mockup
Skill0 starsChanged 3 months agoMITView on GitHub
Produce design drafts for approval - Paper canvas first, Claude artifact fallback, gitignored design-drafts/ HTML last resort. Use for the design-approval step of the checklist, when the user asks for design drafts or to "mock it up", or via /mockup. Args - optional screen/feature to mock.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- ptrandev/claude-skillstheir own version, first seen Oct 29, 2026
- ieuanign/skillstheir own version, first seen Oct 13, 2026
- OHOKAYYEAH/claude-skillstheir own version, first seen Oct 13, 2026
- AI-Driven-School/aikitheir own version, first seen Feb 23, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- ieuanign/skills★ 2same name
- OHOKAYYEAH/claude-skills★ 1same name
- ptrandev/claude-skills★ 1same name
- AI-Driven-School/aiki★ 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 repository7 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- grillSkill
- kickoffSkill
- new-gtm-toolSkill
- nextSkill
- refine-prdSkill
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 3 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
- Very specific: line 13
Paper (default): Use the Paper MCP tools (Paper Desktop serves them at http://127.0.0.1:29979/mcp while a file is open.
- Very specific: line 21
Claude artifact: Write the page to the session scratch directory (never the repo), variant tabs (A/B/C) for competing directions, publish …
- Distinctive: line 30
Every tier respects every UI rule: ink actions, green data, mono numerals, sentence case, no sparkles, no emojis, quiet motion, …
“Common” is measured: kept by at least 6 in 10 of the 3 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
Mockup (design drafts)
Produce the design-approval drafts per standards/ui-ux.md ("Mockups"). Work the hierarchy top down, fall back only on real failure, and tell the user which tier you used and why:
- Paper (default). Use the Paper MCP tools (Paper Desktop serves them at
http://127.0.0.1:29979/mcpwhile a file is open; load via ToolSearch if deferred). Build the key screens from the locked PRD as frames on the canvas, in the house tokens (standards/ui-ux.md/hero.ts), with real-feeling data, light + dark. Each competing direction is its own named frame set, so the user flips between drafts inside Paper. If the tools are absent, the app is not running, or calls fail (free tier: 100 MCP calls/week), say so and drop to tier 2. - Claude artifact. Write the page to the session scratch directory (never the repo), variant tabs (A/B/C) for competing directions, publish as a private artifact, share the link, iterate by republishing the SAME file path (same link, version history preserved).
- Static HTML in the repo (last resort). One plain HTML file per
direction in
design-drafts/at the repo root. Verifydesign-drafts/is in .gitignore before writing (add it if missing); drafts must never reach git history. The user opens the files in a browser.
Every tier respects every UI rule: ink actions, green data, mono numerals, sentence case, no sparkles, no emojis, quiet motion, cursor-pointer.
On approval: record the chosen direction in prd.md, set
Stage: mockup-approved, and offer to start the build loop (first unchecked
feature in tasks.md). The approved draft stays as the design reference;
nothing is ever committed.
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.

