Skip to content

The design language that makes your AI harness better at design.

JavaScript

Scope the verify ceiling to new-work builds (#1049)

Paul Bakaus7a07ce2c379e
diff --git a/skill/SKILL.src.md b/skill/SKILL.src.md
index 12969d39b..9b703a148 100644
--- a/skill/SKILL.src.md
+++ b/skill/SKILL.src.md
@@ -14,7 +14,7 @@ This skill gives you the tools and permission to make design that earns the name
Core principles:
- Finish the job. No hedging, no shortcuts: the deliverable is complete, except assets the user must provide.
- Scale ambition to the surface's mode (see Modes). Persuade and Experience get full commitment: bold, distinct work with a point of view. On Operate and Read, ambition shows as precision and restraint, and patterns the visitor already knows earn their place.
-- Verify in bounded passes, not a loop, and the ceiling covers the whole cycle: screenshots, defect scans, micro-edits, and rebuilds alike. Build fully, inspect once with a batched round (desktop and mobile together on the web; the shipped device classes on a native platform), fix everything it shows in one batch, confirm with at most one more round, and stop polishing. Open-ended self-QA burns the user's money doing worse what the finish handoffs do better.
+- Verify by looking at the rendered result at the sizes it ships at, and batch the checks: fix what one look shows before looking again, rather than screenshotting after every tweak.
## Setup
diff --git a/skill/reference/craft-floor.md b/skill/reference/craft-floor.md
index 0252f5b9c..30b63c7b3 100644
--- a/skill/reference/craft-floor.md
+++ b/skill/reference/craft-floor.md
@@ -4,7 +4,7 @@ Load this after the direction is settled, and build without announcing the check
## Verify
-Each of these is a check on the built result, not an intention. Run them together in the batched inspection rounds, not as separate screenshot trips; the checks share one render.
+Each of these is a check on the built result, not an intention. Run them together in each batched look at the render, not as separate screenshot trips; the checks share one render.
- **Contrast:** body and placeholder text ≥4.5:1, large text ≥3:1. On colored surfaces tint secondary text from that hue or the foreground; never gray. <!-- rule:skill-color-verify-contrast -->
- **Depth:** shadows carry an offset and a soft blur. A zero-offset colored halo is decoration. <!-- rule:skill-color-no-glow-halo -->
diff --git a/skill/reference/new-work.md b/skill/reference/new-work.md
index 44abb022a..a778bd6a4 100644
--- a/skill/reference/new-work.md
+++ b/skill/reference/new-work.md
@@ -137,7 +137,7 @@ Preserve semantics, accessibility, performance, responsiveness, project conventi
## 7. Inspect and finish
-Inspect the surface's target sizes in one batched screenshot round: desktop and mobile on the web; on a native platform (`ios` / `android` / `adaptive`), the shipped device classes per OS, captured from the simulator or emulator the way the platform reference's Verifying the build section describes. When the harness reports the user's actual viewport (an in-app browser's size, a named resolution), add that width to the set: the width that breaks is the one the user sees first. Critique the render against the user's request and the direction contract, fix material gaps, and confirm with one final round; two rounds is the ceiling, and fixes batch between them rather than earning per-tweak screenshots. The ceiling bounds inspection and never closes an open build-phase gate: a gate stays open until it passes or the route it names is taken. On a comp-led build, run `{{scripts_path}}/impeccable comp-diff --comp <approved comp> --build .impeccable/review/desktop.png --spec .impeccable/build/spec.json --out-dir .impeccable/review/diff/final` and read its region rows and paired crops as the critique: the side-by-side is the view the build thread never has on its own, and a region it scores missing or contradicted is a fix whatever the page looks like from memory. Never judge fidelity from one full-page thumbnail; it hides exactly the failures that matter. On a Persuade surface, verify the mode did its job: a first-time visitor should know what this is, why it matters, and what to do within seconds, in the form's own vocabulary.
+Inspect the surface's target sizes in one batched screenshot round: desktop and mobile on the web; on a native platform (`ios` / `android` / `adaptive`), the shipped device classes per OS, captured from the simulator or emulator the way the platform reference's Verifying the build section describes. When the harness reports the user's actual viewport (an in-app browser's size, a named resolution), add that width to the set: the width that breaks is the one the user sees first. On anything interactive, the round drives every interaction and reachable state (open, closed, hover, focus, error, empty, overlong content) and checks each for overlap and clipping, not only the resting screen. Critique the render against the user's request and the direction contract, fix material gaps, and confirm with one final round; two rounds is the ceiling, and fixes batch between them rather than earning per-tweak screenshots. The ceiling bounds inspection and never closes an open build-phase gate: a gate stays open until it passes or the route it names is taken. On a comp-led build, run `{{scripts_path}}/impeccable comp-diff --comp <approved comp> --build .impeccable/review/desktop.png --spec .impeccable/build/spec.json --out-dir .impeccable/review/diff/final` and read its region rows and paired crops as the critique: the side-by-side is the view the build thread never has on its own, and a region it scores missing or contradicted is a fix whatever the page looks like from memory. Never judge fidelity from one full-page thumbnail; it hides exactly the failures that matter. On a Persuade surface, verify the mode did its job: a first-time visitor should know what this is, why it matters, and what to do within seconds, in the form's own vocabulary.
A capture is evidence only when it is valid, and you validate before you send. Settle or disable entrance motion first: an element hidden by animation timing reads as a missing element and gets fixed into a regression. Capture full-page shots from the document top. Capture the comp comparison at the comp's own pixel dimensions. Then open every file once and confirm it shows what its name claims: no black or blank regions, no wrong section behind a right filename, no half-loaded state. A malformed capture sent onward costs the whole round; the reviewer answers it with `disposition: recapture` and nothing it reviewed binds. <!-- rule:skill-capture-validity -->
diff --git a/skill/reference/overdrive.md b/skill/reference/overdrive.md
index 9942b853a..25e509f86 100644
--- a/skill/reference/overdrive.md
+++ b/skill/reference/overdrive.md
@@ -21,7 +21,7 @@ Skipping this step risks building something embarrassing that needs to be thrown
### Verify in the Browser
-Ambitious effects rarely work on the first try, so verify them in the browser rather than from code: an effect that technically runs can still stutter, ease wrong, or land on the wrong frame. SKILL.md's bounded passes apply: one batched inspection, one fix batch, at most one confirming round. Point them at the effect's timing, easing, and smoothness, then stop and name what still falls short instead of opening another round.
+Ambitious effects rarely work on the first try, so verify them in the browser rather than from code: an effect that technically runs can still stutter, ease wrong, or land on the wrong frame. Aim the checks at timing, easing, and smoothness, batch the fixes between looks, and keep refining until the effect is extraordinary.
---