← ClaudeAtlas

design-quorumlisted

Adversarial review of a UI, chart, dashboard, or published page before anyone relies on it - lenses for misreading, degradation, comprehension, craft, and data integrity, because design failures are exactly the class the person who built the thing cannot see. Trigger on "review this design", "review the chart", "before this ships", "does this mislead", "design review", "UI review", "check this dashboard", "is this chart honest".
Lukehle/claude-quorum · ★ 0 · Web & Frontend · score 70
Install: claude install-skill Lukehle/claude-quorum
# Design quorum Design failures are the hardest class to self-review: **you know what the chart means, so you cannot experience misreading it.** A checklist catches what you remembered to look for. It does not catch "a reader draws the opposite conclusion from this axis." This adapter seats lenses that hunt exactly that. --- ## When to run it | Run it | Skip it | |---|---| | Before a chart or page goes to a board, investor, client, or the public | Exploratory views nobody will act on | | Before publishing anything that distributes | Formatting-only changes | | When the visual is technically fine but feels generic | Work already reviewed and unchanged since | | When a number on the page will be quoted | | Run the mechanical checklist **first** (`artifact-testing` in the chartroom pack, or your own), then this. They catch different things: the checklist catches omissions, the quorum catches misreads. --- ## The lenses Five, coined for visual work. Drop any that does not apply; add subject-specific ones. ### 1. Misread adversary > *"Show me a competent reader reaching a wrong conclusion from this."* Hunts: truncated axes on additive measures, dual axes implying a relationship, inconsistent series colours across charts, a smoothed line through discrete periods, a definition change with no visible break, "other" larger than the smallest named category, percentage without base, area encoding read as linear. The strongest single lens here. Most charts that mislead do so