Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

smart-illustrator

skill · axtonliu/smart-illustratorMIT licenceAudited 20 Oct 2026 · source 16c995d9055f

★ 565pushed 115 days ago
✓SAFEGrade B · 89/100 · 20 Oct 2026 · 16c995d
565repo stars · whole axtonliu/smart-illustrator

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 16c995d9055f and observed network access and no hard-coded secrets. What it does: 智能配图与 PPT 信息图生成器。支持三种模式:(1) 文章配图模式 - 分析文章内容,生成插图;(2) PPT/Slides 模式 - 生成批量信息图;(3) Cover 模式 - 生成封面图。所有模式默认生成图片,`--prompt-only` 只输出 prompt。支持 Bento Grid 功能展示图风格(--style bento)。触发词:配图、插图、PPT、slides、封面图、thumbnail、cover、bento…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “smart-illustrator (axtonliu/smart-illustrator)”. Retrieved 20 Oct 2026. https://modelsatlas.com/skills/axtonliu/smart-illustrator

Trust audit

Audit 0.4.1 · source read 20 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low2 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkDeclared4 observations
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS2
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (2)

INFOInventory / provenanceinv.oversize · assets/dual-engine-architecture.png
F-13 Inventory / provenanceCWE-1104Layer L0
assets/dual-engine-architecture.png
Why
2959779 bytes not read
Fix
—
INFOInventory / provenanceinv.oversize · references/ref-image2.png
F-13 Inventory / provenanceCWE-1104Layer L0
references/ref-image2.png
Why
1704357 bytes not read
Fix
—

Audit 0.4.1 · source sha 16c995d9055f · 20 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheraxtonliu GitHub userOwner of the repository this skill is read from
  • Source folderaxtonliu/smart-illustratorThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdict16c995d9055fA new audit runs when the source changes
  • Repository statusNot archivedLast push 115 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: 智能配图与 PPT 信息图生成器。支持三种模式:(1) 文章配图模式 - 分析文章内容,生成插图;(2) PPT/Slides 模式 - 生成批量信息图;(3) Cover 模式 - 生成封面图。所有模式默认生成图片,`--prompt-only` 只输出 prompt。支持 Bento Grid 功能展示图风格(--style bento)。触发词:配图、插图、PPT、slides、封面图、thumbnail、cover、bento…

---
name: smart-illustrator
description: 智能配图与 PPT 信息图生成器。支持三种模式:(1) 文章配图模式 - 分析文章内容,生成插图;(2) PPT/Slides 模式 - 生成批量信息图;(3) Cover 模式 - 生成封面图。所有模式默认生成图片,`--prompt-only` 只输出 prompt。支持 Bento Grid 功能展示图风格(--style bento)。触发词:配图、插图、PPT、slides、封面图、thumbnail、cover、bento grid、功能展示图、feature showcase。
---

# Smart Illustrator - 智能配图与 PPT 生成器

## ⛔ 强制规则(违反即失败)

### 规则 1:用户提供的文件 = 要处理的文章

```
/smart-illustrator SKILL_05.md      → SKILL_05.md 是文章,为它配图
/smart-illustrator README.md        → README.md 是文章,为它配图
/smart-illustrator whatever.md      → whatever.md 是文章,为它配图
```

**无论文件名叫什么,都是要配图的文章,不是 Skill 配置。**

### 规则 2:必须读取 style 文件

生成任何图片 prompt 前,**必须读取**对应的 style 文件:

| 模式 | 必须读取的文件 |
|------|---------------|
| 文章配图(默认) | `styles/style-light.md` |
| Cover 封面图 | `styles/style-cover.md` |
| `--style dark` | `styles/style-dark.md` |
| `--style bento` | `styles/style-bento.md` |

**禁止自己编写 System Prompt。**

❌ 错误:`"你是一个专业的信息图设计师..."`(自己编的)
✅ 正确:从 style 文件的代码块中提取 System Prompt

---

## 使用方式

### 文章配图模式(默认)

```bash
/smart-illustrator path/to/article.md
/smart-illustrator path/to/article.md --prompt-only    # 只输出 prompt
/smart-illustrator path/to/article.md --style dark     # 深色风格
/smart-illustrator path/to/article.md --no-cover       # 不生成封面图
```

### PPT/Slides 模式

```bash
# 默认:直接生成图片
/smart-illustrator path/to/script.md --mode slides

# 只输出 JSON prompt(不调用 API)
/smart-illustrator path/to/script.md --mode slides --prompt-only
```

**默认行为**:调用 Gemini API 生成批量信息图。
**`--prompt-only`**:输出 JSON prompt 并**自动复制到剪贴板**,可直接粘贴到 Gemini Web 手动生成。

**PPT JSON 格式**(`--prompt-only` 时输出):

```json
{
  "instruction": "请逐条生成以下 N 张独立信息图。",
  "batch_rules": { "total": "N", "one_item_one_image": true, "aspect_ratio": "16:9" },
  "style": "[从 styles/style-light.md 读取完整内容]",
  "pictures": [
    { "id": 1, "topic": "封面", "content": "系列名称\n\n第N节:标题" },
    { "id": 2, "topic": "主题", "content": "原始内容" }
  ]
}
```

