squig
Skill0 starsChanged 2 days agoLicence not identifiedView on GitHub
Wireframe page and app structure with Squig (squig.sh) — Pablo Stanley's free, MIT-licensed, agent-native wireframing canvas where 155 real UI components (the shadcn/ui vocabulary plus marketing blocks, app blocks, mobile screens and full templates) render as hand-drawn rough.js sketches, driven by an agent through window.squig in the open browser tab, a local CLI, or a local MCP/HTTP companion that owns one .squig.json file and renders PNG/SVG back for inspection. It produces structure (geometry, component props, named side-by-side variations), never production React code. Key trap — it is NOT installable the usual ways: there is no npm package (npx squig 404s), no shadcn registry (/r/*.json 404s), no install script, and the hosted https://squig.sh/mcp endpoint is retired (HTTP 410); local agent use needs a persistent git clone built with Node 24+ and pnpm 10. Use this whenever someone says "wireframe this", "sketch the layout", "lo-fi mockup", "napkin sketch", "block out the page", "show me three layout directions", "compare layouts side by side", "what goes where before we pick colors", "information architecture for this page", or names squig, squig.sh or a .squig.json file; whenever design work starts on a new page or app and the structure is not yet decided (design-arsenal's Structure phase, between Direction and Identity); and whenever a chosen wireframe must be handed off to shadcn components — the kind-to-`npx shadcn add` table and the CLI/HTTP/MCP recipes live in references/integration.md.
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- musterd-io/musterdtheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- musterd-io/musterd★ 1same 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 repository34 other files it gives its agents.
- skills/react-best-practices/AGENTS.mdAGENTS.md
- arc-uiSkill
- audiocnSkill
- bestfreefontsSkill
- brandkitSkill
- industrial-brutalist-uiSkill
- componentrySkill
- cosmosSkill
- design-arsenalSkill
- fffuelSkill
- frontend-designSkill
- gauge-uiSkill
- haikeiSkill
- iconographySkill
- jitterSkill
- logoaiSkill
- logosystemSkill
- mdxcnSkill
- minimalist-uiSkill
- motion-primitivesSkill
- motionsitesSkill
- full-output-enforcementSkill
- pafoliosSkill
- peleSkill
- vercel-react-best-practicesSkill
- recent-designSkill
- redesign-existing-projectsSkill
- shadcnSkill
- high-end-visual-designSkill
- splineSkill
- supaheroSkill
- uicolorsSkill
- ui-ux-pro-maxSkill
- uppbeatSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
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.

