Visual annotation tool for design review workflows

Conclave AI visual review — Playwright screenshots + pixel diff for before/after design review.

Judgement Yields Navigation: composable software design, review, documentation, and investigation skills for coding agents

Floor-raising code and design review for opencode: a read-only reviewer model you configure independently of your session model

Idea into committed design through approval gates a human holds. Every outcome it emits — including its own multiple-choice questions — passes the orientation question before it is spoken. Brainstorming, ideation, requirements gathering, design review.

Drop-in Figma-style design review commenting overlay for Vite + React + Express prototypes.

Files-first design review: an agent condenses a repo's design into decidable facts, a human reviews them, the approved revision drives implementation

Design review in CI with a line down the middle: measured checks that gate the build (WCAG contrast from your tokens or from a real rendered page, one-off values in your markup) and a fresh-eyes model judge whose verdicts stay advisory. Zero dependencies.

Session-scoped MCP scratchpad with interactive HTML previews, revision comparison, and design review.

Catch bad animations before they ship — deterministic motion audit + vision-LLM design review for your terminal and Claude Code.

Evidence-first design review for Apple apps. Capture the screen, read the AX tree, fix the slop.

A drop-in React feedback system for component-level feedback capture during development and design review

Git-backed memory and design review for AI coding agents

FlowRail skill markdown for Claude Code agents. Auto-invocable skills for design review, verify, lineage, and dep-check; copied into .claude/skills/ by @flowrail/init.

Universal AI Design Review Agent - CLI tool for scanning code for design drift

A second pair of eyes for a UI: capture screenshots and measured facts, get a ranked visual critique from Gemini or OpenAI, and verify before and after. Built so one coding agent (Claude Code) can ask another model for design review.

Drive Figma from Claude Code — design, review, and file feedback.

Claude Code skills for Electron app QA — design review, visual testing, and performance benchmarking

Independent design-review workflow for coding agents

MCP server for DesignPin — wrap any AI tool (Claude Desktop, Cursor, ChatGPT, Gemini) into a design review workflow. Push HTML prototypes, fetch reviewer comments, upload revisions.