{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihefp2v3mroudtmf6famuzsnpfu2pbzimctbvj4r35dr3fip25oyy",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mng6viu7rkm2"
  },
  "path": "/t/codex-skill-for-editable-excalidraw-diagrams/1382592#post_1",
  "publishedAt": "2026-06-03T22:32:12.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "github.com",
    "GitHub - fabricioartur/codex-excalidraw-skill",
    "GitHub",
    "fabricioartur - Overview",
    "https://www.linkedin.com/in/fartur/"
  ],
  "textContent": "Hi everyone,\n\nI wanted to share a small original project I built while experimenting with Codex skills:\n\n**codex-excalidraw-skill**\n\ngithub.com\n\n### GitHub - fabricioartur/codex-excalidraw-skill\n\nContribute to fabricioartur/codex-excalidraw-skill development by creating an account on GitHub.\n\nThe idea was to make Codex generate diagrams that are not just static images, but real editable Excalidraw scenes. The skill creates structured `.excalidraw` JSON, SVG/HTML previews, ready-to-open Excalidraw Web links, and local session state so follow-up requests can modify the previous diagram instead of starting from scratch.\n\nI built it because I wanted a workflow closer to an interactive diagramming assistant: ask Codex for a visual, inspect the preview, open it in Excalidraw, and keep iterating. The repository includes the skill instructions, helper scripts, references, examples, and an example tactical diagram rendered in the README.\n\nA few things the skill currently supports:\n\n  * Natural-language requests to editable Excalidraw diagrams\n  * SVG and HTML previews\n  * Open-in-Excalidraw web links\n  * Session-state reuse for incremental edits\n  * Validation checks for unreadable text and broken scene structure\n  * Specialized templates for tactical football rosters and building elevations\n\n\n\nThis is my own implementation, created through hands-on testing and iteration in Codex. I did not copy an existing skill; I used the project as a way to learn how far Codex skills can go for visual, editable artifacts.\n\nI am sharing it here in case it helps other builders thinking about Codex skills, diagram generation, or editable AI-created artifacts.\n\nI would love feedback from the community, especially on:\n\n  * How to make the skill easier for others to install and adapt\n  * Better patterns for preserving manual edits across follow-up requests\n  * Whether this kind of workflow should eventually become a proper MCP/widget integration\n\n\n\nMade by Fabricio Artur.\n\nGitHub\n\n### fabricioartur - Overview\n\nSenior Pre-Sales Engineer | Solutions Architect | Cloud, Security & AI - fabricioartur\n\nhttps://www.linkedin.com/in/fartur/",
  "title": "Codex skill for editable Excalidraw diagrams"
}