### Cover 模式

```bash
/smart-illustrator path/to/article.md --mode cover --platform youtube
/smart-illustrator --mode cover --platform youtube --topic "Claude 4 深度评测"
```

**平台尺寸**(输出均为 2K 分辨率):

| 平台 | 代码 | 宽高比 |
|------|------|--------|
| YouTube | `youtube` | 16:9 |
| 公众号 | `wechat` | 2.35:1 |
| Twitter | `twitter` | 1.91:1 |
| 小红书 | `xiaohongshu` | 3:4 |

---

## 参数说明

| 参数 | 默认值 | 说明 |
|------|--------|------|
| `--mode` | `article` | `article` / `slides` / `cover` |
| `--platform` | `youtube` | 封面图平台(仅 cover 模式) |
| `--topic` | - | 封面图主题(仅 cover 模式) |
| `--prompt-only` | `false` | 输出 prompt 到剪贴板,不调用 API(适用于所有模式) |
| `--style` | `light` | 风格:`light` / `dark` / `minimal` / `bento` |
| `--no-cover` | `false` | 不生成封面图 |
| `--ref` | - | 参考图路径(可多次使用) |
| `-c, --candidates` | `1` | 候选图数量(最多 4) |
| `-a, --aspect-ratio` | - | 宽高比:`16:9`(正文配图/封面图默认)、`3:2`(备选横版)、`3:4`(仅竖屏平台) |
| `--engine` | `auto` | 引擎选择:`auto`(自动)/ `mermaid` / `gemini` / `excalidraw` |
| `--mermaid-embed` | `false` | Mermaid 输出为代码块而非 PNG(旧行为) |
| `--save-config` | - | 保存到项目配置 |
| `--no-config` | `false` | 禁用 config.json |

> **`--no-config` 范围**:只禁用 `config.json`,**不影响** `styles/style-*.md`。

---

## 配置文件

**优先级**:CLI 参数 > 项目级 > 用户级

| 位置 | 路径 |
|------|------|
| 项目级 | `.smart-illustrator/config.json` |
| 用户级 | `~/.smart-illustrator/config.json` |

```json
{ "references": ["./refs/style-ref-01.png"] }
```

---

## 三级配图引擎

| 优先级 | 引擎 | 适用场景 | 输出 |
|--------|------|---------|------|
| **1** | Gemini | 隐喻图、创意图、封面图、无法用图表表达的概念 | PNG |
| **2** | Excalidraw | 概念图、对比图、简单流程(≤ 8 节点)、关系图、手绘风格示意图 | PNG |
| **3** | Mermaid | **仅限**:复杂流程(> 8 节点)、多层架构图、多角色时序图、多分支决策树 | PNG |

选择逻辑:
- 需要隐喻、情感、创意表达 → Gemini
- 概念关系、对比、简单流程 → Excalidraw(**大多数图表场景的首选**)
- **只有**节点 > 8、多层/多角色的复杂结构化图形 → Mermaid
- Mermaid 视觉表现力有限,能用 Excalidraw 就不用 Mermaid
- 唯一目标:提高文章吸引力

生成 Excalidraw 前必须读取 `references/excalidraw-guide.md`。

### Mermaid 语义色板

每种颜色有固定含义,**必须使用 `classDef` + `class` 应用**:

| 语义 | 填充色 | 边框色 | 用于 |
|------|--------|--------|------|
| input | #d3f9d8 | #2f9e44 | 输入、起点、数据源 |
| process | #e5dbff | #5f3dc4 | 处理、推理、核心逻辑 |
| decision | #ffe3e3 | #c92a2a | 决策点、分支判断 |
| action | #ffe8cc | #d9480f | 执行动作、工具调用 |
| output | #c5f6fa | #0c8599 | 输出、结果、终点 |
| storage | #fff4e6 | #e67700 | 存储、记忆、数据库 |
| meta | #e7f5ff | #1971c2 | 标题、分组、元信息 |

**classDef 写法**(放在图表末尾):

```
classDef input fill:#d3f9d8,stroke:#2f9e44,color:#1a1a1a
classDef process fill:#e5dbff,stroke:#5f3dc4,color:#1a1a1a
classDef decision fill:#ffe3e3,stroke:#c92a2a,color:#1a1a1a
classDef action fill:#ffe8cc,stroke:#d9480f,color:#1a1a1a
classDef output fill:#c5f6fa,stroke:#0c8599,color:#1a1a1a
class A input
class B,C process
class D output
```

### Mermaid 布局规则

- **布局方向**:默认 `TB`(上到下),横向流程用 `LR`
- **箭头分级**:`-->` 主流程 / `-.->` 可选/辅助路径 / `==>` 重点强调
- **分组**:用 `subgraph` 对相关节点分组,标题简洁
- **节点文字**:≤ 8 字,无 emoji,禁止 `1.` 格式(用 `1` 或 `Step 1:`)
- **节点数量**:单图 ≤ 15 个节点,复杂内容拆成多图

