This repository packages one agent skill for turning source text into editorial-style information cards. It focuses on layout-aware HTML output, with optional PNG capture, so the same content can be reshaped for different card formats instead of just resized.
Builders who want their agent to turn content into polished information cards.
You can turn notes or articles into screenshot-ready HTML cards without rebuilding the layout by hand.
Turns natural-language source material into dense, magazine-style information cards.
Creates screenshot-ready HTML and can also produce PNG images.
Supports multiple canvas shapes, including `3:4`, `4:3`, `1:1`, `16:9`, `9:16`, `2.35:1`, `3:1`, and `5:2`.
Ships as a full skill directory that should be copied together, not file by file.
Provides example prompts for turning text into an editorial card or requesting HTML only.
Make a portrait 3:4 info card from these notes.
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 the full skill package, not a single file:
Copy or install the entire directory into your agent's skills location. Keep these files together:
SKILL.mdassets/references/scripts/agents/ when supported by the hostAfter 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.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.The same source content is reorganized for each target canvas instead of being mechanically resized. The skill supports 3:4, 4:3, 1:1, 16:9, 9:16, 2.35:1, 3:1, and 5:2.
For PNG capture, the current helper expects local Google Chrome at:
/Applications/Google Chrome.app/Contents/MacOS/Google Chrome
skills/
editorial-card-screenshot/
docs/
examples/
docs/agent-usage.mddocs/editorial-card-prompt.mddocs/content-fit.mddocs/project-overview.mddocs/github-metadata.mdSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.