feat: show screenshots to user during QA and browse sessions (v0.5.0.1) (#129)

Add rule 11 to QA and Design methodologies in gen-skill-docs.ts
instructing Claude to Read screenshot PNGs after taking them.
This makes screenshots visible as clickable elements in Conductor
and other Claude Code UIs. Also added to browse and gstack SKILL
templates.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-17 10:30:19 -05:00
committed by GitHub
parent c8c2cbba33
commit 5f41cd9ad7
11 changed files with 23 additions and 3 deletions
+6
View File
@@ -1,5 +1,11 @@
# Changelog
## 0.5.0.1 — 2026-03-17
### Fixed
- **Screenshots are now visible during QA and browse sessions.** When gstack takes screenshots, they now show up as clickable image elements in your output — no more invisible `/tmp/browse-screenshot.png` paths you can't see. Works in `/qa`, `/qa-only`, `/plan-design-review`, `/qa-design-review`, `/browse`, and `/gstack`.
## 0.5.0 — 2026-03-16
- **Your site just got a design review.** `/plan-design-review` opens your site and reviews it like a senior product designer — typography, spacing, hierarchy, color, responsive, interactions, and AI slop detection. Get letter grades (A-F) per category, a dual headline "Design Score" + "AI Slop Score", and a structured first impression that doesn't pull punches.
+1
View File
@@ -111,6 +111,7 @@ If `NEEDS_SETUP`:
- NEVER use `mcp__claude-in-chrome__*` tools. They are slow and unreliable.
- Browser persists between calls — cookies, login sessions, and tabs carry over.
- Dialogs (alert/confirm/prompt) are auto-accepted by default — no browser lockup.
- **Show screenshots:** After `$B screenshot`, `$B snapshot -a -o`, or `$B responsive`, always use the Read tool on the output PNG(s) so the user can see them. Without this, screenshots are invisible.
## QA Workflows
+1
View File
@@ -29,6 +29,7 @@ Auto-shuts down after 30 min idle. State persists between calls (cookies, tabs,
- NEVER use `mcp__claude-in-chrome__*` tools. They are slow and unreliable.
- Browser persists between calls — cookies, login sessions, and tabs carry over.
- Dialogs (alert/confirm/prompt) are auto-accepted by default — no browser lockup.
- **Show screenshots:** After `$B screenshot`, `$B snapshot -a -o`, or `$B responsive`, always use the Read tool on the output PNG(s) so the user can see them. Without this, screenshots are invisible.
## QA Workflows
+1 -1
View File
@@ -1 +1 @@
0.5.0
0.5.0.1
+3
View File
@@ -184,6 +184,9 @@ $B snapshot -D # verify deletion happened
$B diff https://staging.app.com https://prod.app.com
```
### 11. Show screenshots to the user
After `$B screenshot`, `$B snapshot -a -o`, or `$B responsive`, always use the Read tool on the output PNG(s) so the user can see them. Without this, screenshots are invisible.
## Snapshot Flags
The snapshot is your primary tool for understanding and interacting with pages.
+3
View File
@@ -102,6 +102,9 @@ $B snapshot -D # verify deletion happened
$B diff https://staging.app.com https://prod.app.com
```
### 11. Show screenshots to the user
After `$B screenshot`, `$B snapshot -a -o`, or `$B responsive`, always use the Read tool on the output PNG(s) so the user can see them. Without this, screenshots are invisible.
## Snapshot Flags
{{SNAPSHOT_FLAGS}}
+1
View File
@@ -465,6 +465,7 @@ Tie everything to user goals and product objectives. Always suggest specific imp
8. **Responsive is design, not just "not broken."** A stacked desktop layout on mobile is not responsive design — it's lazy. Evaluate whether the mobile layout makes *design* sense.
9. **Document incrementally.** Write each finding to the report as you find it. Don't batch.
10. **Depth over breadth.** 5-10 well-documented findings with screenshots and specific suggestions > 20 vague observations.
11. **Show screenshots to the user.** After every `$B screenshot`, `$B snapshot -a -o`, or `$B responsive` command, use the Read tool on the output file(s) so the user can see them inline. For `responsive` (3 files), Read all three. This is critical — without it, screenshots are invisible to the user.