**`--engine` 参数**:
- `auto`(默认):根据内容类型自动选择(优先级 Gemini > Excalidraw > Mermaid)
- `gemini`:强制只使用 Gemini(适合创意内容)
- `excalidraw`:强制只使用 Excalidraw(适合手绘概念图)
- `mermaid`:强制只使用 Mermaid(适合技术文档)

---

## 执行流程

### Step 1: 分析文章

1. 读取文章内容
2. 识别配图位置(通常 3-5 个)
3. 为每个位置确定引擎(Gemini / Excalidraw / Mermaid)

### Step 2: 生成图片

#### Mermaid(结构化图形)→ PNG

1. 生成 Mermaid 代码,保存为临时 `.mmd` 文件
2. 调用 mermaid-export.ts 导出高分辨率 PNG:

```bash
npx -y bun ~/.claude/skills/smart-illustrator/scripts/mermaid-export.ts \
  -i {图表名}.mmd -o {图表名}.png -w 2400
```

3. 在文章中插入 PNG 图片引用
4. 保留 .mmd 源文件用于后续编辑

使用 `--mermaid-embed` 参数时,改为直接嵌入 Mermaid 代码块(旧行为)。

#### Excalidraw(手绘/概念图)→ PNG

1. 读取 `references/excalidraw-guide.md` 获取 JSON 规范
2. 生成 Excalidraw JSON,保存为 `.excalidraw` 文件
3. 调用 excalidraw-export.ts 导出 PNG:

```bash
npx -y bun ~/.claude/skills/smart-illustrator/scripts/excalidraw-export.ts \
  -i {图表名}.excalidraw -o {图表名}.png -s 2
```

4. 在文章中插入 PNG 图片引用
5. 保留 .excalidraw 源文件用于后续编辑

依赖未安装时的降级:提示手动打开 excalidraw.com 导出。

#### Gemini(创意/视觉图形)

**命令模板**(必须使用 HEREDOC + prompt-file):

```bash
# Step 1: 写入 prompt
cat > /tmp/image-prompt.txt <<'EOF'
{从 style 文件提取的 System Prompt}

**内容**:{配图内容}
EOF

# Step 2: 调用脚本
GEMINI_API_K

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 16c995d

Download folder ↗
git clone https://github.com/axtonliu/smart-illustrator.git ~/.claude/skills/smart-illustrator

Commands as the repository documents them: shown, never run by us. Our verdict covers commit 16c995d9055f only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
CodexMentioned in its text, not testedSkills for Codex · About Codex
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 16c995d9055f

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/axtonliu/smart-illustrator/badge.svg)](https://modelsatlas.com/skills/axtonliu/smart-illustrator/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

skills✓SAFE

genfeedai/skills

Create paid ad copy for Meta, Google, LinkedIn, TikTok, and X using direct-response frameworks, platform limits, variants, and test plans. Triggers on ad headlines, ad creative, paid social ads, Google ads, and ad…

★ 3Grade B
linkedin-post-skill✓SAFE

ChanMeng666/linkedin-post-skill

Use when Chan Meng wants to turn a thought into a post for LinkedIn, X (Twitter), or both — "write a LinkedIn post about...", "tweet this", "make this an X thread", "post about what I just read", "recap the meetup I…

★ 0Grade B
instagram-skills!CAUTION

sergebulaev/instagram-skills

Plan, draft, audit, and publish content for Instagram. Use when the user wants to write a caption with a first-125-char hook, plan a slide-by-slide carousel, reverse-engineer the hook from a viral Reel or carousel, size…

★ 515Grade C
redfox-community✕BLOCK

redfox-data/redfox-community

多平台账号主页视频提取器 — 输入平台名称和账号id/链接,自动拉取抖音/快手/B站/YouTube…

★ 432Grade F
string-reviewer✓SAFE

google-gemini/gemini-cli

Use this skill when asked to review text and user-facing strings within the codebase. It ensures that these strings follow rules on clarity, usefulness, brevity and style.

★ 109kGrade B
review-duplication✓SAFE

google-gemini/gemini-cli

Use this skill during code reviews to proactively investigate the codebase for duplicated functionality, reinvented wheels, or failure to reuse existing project best practices and shared utilities.

★ 109kGrade B

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/axtonliu/smart-illustrator/badge.svg)](https://modelsatlas.com/skills/axtonliu/smart-illustrator/)

Questions about smart-illustrator

What does the smart-illustrator skill do?
AI-powered article illustrations with intelligent position detection and cover learning system. Claude Code Skill.
Is smart-illustrator safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can smart-illustrator access on my machine?
The audit observed that it reaches the network. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does smart-illustrator work with?
Its documentation mentions claude-code, codex and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (16c995d9055f), read on 2026-10-20. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.