Claude Skill
shaom/infocard-skills
infocard-skills is an open-source collection of agent skills that generate editorial-style information cards from natural-language input. Ideal for AI agents and automated content workflows.
Overview
Repository
Install this Skill
git clone https://github.com/shaom/infocard-skills.gitRegistry
Summary
infocard-skills is an open-source collection of agent skills that transform natural-language input into editorial-style information cards. Designed for AI agents, it enables the automatic generation of visually structured, publication-ready infocards without manual design work.
开源代理技能，用于从自然语言输入生成编辑风格的信息卡片。
Key features
- Natural-language to editorial infocard generation
- Open-source agent skills for AI integration
- Structured, publication-ready card output
- Lightweight and easy to deploy
Use cases
- Automated news summary cards for AI agents
- Quick editorial content previews
- Data-to-visual card conversion in chatbots
- Rapid prototyping of information displays
README excerpt
[中文](./README.zh-CN.md) # infocard-skills Open-source agent skills for generating editorial-style information cards from natural-language input.  `infocard-skills` is a small repository of installable skill packages for agents. The current package, `editorial-card-screenshot`, turns source material into screenshot-ready HTML cards and optional PNG outputs. ## Install Install the full skill package, not a single file: - [`skills/editorial-card-screenshot`](./skills/editorial-card-screenshot) Copy or install the entire directory into your agent's skills location. Keep these files together: - `SKILL.md` - `assets/` - `references/` - `scripts/` - `agents/` when supported by the host ## Verify After installation, test with one of these prompts: - `Use $editorial-card-screenshot to turn these notes into an editorial info card.` - `Use $editorial-card-screenshot to make a 3:4 information card from this text.` - `Use $editorial-card-screenshot and give me both the HTML and PNG.` ## Usage Typical requests: - `Turn this article into an editorial information card.` - `Make a portrait 3:4 info card from these notes.` - `Summarize this content as a dense magazine-style card.` - `Create the HTML only. I do not need the image.` ## Render Requirement For PNG capture, the current helper expects local Google Chrome at: ```text /Applications/Google Chrome.app/Contents/MacOS/Google Chrome ``` ## Repository ```text skills/ editorial-card-screenshot/ docs/ examples/ ``` ## Docs - [`docs/agent-usage.md`](./docs/agent-usage.md) - [`docs/editorial-card-prompt.md`](./docs/editorial-card-prompt.md) - [`docs/project-overview.md`](./docs/project-overview.md) - [`docs/github-metadata.md`](./docs/github-metadata.md