design-doctor
Skill0 starsChanged 49 days agoMITView on GitHub
Health check and map of the whole design toolkit (graphic design, illustration, photo, UI, typography, print, Blender 3D, video editing, screen recording) and its container images. Use when the user asks what design tools are available, whether everything works, which tool or skill fits a creative task, why a design tool misbehaves, or wants to know what to install or pull.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- codeonym-org/codeonym-arch-designedited, first seen Sep 25, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- codeonym-org/codeonym-arch-design★ 033% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- 3d-modelingSkill
- design-sandboxSkill
- graphic-designSkill
- illustrationSkill
- photo-editingSkill
- print-layoutSkill
- screen-recordingSkill
- typographySkill
- ui-designSkill
- video-editingSkill
The file
Files
Design doctor
Run it
bash <skill-dir>/scripts/doctor.sh # one-screen summary
bash <skill-dir>/scripts/doctor.sh --verbose # every check in detail, with install commandsIt reports the runtime (Docker / Podman / native), which images are pulled, then runs every skill's check script in the
right place. It never pulls an image by itself — checks whose image is missing say skipped — ds pull core|full.
In native mode it also flags PATH shadowing (e.g. Homebrew tools hiding the distro's ffmpeg/perl/python3).
Which skill for which job
| I want to… | Skill | Main tools | Image |
| Logo, banner, social post, thumbnail, icon; batch resize/convert/compress images | graphic-design | Inkscape, ImageMagick, optimizers (GIMP, G'MIC) | core |
| Draw, paint, concept art, comics; Krita canvases and batch export | illustration | Krita | full |
| Develop / grade / batch photos, strip GPS, web-ready photos | photo-editing | darktable, exiftool, ImageMagick | core (+full for darktable) |
| Mockups, design system tokens, favicons & app icons, color palettes | ui-design | Penpot/Figma/Lunacy, Inkscape | core |
| Choose/pair fonts, specimens, project fonts, web fonts | typography | fontconfig, FontForge, woff2 | core |
| Flyer, poster, brochure, business card, print-ready PDF, preflight | print-layout | Scribus, Ghostscript, Poppler | core (+full for Scribus) |
| 3D models, design mockups, renders, turntables, GLB for the web, 3D print | 3d-modeling | Blender | full |
| Edit/encode videos, loudness, GIFs, thumbnails, render Kdenlive projects | video-editing | ffmpeg, melt | core (+full for melt) |
| Record tutorials/demos, OBS setup, keystrokes, zoom effects | screen-recording | OBS (desktop), ffmpeg | host + core |
| Set up / understand / troubleshoot the container itself | design-sandbox | ds, Docker/Podman | — |
Cross-skill pipelines
- Brand kit:
typography(pick fonts) →ui-design/palette.sh(colors) →graphic-design(logo SVG,graphic-design/svg-export.sh) →ui-design/icon-set.sh(favicons) →print-layout(business card) →3d-modeling/mockup.py(presentation shots). - Tutorial video:
screen-recording(record,screen-recording/finish-recording.sh) →video-editing(edit,video-editing/encode.sh) →video-editing/thumbs.sh+graphic-design(thumbnail) →video-editing/gif.sh(README loop). - Portfolio piece:
3d-modeling/turntable.pyor3d-modeling/mockup.py→3d-modeling/render.sh --anim→video-editing/encode.sh web→graphic-design/optimize.shfor stills.
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
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.