# screenshot-reviewer

Checks synthesized task lists against screenshots and analysis files, exposing gaps, contradictions, and unclear acceptance details before implementation.

- subagent · `type=agent` · Claude Code · 454 installs
- Author: davila7
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/ui-analysis/screenshot-reviewer.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/agents/screenshot-reviewer

## What it does

This subagent compares a completed task list with the original screenshots and JSON analysis files. It checks whether visible interface elements, user actions, business functions, empty states, errors, and loading behavior are represented. It also looks for features that have no corresponding tasks.

The review covers terminology, task detail, hierarchy, conflicting requirements, acceptance criteria, dependencies, priority, and ambiguity. It works with `Read`, `Write`, and `TodoWrite`, then produces a Markdown-style review with findings and specific revisions. Without the source screenshots and JSON analyses, it cannot verify the list against the reference material.

## Install

### Claude Code (native platform)

1. **claude-code-templates**
```bash
npx claude-code-templates@latest --agent ui-analysis/screenshot-reviewer
```

2. **Manually: put the files in place**
- File: `.claude/agents/screenshot-reviewer.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/screenshot-reviewer.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/screenshot-reviewer.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/davila7/claude-code-templates/tree/HEAD/cli-tool/components/agents/ui-analysis/screenshot-reviewer.md

## When to use it
- compare tasks with source screenshots
- spot missing interface states
- find conflicting requirements
- check acceptance criteria and dependencies
- suggest concrete task-list fixes

## Example prompts
- Review this task list against the source screenshots and JSON analyses.
- Find missing states, conflicting requirements, and unclear acceptance criteria.
- Write the review report and propose specific corrections.

## Similar
- [code-reviewer](https://affpapa.org/en/nevibecode/agents/anthropic-code-reviewer.md) — subagent · 31050 installs
- [code-reviewer](https://affpapa.org/en/nevibecode/agents/code-reviewer.md) — subagent · 31050 installs
- [test-engineer](https://affpapa.org/en/nevibecode/agents/test-engineer.md) — subagent · 9715 installs
- [code-reviewer](https://affpapa.org/en/nevibecode/agents/voltagent-community-code-reviewer.md) — subagent · 31050 installs
- [fullstack-developer](https://affpapa.org/en/nevibecode/agents/fullstack-developer.md) — subagent · 18117 installs
- [prompt-engineer](https://affpapa.org/en/nevibecode/agents/voltagent-community-prompt-engineer.md) — subagent · 16078 installs

From the same set: [davila7/claude-code-templates](https://affpapa.org/en/nevibecode/by/davila7/claude-code-templates.md) — 804 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md