variants
Skill43 starsChanged 23 days agoMITView on GitHub
Three directions side by side for any design ask, with the Art Director's notes on each and no polish. Use when you want to see the options before committing, or to pick a direction yourself.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- Devolutions/IronRDPtheir own version, first seen Nov 1, 2026
- harshil-1411/claude_plugin_video_studiotheir own version, first seen Oct 17, 2026
- Pawel-Kica/ai-coding-100their own version, first seen Oct 8, 2026
- Pawel-Kica/claude-code-100their own version, first seen Sep 12, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- Devolutions/IronRDP★ 3.3ksame name
- Pawel-Kica/ai-coding-100★ 2same name
- Pawel-Kica/claude-code-100★ 2same name
- harshil-1411/claude_plugin_video_studio★ 0same name
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 repository25 other files it gives its agents.
- adapters/agents.mdAGENTS.md
- accessibility-auditSkill
- brand-kitSkill
- chart-designSkill
- dashboard-layoutSkill
- dashboardSkill
- design-critiqueSkill
- design-handoffSkill
- design-qaSkill
- design-reviewSkill
- designSkill
- design-systemSkill
- design-templateSkill
- studioSkill
- email-campaignSkill
- email-templateSkill
- helpSkill
- initSkill
- motion-designSkill
- presentation-designSkill
- social-campaignSkill
- social-contentSkill
- statusSkill
- tasteSkill
- videoSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Run the roughs step on its own as the Design Manager.
- Very specific: line 29
Run: Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above.
- Very specific: line 31
Run steps 0 to 3 as written, then only the Roughs part of step 4, rendered with screenshots.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Run the roughs step on its own as the Design Manager.
Deliverable and standard. Three roughs of whatever the ask is, each in a different composition pattern from the deliverable's standard, laid out side by side with notes. The standard is the one that matches the ask (card, carousel, landing page, email, deck, chart, dashboard, clip, icon set, print piece). No polish, no proof gate, no sign-off: these are directions, not finished files.
Desks.
| Desk | Agent | Tier | Does |
| the deliverable's builder desk | per the standard: desk:ui-designer, desk:social-media-designer, desk:email-designer, desk:data-viz-designer, desk:motion-designer, desk:presentation-designer, desk:landing-page-designer, desk:dashboard-architect, desk:icon-designer, desk:print-designer | senior (roughs run at the senior model) | one rough each, in parallel |
| Art Director | desk:art-director | director | notes per rough: what works, what fails, what it would take, and a recommendation without applying it |
Inputs. Text, a file to draw from, a URL, a screenshot, the same as design.
Proof sizes. The standard's default sizes. Proof renders screenshots only, no checks.
Output under .desk/out/<id>/:
rough-1.html,rough-2.html,rough-3.html(up to--count), each named for its pattern in a comment on line one.compare.html: the roughs side by side at each size with the pattern name and the Art Director's notes under each.compare.md: the notes and the recommendation in text.renders/per rough.
Run. Read ${CLAUDE_PLUGIN_ROOT}/skills/desk/SKILL.md now and follow it from step 0 to step 7 as the Design Manager with the desks above. Command name for state and events: variants. Changes to the loop for this command:
- Run steps 0 to 3 as written, then only the Roughs part of step 4, rendered with screenshots. The Art Director writes notes and a recommendation but no
final.htmlis made andpickin state records{ "by": "none" }. - Skip polish, proof checks and sign-off.
scoresstays empty. The handback's Scores line readsnot scored, variants onlyand the Open line says how to continue:/desk:designwith the chosen rough's path as the input. --countabove 3 spawns more roughs, each in a further pattern, and the standard has five.
The ask: $ARGUMENTS
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.