Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AgenticAIPlan/AgenticAISkills --skill xinghe-imagegit clone --depth 1 https://github.com/AgenticAIPlan/AgenticAISkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agenticaiplan/agenticaiskills/xinghe-image)<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/xinghe-image"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/xinghe-image/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agenticaiplan/agenticaiskills/xinghe-image"><img src="https://agentmods.dev/badge/skills/agenticaiplan/agenticaiskills/xinghe-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.03660 |
| Opus 5 | $0.00042 | $0.01830 |
| Sonnet 5 | $0.00017 | $0.00732 |
| Haiku 4.5 | $0.00008 | $0.00366 |
Grade A, and why
xinghe-image scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
星河 AI 生图 Skill
统一生图入口，两条风格路线，按场景自动路由。
依赖
- 生图脚本：
scripts/generate.py - Python 3.8+ +
openai库（pip install openai） - 提示词语言：强制中文（中文效果更好）
- API：百度 AIStudio API + API Key（见下方首次配置）
首次配置：API Key 检测 ⛔ BLOCKING（每次启动执行）
每次 Skill 启动时，先运行以下检测命令：
test -n "$AISTUDIO_API_KEY" && echo "KEY_ENV=OK" || echo "KEY_ENV=MISSING"
KEY_ENV=OK → 直接进入 Step 0。
KEY_ENV=MISSING → 向用户说明并请求 API Key，配置完成前不继续：
⚠️ 未检测到 API Key，需要完成一次性配置才能生图。
请前往以下地址获取你的 Access Token（免费，登录百度账号即可）：
https://aistudio.baidu.com/account/accessToken
获取后，把 Key 直接粘贴到这里，我来帮你完成配置。
用户提供 Key 后，由 AI 自动完成以下全部步骤，无需用户手动操作：
Step A：检测当前 Shell
basename "$SHELL"
根据结果选择写入文件：zsh → ~/.zshrc，bash → ~/.bashrc，其他 → ~/.profile。
Step B：写入并生效
# 以 zsh 为例，实际根据 Step A 结果选择对应文件
echo 'export AISTUDIO_API_KEY={用户提供的Key}' >> ~/.zshrc && source ~/.zshrc
Step C：验证
python3 {baseDir}/scripts/generate.py \
--prompt "测试" --size 1024x1024 --output /tmp/xinghe-test.png
- 输出
✓ 已保存→ 配置成功，告知用户后继续 Step 0。 - 输出
错误:→ 提示 Key 可能有误，请用户重新获取后再次粘贴。
Step 0：欢迎菜单
智能跳过：若用户消息已包含以下触发词，直接进入 Step 1，不弹菜单。
| 触发词 | 对应场景 |
|---|---|
| 信息图、数据可视化、知识图谱、流程图 | 信息图 |
| 文章配图、章节配图 | 文章配图 |
| 封面、Banner、封面图 | 封面图 |
| 小红书图文、小红书帖子、小红书图片 | 小红书图文 |
无法识别场景时 ⛔ BLOCKING，使用 AskUserQuestion 展示以下选项：
你好！我是星河 AI 生图助手。
请选择你需要的生图类型：
1. 📊 信息图 —— 数据可视化、知识图谱、流程图海报
2. 🖼️ 文章配图 —— 为文章每个章节生成「海报级」配图（激进风格化）
3. 🎨 封面图 —— 博客/公众号/视频封面
4. 📱 小红书图文 —— 内容分析 + 多图卡片 + 文案包，一键生成完整发帖包
用户选择后，跳转到对应子流程（见下方路由表）。
Step 1：内容输入
根据选择的场景，引导用户提供：
| 场景 | 需要的输入 |
|---|---|
| 信息图 | 要可视化的内容/数据/主题，以及期望传达的核心信息 |
| 文章配图 | 文章全文或分段摘要 |
| 封面图 | 文章标题/主题描述，期望的视觉风格倾向（可选） |
| 小红书图文 | 文章/笔记/文案等已有内容，AI 自动分析拆解 |
文字来源原则：
- 凡是会出现在图片上或文案包里的文字内容，默认都应来自用户提供的文章、笔记、标题、数据或明确的措辞要求
- 允许为了版面和平台表达做压缩、改写、口语化重组，但不得新增原文中没有的事实、数据、结论、承诺、人物经历或卖点
- 如果用户只给了主题而没有给可直接上图的文案，优先生成无字视觉稿，或仅使用用户明确提供的标题
Step 2：风格路线选择
两条路线，按场景自动路由：
What ships with it
17 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/preview-banner-styles-1.png 1157 KB
- assets/preview-banner-styles-2.png 1692 KB
- assets/preview-banner-styles-3.png 1332 KB
- assets/preview-banner-styles-4.png 1027 KB
- assets/preview-xhs-presets-1.png 1620 KB
- assets/preview-xhs-presets-2.png 965 KB
- assets/preview-xhs-presets-3.png 717 KB
- assets/preview-xhs-presets-4.png 624 KB
- README.md 6.8 KB
- references/image-presets.csv 41 KB
- references/styles-index.csv 30 KB
- references/workflows/article-illustration.md 12 KB
- references/workflows/cover-image.md 6.8 KB
- references/workflows/infographic.md 5.0 KB
- references/workflows/prompt-assembly.md 23 KB
- references/workflows/xiaohongshu.md 6.6 KB
- scripts/generate.py 5.7 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 341 lines · 83 tokens per session scan A 11979911fe6b
xinghe-image is a skill published in the GitHub repository AgenticAIPlan/AgenticAISkills (11 stars, last pushed 3mo ago), licensed MIT. It adds 83 tokens to every session and 3,660 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.