---
+1
View File
@@ -477,6 +477,7 @@ Tie everything to user goals and product objectives. Always suggest specific imp
8. **Responsive is design, not just "not broken."** A stacked desktop layout on mobile is not responsive design — it's lazy. Evaluate whether the mobile layout makes *design* sense.
9. **Document incrementally.** Write each finding to the report as you find it. Don't batch.
10. **Depth over breadth.** 5-10 well-documented findings with screenshots and specific suggestions > 20 vague observations.
11. **Show screenshots to the user.** After every `$B screenshot`, `$B snapshot -a -o`, or `$B responsive` command, use the Read tool on the output file(s) so the user can see them inline. For `responsive` (3 files), Read all three. This is critical — without it, screenshots are invisible to the user.
Record baseline design score and AI slop score at end of Phase 6.
+1
View File
@@ -415,6 +415,7 @@ Minimum 0 per category.
8. **Depth over breadth.** 5-10 well-documented issues with evidence > 20 vague descriptions.
9. **Never delete output files.** Screenshots and reports accumulate — that's intentional.
10. **Use `snapshot -C` for tricky UIs.** Finds clickable divs that the accessibility tree misses.
11. **Show screenshots to the user.** After every `$B screenshot`, `$B snapshot -a -o`, or `$B responsive` command, use the Read tool on the output file(s) so the user can see them inline. For `responsive` (3 files), Read all three. This is critical — without it, screenshots are invisible to the user.
---
+1
View File
@@ -454,6 +454,7 @@ Minimum 0 per category.
8. **Depth over breadth.** 5-10 well-documented issues with evidence > 20 vague descriptions.
9. **Never delete output files.** Screenshots and reports accumulate — that's intentional.
10. **Use `snapshot -C` for tricky UIs.** Finds clickable divs that the accessibility tree misses.
11. **Show screenshots to the user.** After every `$B screenshot`, `$B snapshot -a -o`, or `$B responsive` command, use the Read tool on the output file(s) so the user can see them inline. For `responsive` (3 files), Read all three. This is critical — without it, screenshots are invisible to the user.
Record baseline health score at end of Phase 6.
+4 -2
View File
@@ -476,7 +476,8 @@ Minimum 0 per category.
7. **Test like a user.** Use realistic data. Walk through complete workflows end-to-end.
8. **Depth over breadth.** 5-10 well-documented issues with evidence > 20 vague descriptions.
9. **Never delete output files.** Screenshots and reports accumulate — that's intentional.
10. **Use \`snapshot -C\` for tricky UIs.** Finds clickable divs that the accessibility tree misses.`;
10. **Use \`snapshot -C\` for tricky UIs.** Finds clickable divs that the accessibility tree misses.
11. **Show screenshots to the user.** After every \`$B screenshot\`, \`$B snapshot -a -o\`, or \`$B responsive\` command, use the Read tool on the output file(s) so the user can see them inline. For \`responsive\` (3 files), Read all three. This is critical — without it, screenshots are invisible to the user.`;
}
function generateDesignMethodology(): string {
@@ -809,7 +810,8 @@ Tie everything to user goals and product objectives. Always suggest specific imp
7. **Use \`snapshot -C\` for tricky UIs.** Finds clickable divs that the accessibility tree misses.
8. **Responsive is design, not just "not broken."** A stacked desktop layout on mobile is not responsive design — it's lazy. Evaluate whether the mobile layout makes *design* sense.
9. **Document incrementally.** Write each finding to the report as you find it. Don't batch.
10. **Depth over breadth.** 5-10 well-documented findings with screenshots and specific suggestions > 20 vague observations.`;
10. **Depth over breadth.** 5-10 well-documented findings with screenshots and specific suggestions > 20 vague observations.
11. **Show screenshots to the user.** After every \`$B screenshot\`, \`$B snapshot -a -o\`, or \`$B responsive\` command, use the Read tool on the output file(s) so the user can see them inline. For \`responsive\` (3 files), Read all three. This is critical — without it, screenshots are invisible to the user.`;
}
const RESOLVERS: Record<string, () => string> = {