visualizer
Skill0 starsChanged 5 months agoMITView on GitHub
Generate live, self-contained HTML previews of UI and diagrams that consume the project's TOKENS.css (zero hardcoded hex, no CDN, all states, labeled placeholders). For 03 (UX/UI), 05 (Data Modeler), 06 (Frontend) and 08 (QA).
3 other projects use a version of this.
Adopted by
Most recently taken up by
- MAGA2010/data-mastertheir own version, first seen Oct 25, 2026
- Practice019/agent-skillstheir own version, first seen Sep 9, 2026
- AlexZWANG1/Augurtheir own version, first seen May 9, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- MAGA2010/data-master★ 78same name
- AlexZWANG1/Augur★ 0same name
- Practice019/agent-skills★ 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 repository20 other files it gives its agents.
- docs/AGENTS.mdAGENTS.md
- adopt-groundSkill
- agent-authoringSkill
- architecture-decisionSkill
- asset-sourcingSkill
- brand-evaluation-rubricSkill
- criticSkill
- data-integritySkill
- diagrams-gateSkill
- drift-protocolSkill
- env-reproducibleSkill
- orchestrator-bridgeSkill
- project-cleanupSkill
- qa-eyesSkill
- qa-visual-criteriaSkill
- research-methodologySkill
- security-auditSkill
- setupSkill
- smoke-testSkill
- technical-documentationSkill
The file
Files
SKILL: visualizer
For: Agents 03 (UX/UI) · 05 (Data Modeler) · 06 (Frontend) · 08 (QA)
Version: 1.0.0
Purpose
Generate live previews of UI and diagrams to validate the design before and during the build. Produces a self-contained, runnable HTML PREVIEW of a component, layout or diagram that consumes the project's TOKENS.css.
Hard rules
ALWAYS USE:
✓ var(--<prefix>-*) for every visual value — ZERO hardcoded hex
✓ Local fonts and assets — NO CDN (P-02), the preview runs offline
✓ ALL relevant states: default / active / disabled / error
✓ Motion where it matters (e.g. needle ballistics)
✓ Every sample datum LABELED as placeholder (P-11) — never appearing to be real
NEVER:
× Hex colors or other literals instead of var(--<prefix>-*)
× CDN resources (breaks P-02 and the offline preview)
× A single state when the component has several
× Sample data sold as real (P-11 defect)
When they use it
03 UX/UI → visual directions and components 05 DATA MODELER → data diagrams (mermaid / ER) 06 FRONTEND → UI preview 08 QA → visual gate inspection
Output
An .html file in the project's docs/ or previews/.
Self-contained: opens and runs with no server or network, consuming the project's TOKENS.css.
Verification
STEP 1 — Open the .html (or take a screenshot).
STEP 2 — Confirm the var(--<prefix>-*) tokens resolve (nothing unstyled or fallback-colored).
STEP 3 — Confirm ZERO console errors.
STEP 4 — Confirm each declared state shows, and every placeholder is labeled (P-11).
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.