fix(prompts): align quality-evaluator.md with new VQ-01 + proportional rules#7392
Merged
Conversation
…l rules quality-evaluator.md is the standalone/offline reviewer (NOT workflow-active — ai-quality-review.md is what impl-review.yml actually invokes). The two prompts had drifted: quality-evaluator.md still demanded "Font sizes explicitly set (not defaults)" while quality-criteria.md (just updated in #7391) now says source-of-values is irrelevant and only the visual result matters. Changes: - Header note clarifies the file's standalone role and points to ai-quality-review.md as the authoritative workflow-active reviewer when the two contradict. - VQ-01 row: dropped the "(not defaults)" constraint, added mobile- readability check. - VQ-05 row: added title-width / overflow guidance. - New "Proportional sizing notes" block under the Visual Quality table: matches the rules in default-style-guide.md, ai-quality-review.md Section 5d, and quality-criteria.md VQ-01 — including the mandated- long-title exception and the "source-of-values irrelevant" principle.
Contributor
There was a problem hiding this comment.
Pull request overview
Aligns the standalone quality-evaluator.md reviewer prompt with the wording changes made to the workflow-active ai-quality-review.md in #7391, so the two rubrics no longer drift on VQ-01 / VQ-05 and proportional sizing.
Changes:
- Adds a header note clarifying that
ai-quality-review.mdis authoritative when the two prompts disagree. - Updates VQ-01 (drops "not defaults", adds mobile readability) and VQ-05 (title width / overflow guidance).
- Adds a "Proportional sizing notes" block matching the style guide and the workflow reviewer.
Merged
1 task
MarkusNeusinger
added a commit
that referenced
this pull request
May 19, 2026
…w VQ-01 philosophy (#7393) ## Summary After #7391/#7392 changed the VQ-01 rubric (source-of-values irrelevant; defaults vs AI-tuned score equally), the example JSON output and example weaknesses in \`quality-evaluator.md\` were still showing the OLD philosophy: - \`vq01_text_legibility\` example note: \"Readable but relying on defaults (font sizes not explicitly set)\" → \"Title slightly oversized for content...\" - \`weaknesses[0]\`: \"Relying on default font sizes instead of explicit settings\" → \"Title at fontsize=18pt squeezes against the right edge\" These examples are the most concrete guidance for the reviewer; if they show old reasoning, the reviewer follows old reasoning regardless of what the rubric tables say. ## Test plan - [ ] CI green 🤖 Generated with [Claude Code](https://claude.com/claude-code)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
quality-evaluator.md is the standalone/offline reviewer (not workflow-active — ai-quality-review.md is what `impl-review.yml` actually invokes). After #7391's wording changes the two prompts drifted on VQ-01.
Changes
Test plan
🤖 Generated with Claude Code