一键在 Manus 中运行任何 Skill

mofa-infographic

星标11

分支12

更新时间2026年6月8日 17:36

AI-generated infographics and visual posters. Triggers: infographic, poster, 信息图, 海报, data poster, visual summary, mofa infographic. Generates multi-section infographic via Gemini with optional Qwen-Edit refinement, stitched into a single tall image.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

mofa-org

mofa-org/mofa-skills

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

mofa-infographic

CLI: mofa infographic — generate multi-section infographic posters via Gemini, stitched vertically into a single tall PNG. Optional Qwen-Edit refinement (requires DASHSCOPE_API_KEY).

For LLM-facing discovery and routing, the manifest discovery card declares the hints below; this SKILL.md is the long-form reference loaded on demand.

Output paths (LOAD-BEARING)

Use RELATIVE paths. Never prefix skill-output/ yourself — the Octos host rebinds plugin output paths to <workspace>/skill-output/ automatically; a manual prefix double-prefixes and breaks delivery. Never use absolute paths like /tmp/poster.png.

mofa-infographic-<YYYYMMDD-HHMMSS>/poster.png
mofa-infographic-<YYYYMMDD-HHMMSS>/sections/

The out argument MUST be a relative path — the tool description repeats this. Absolute paths break the workspace contract and prevent the output from being delivered.

Built-in styles (4)

`--style`	Best For
`cyberpunk-neon` (default)	Tech, AI, data
`editorial`	Reports, articles, longform
`clean-light`	Business, consulting
`multi-panel`	Comparisons, multi-topic summaries

Full style table, custom inline styles, and variants (header / normal / footer): see docs/styles.md.

Section JSON (top-level: array of section objects)

Field	Required	Description
`prompt`	yes	Section content description (data, titles, visual elements)
`variant`	no	`"header"` / `"normal"` / `"footer"` (auto-detected by position)
`refine_prompt`	no	Qwen-Edit refinement instruction (needs `--refine` + DASHSCOPE_API_KEY)

Full schema, prompt writing tips, and 4 worked examples (tech / business / editorial / batch): see docs/examples.md.

Quick reference

CLI flags, resolution & quality, output structure, mofa/config.json: docs/cli-flags.md.
API modes (rt vs batch), per-section timing, 10-minute timeout strategy, cached-section recovery: docs/api-modes-and-timing.md.
Telegram preferences flow + inline-keyboard example for picking style / sections / resolution: docs/interaction.md.

Minimal example

[
  {"prompt": "Header: 'Q3 Review' bold title, gradient background.", "variant": "header"},
  {"prompt": "3 KPI cards: Revenue $12.4M, NPS 72, Churn 2.1%."},
  {"prompt": "Footer: sources and credits.", "variant": "footer"}
]

mofa infographic --style clean-light --out review.png -i sections.json

Run notes

Each section ~15-30s. Keep sections ≤8 for a single call to stay inside the 600s tool timeout.
--api batch is 50% cheaper but 5-30 min — avoid in octos tool calls.
Cached sections (section-XX.png >10KB) are reused on rerun; delete to regenerate.

同仓库更多 Skills

同仓库

mofa-publish

mofa-org/mofa-skills

Deploy static sites to GitHub Pages or Mac Mini hosting. Triggers: mofa publish, deploy site, publish website, 发布网站, 部署网页, github pages, deploy to mini, host website, 上线, push to pages, mofa deploy, 发布到GitHub.

2026-06-2211

mofa-site

mofa-org/mofa-skills

Build or scaffold websites from content using Quarto, Astro, Next.js, or React/Vite. Triggers: mofa site, build website, make a website, 建网站, 做个网站, generate site, mofa web, create website, 生成网页, build lesson site, build docs site, 做个教程网站.

2026-06-2211

mofa-cli

mofa-org/mofa-skills

Shared CLI binary for all mofa skills (slides, cards, comic, infographic, video). Not a user-facing skill.

2026-06-2011

mofa-cards

mofa-org/mofa-skills

AI-generated greeting cards as PNG images. Triggers: greeting card, 贺卡, mofa card, mofa 贺卡, make a card, CNY card, New Year card, 新年贺卡, ink-wash card. Generates full-bleed AI artwork via Gemini in various Chinese art styles.

2026-06-0811

mofa-comic

mofa-org/mofa-skills

AI-generated comic strips and illustrations. Triggers: comic, manga, xkcd, 漫画, comic strip, 四格漫画, panel comic, illustration strip, snoopy. Generates multi-panel comics via Gemini with optional Qwen-Edit refinement, stitched into a single image.

2026-06-0811

pdf

mofa-org/mofa-skills

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

2026-06-0811

name	mofa-infographic
version	0.5.0
description	AI-generated infographics and visual posters. Triggers: infographic, poster, 信息图, 海报, data poster, visual summary, mofa infographic. Generates multi-section infographic via Gemini with optional Qwen-Edit refinement, stitched into a single tall image.
requires_bins	mofa
requires_env	GEMINI_API_KEY

mofa-infographic

CLI: mofa infographic — generate multi-section infographic posters via Gemini, stitched vertically into a single tall PNG. Optional Qwen-Edit refinement (requires DASHSCOPE_API_KEY).

For LLM-facing discovery and routing, the manifest discovery card declares the hints below; this SKILL.md is the long-form reference loaded on demand.

Output paths (LOAD-BEARING)

mofa-infographic-<YYYYMMDD-HHMMSS>/poster.png
mofa-infographic-<YYYYMMDD-HHMMSS>/sections/

The out argument MUST be a relative path — the tool description repeats this. Absolute paths break the workspace contract and prevent the output from being delivered.

Built-in styles (4)

`--style`	Best For
`cyberpunk-neon` (default)	Tech, AI, data
`editorial`	Reports, articles, longform
`clean-light`	Business, consulting
`multi-panel`	Comparisons, multi-topic summaries

Full style table, custom inline styles, and variants (header / normal / footer): see docs/styles.md.

Section JSON (top-level: array of section objects)

Field	Required	Description
`prompt`	yes	Section content description (data, titles, visual elements)
`variant`	no	`"header"` / `"normal"` / `"footer"` (auto-detected by position)
`refine_prompt`	no	Qwen-Edit refinement instruction (needs `--refine` + DASHSCOPE_API_KEY)

Full schema, prompt writing tips, and 4 worked examples (tech / business / editorial / batch): see docs/examples.md.

Quick reference

CLI flags, resolution & quality, output structure, mofa/config.json: docs/cli-flags.md.
API modes (rt vs batch), per-section timing, 10-minute timeout strategy, cached-section recovery: docs/api-modes-and-timing.md.
Telegram preferences flow + inline-keyboard example for picking style / sections / resolution: docs/interaction.md.

Minimal example

[
  {"prompt": "Header: 'Q3 Review' bold title, gradient background.", "variant": "header"},
  {"prompt": "3 KPI cards: Revenue $12.4M, NPS 72, Churn 2.1%."},
  {"prompt": "Footer: sources and credits.", "variant": "footer"}
]

mofa infographic --style clean-light --out review.png -i sections.json

Run notes

Each section ~15-30s. Keep sections ≤8 for a single call to stay inside the 600s tool timeout.
--api batch is 50% cheaper but 5-30 min — avoid in octos tool calls.
Cached sections (section-XX.png >10KB) are reused on rerun; delete to regenerate.