agentleFS
feimacodefeimacode/open-design-agent-kit/.agents/skills/open-design-social-post/SKILL.md

open-design-social-post

Skill678 starsChanged yesterdayMITView on GitHub

Design a social media post (X, Instagram, LinkedIn, Xiaohongshu, Stories/Reels, YouTube thumbnail or video) and export upload-ready files — use whenever the user wants something to post on social media (an X/Twitter image, Instagram or LinkedIn post or carousel, Xiaohongshu cards, a Story/Reels cover, a YouTube thumbnail or video), even if they don't mention Open Design

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the user's own words. If they say "artifact", "design tokens" or give a file path, use those terms back.

    line 13
  2. Very specific:

    Keep the machinery out of replies: no tool names, no ids like od:prototype:poster-hero, no internal files (.artifact.json, .comments.json, …

    line 14
  3. Distinctive:

    If the brief names a platform or format, use it.

    line 33
  4. Distinctive:

    Use real copy from the brief, with no lorem ipsum.

    line 57
  5. Distinctive:

    No external image URLs unless the user supplied them.

    line 58
  6. Distinctive:

    No emoji as key visuals. They render from the exporting machine's fonts and can come out as empty boxes.

    line 59
  7. Very specific:

    Call register_open_design_artifact with the entry path, kind html, a title, sourceSkillId set to the row's skillId, and the same format you …

    line 63
  8. Very specific:

    YouTube video: follow the brief's "Host override" section.

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- generated:open-design-agent-kit -->

Design a social media post with Open Design and export files that are ready to upload.

Brief: the rest of the user's message (if there is none, ask the user: "What should the post say, and for which platform?")

How to talk to the user. Many people using Open Design don't write code, so:

  • Use the user's own words. If they say "artifact", "design tokens" or give a file path, use those terms back; otherwise use the plain words below.
  • Keep the machinery out of replies: no tool names, no ids like od:prototype:poster-hero, no internal files (.artifact.json, .comments.json, config.json), and not the words "register", "manifest", "sidecar", "entry" or "surface", unless the user used them first.
  • Explain a print term the first time it comes up, in one short clause, and not again.
  • Say where a file is the way the user would find it ("in your Open Design folder, under seed-swap-flyer"). Give a raw path only where the user can click it (Claude Code, Claude Desktop's Code tab, VS Code) or asks for it.
  • End each reply that finishes a step with one line on what they can do next, with at most two options ("Want it in Instagram sizes too, or is it ready to print?").
Instead ofSay
artifact, entry, registeredyour design, saved
design system, active design systemyour style (the first time: "a saved style: colours, fonts and spacing")
surface, skill, template, recipekind of design, starting layout, or nothing
workspace, output directoryyour folder, your Open Design folder
bleedprint edge ("a few millimetres extra that the printer trims off")
trim sizefinal size
preflight findings, errors"I checked it and fixed…", "one thing to look at:"
exportsave as PDF, save as an image
inline preview, MCP Appthe preview above

1. Pick the platform and format

If the brief names a platform or format, use it. Otherwise ask the user to pick one of the rows below before doing anything else. Don't guess.

FormatCanvasskillIdExport
X single image1600×900od:prototype:card-twitterpreset: "x-image"
X post mock (for a video overlay or quote)card elementod:prototype:social-x-post-cardselector: "[data-od-card]", maxBytes: 5000000
Square carousel (Instagram / LinkedIn)1080×1080 per cardod:prototype:social-carouselpreset: "ig-square"
Instagram portrait1080×1350od:prototype:poster-heropreset: "ig-portrait"
Story / Reels / TikTok cover1080×1920od:prototype:poster-heropreset: "story"
Xiaohongshu cards1080×1440 per cardod:prototype:card-xiaohongshupreset: "xhs-card"
YouTube thumbnail1280×720od:prototype:social-youtube-thumbnailpreset: "yt-thumbnail"
YouTube video1920×1080 MP4od:video:hyperframesMP4 via the HyperFrames CLI (see step 4)

A preset fills in the canvas size, selector: "[data-od-card]" and the platform's upload limit (X 5 MB, Instagram 8 MB, YouTube thumbnail 2 MB).

For several platforms at once, run steps 2–4 once per format and keep each one as its own artifact.

2. Generate

Call prepare_open_design_brief with the row's skillId, the brief, and format set to the row's preset id (leave it out for the X post mock and YouTube video). Call list_open_design_design_systems first if the user names a brand or visual direction, or recommend_open_design_design_systems if they name none and no design system is active. For the X post mock, say in the brief that it is one card element.

Author the files yourself with your own file-editing tools, following the returned instructions, and add these rules for social posts:

  • Each card or canvas is a fixed-size element at exactly the table's size with overflow: hidden, and carries a data-od-card attribute. For multi-card formats, stack the cards vertically in one HTML file, one data-od-card element per card.
  • Use real copy from the brief, with no lorem ipsum. Keep text inside a 48px safe margin, and make the hook readable at thumbnail size.
  • No external image URLs unless the user supplied them.
  • No emoji as key visuals. They render from the exporting machine's fonts and can come out as empty boxes. Draw icons and subjects as inline SVG.

3. Register

Call register_open_design_artifact with the entry path, kind html, a title, sourceSkillId set to the row's skillId, and the same format you passed to the brief, so the export can find the right size.

4. Export

  • Image formats: call export_open_design_artifact with the entry path and the row's export arguments. If its preflight reports errors (text cut off, a card that isn't the canvas size) or it returns warnings (failed fonts or images, over budget), fix the artifact and export again. Before exporting, call check_open_design_artifact to see the post as an image with its preflight findings, without writing files; fix every error first.
  • YouTube video: follow the brief's "Host override" section. Render with npx hyperframes render … --output <artifact-dir>/exports/<name>.mp4, and check ffmpeg -version first.

5. Report

List each exported file's path, pixel size, and file size, and remind the user of the post's copy (caption and hashtags) if you wrote any. Don't post anything anywhere yourself.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.