flow, layer, matrix, hub, tree, cycle, radar, skill-card, timeline-lane, matrix-grid or three-col, and writes SVG following a style guide, with a unique figure ID on each root element and a caption below.
SVG Book Illustrator fits situations like: adding architecture or flow diagrams to a book chapter; replacing mermaid or ASCII diagrams with print-ready SVG; checking that figures match the text and are spread evenly across chapters; creating radar, timeline or matrix figures for a formal article.
Run `npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a claude-code`. Or copy the skill folder (skills/svg-book-illustrator in cat-xierluo/legal-skills) into .claude/skills/svg-book-illustrator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a codex`. Or copy the skill folder (skills/svg-book-illustrator in cat-xierluo/legal-skills) into .agents/skills/svg-book-illustrator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cat-xierluo/legal-skills --skill svg-book-illustrator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/svg-book-illustrator, .gemini/skills/svg-book-illustrator, .github/skills/svg-book-illustrator and .opencode/skills/svg-book-illustrator in your project.
Going by SKILL.md and its folder, SVG Book Illustrator needs Python for the scripts in its folder and the command-line tools its instructions call (python3, node, python and npm). Our summary lists: Python 3 for the bundled scripts.
SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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.
SVG Book Illustrator is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 3k tokens (SKILL.md is roughly 12k 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 23k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with SVG Book Illustrator: Visual Design (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Smart Illustrator (axtonliu/smart-illustrator, 564 stars), Chart Image Generator for WeChat Articles (SpaceZephyr/creator-buddy, 1.6k stars) and Article Illustration Batch Generator (SpaceZephyr/design-buddy, 176 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
cat-xierluo (a GitHub user) maintains it in cat-xierluo/legal-skills, which has 721 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 10, 2026.
Source: cat-xierluo/legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.