Skip to main content
affpapa.org
RU EN
subagent

screenshot-reviewer — Claude Code subagent: setup and review

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

Install into Claude Code · claude-code-templates All methods and platforms ↓ 
npx claude-code-templates@latest --agent ui-analysis/screenshot-reviewer
Open on GitHub

What screenshot-reviewer 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.

What it helps with

  • compare tasks with source screenshots
  • spot missing interface states
  • find conflicting requirements
  • check acceptance criteria and dependencies
  • suggest concrete task-list fixes

Example prompts for the agent

  • 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.

How to install screenshot-reviewer

1claude-code-templates

npx claude-code-templates@latest --agent ui-analysis/screenshot-reviewer

2Manually: put the files in place

.claude/agents/screenshot-reviewer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about screenshot-reviewer

How do I install screenshot-reviewer in Claude Code?

Run npx claude-code-templates@latest --agent ui-analysis/screenshot-reviewer, then add .claude/agents/screenshot-reviewer.md.

What does screenshot-reviewer do?

It audits a synthesized task list against screenshots and JSON analyses, checking coverage, consistency, task quality, and development readiness.

Which tools does screenshot-reviewer use?

The subagent uses Read, Write, and TodoWrite. Its review relies on the source screenshots and JSON analysis files.

Similar subagents

All subagents for Testing and QA →
code-reviewer official Anthropic Reviews code changes against CLAUDE.md project rules and flags material defects. Run it before a commit or pull request. 31,050installs code-reviewer official Anthropic This subagent checks code changes for bugs, security issues, and project-rule violations. Use it when a review should focus on findings that matter. 31,050installs test-engineer official Anthropic This subagent captures legacy behavior in tests and compares it with a rewritten implementation. Use it before changing existing modules. 9,715installs code-reviewer VoltAgent Community Reviews code changes for bugs, security flaws and maintenance issues. Use it before merging complex work or auditing a project. 31,050installs fullstack-developer VoltAgent Community This subagent carries a feature across the database, API, and frontend layers. Use it when one change needs a consistent end-to-end implementation. 18,117installs prompt-engineer VoltAgent Community This subagent designs, tests, and improves prompts for LLM production systems. Use it when prompts need evaluation, metrics, or cost tracking. 16,078installs

From the same set804

The whole set →
communication-excellence-coach Reviews email drafts and adjusts message tone for different audiences. Prepares you for difficult workplace conversations using What-Why-How and SBI models. 464installs write-tests Creates unit, integration, end-to-end, and component tests with mocks. Use it when a file needs a test plan and framework-specific checks. 459installs scientific-writing Writes research papers in standard IMRAD format using continuous prose, verified citations, and schematic workflows. 455installs vercel-auto-deploy Triggers automated Vercel deployments right after Claude Code edits source files in your project. 454installs flutter-go-reviewer A Claude subagent that reviews pull request diffs and fresh code across Go, Protobuf, PostgreSQL, Flutter, Riverpod and GetX. 452installs laravel-expert A skill that makes Claude answer as a senior Laravel engineer: thin controllers, FormRequest validation, API Resources, queues and caching. Useful when you build or refactor a Laravel 10/11+ backend. 449installs architecture Guides architectural choices and helps document decisions through ADRs in Claude Code. Useful when structuring new systems. 449installs optimize Analyzes active and past task orchestrations in Claude Code to detect bottlenecks, balance agent workloads, and surface parallel execution paths. 440installs

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor