manzanas: Skill for Claude Code

UI audit + predicates: stop hand-parsing trees

Two tools replace manual tree/screenshot inspection during QA:

1. audit — deterministic geometry checks over the accessibility tree, returning findings (measured evidence, never pass/fail verdicts) plus an annotated screenshot with a labeled red box per finding. Both are journaled automatically.
2. Predicates — strict element matching for tap_element, type_into_element, wait_for_element, scroll_to_element. A predicate must resolve to exactly one element; ambiguity fails loudly with every candidate listed instead of silently guessing.

Audit a screen

manzanas audit --lease $LID -o annotated.png            # all six checks
manzanas audit --lease $LID --checks touch_target,missing_labels
manzanas audit --lease $LID --label "Sign up"           # scope to one subtree
manzanas audit --lease $LID --region 0,0,393,400        # scope to a screen area

MCP agents call the audit tool with the same fields (checks, region, matcher fields, min_touch_pt, alignment_tolerance_pt, spacing_tolerance_pt, safe_area_insets).

Checks: touch_target (< 44x44pt interactive), clipping (past screen or non-scrolling parent bounds), alignment (near-miss edge deltas ≤ 4pt), spacing (sibling gaps deviating > 4pt from the median), safe_area (interactive elements in the insets), missing_labels (interactive elements a screen reader cannot name).

Reading results:

• Each finding has check, ref (F1, F2, ... — matches the red box on the annotated screenshot), the element's role/label/id/frame, measured values, and an evidence sentence.
• Findings are EVIDENCE, not verdicts. You decide what matters: a 30x30 close button is probably a real defect; a deliberately compact stepper may not be.
• Dense repeated grids (keyboards, emoji pickers, calendar cells) are auto-suppressed; suppressed_elements reports how many.
• System chrome is auto-suppressed too: scroll-indicator pseudo-elements, the status bar, and the keyboard never produce findings by default (--include-system-chrome restores them; individual keyboard keys stay under the dense-group rule), and touch_target withholds small controls covered by a full-size tappable list row (Cell or Button) — stock Settings' ~28pt row buttons — reported as suppressed_covered_controls (--include-covered-controls restores them). So a noisy stock-app screen audits clean; remaining findings are the app's own layout.
• Both artifacts land in the journal: manzanas journal export $LID -o evidence.md includes them — paste into the PR.