Skip to content

Design Audit Method ​

The shared method behind OnRamp's two design-audit skills. Both reference this page rather than restating it:

  • /design-handoff-eval — audits freshly generated handoff output for drift from the design system (static, runs right after /design-build).
  • /design-critique — a design panel's critique of an established, rendered experience from the customer's side, graded by customer impact.

They differ in subject and altitude. Both follow the evidence rule below; the forbidden-pattern sweep and report conventions are handoff-eval's, and critique defers the sweep to it. The design-system prohibitions themselves live in Forbidden Patterns; the compositional standard lives in UI Conventions.

Evidence rule ​

Every count, ratio, contrast value, and "none found" claim in any section of an audit report MUST cite a line of output from a command run in that report's mechanical-evidence pass. If you did not run the command or probe, you may not state the result. Do not estimate from reading code.

This exists because an LLM self-audit overstates compliance — the original handoff audit reported "no custom components" when 16 existed, because it read a few files instead of counting. Each skill records the raw output of every command it ran — handoff-eval in an opening Section 0 mechanical evidence block of static find/grep inventory, critique in an evidence appendix beside its walkthrough captures — and every count traces to a line in it. Critique's judgment findings cite a moment in the walk instead; the rule binds its numbers, not its judgment.

Forbidden-pattern sweep ​

For each **Pattern:** regex in Forbidden Patterns, run grep -rnE '<regex>' <target> and paste the output. Source the regexes from that canonical doc — never retype them here or in a skill. 0 matches is a valid and required per-pattern result, not an omission.

Report conventions ​

  • Evidence-first. Per the evidence rule above — if a number isn't backed by pasted command output, it doesn't go in the report.
  • Direct, no hedging. Findings are facts; recommendations are concise and actionable (a concrete fix, not "improve hierarchy").
  • File paths in backticks; line numbers prefixed L (e.g. Foo.vue:L42). Snippets capped at ~80 chars.
  • Severity tiers: 🔴 critical · 🟠 medium · 🟡 polish. (Where each skill applies them — flat lists vs. a ranked table — is the skill's own call.)
  • Effort tiers: LOW single-file mechanical · MED single-component restructure · HIGH cross-cutting refactor.

Internal documentation — gated behind Cloudflare Access.