Visual Feedback Loop

AI agent visual feedback loop for any web app. Use when iterating on visual code (UI, canvas, 3D, SVG, charts, animations) and you need to SEE the rendered result to evaluate quality. Covers: dev-screenshot API pattern (GET trigger → SSE → client capture → POST back → file saved), parameterized rendering, metadata sidecars, visual regression with pixel diff, WebMCP tool registration, and console fallbacks. Activate on: 'take a screenshot', 'show me the render', 'visual QA', 'compare before/after', 'pixel diff', or any iterative visual work where the agent needs to inspect rendered output.

9 stars 1 forksFrontend & Design

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add vladmdgolam/agent-skills --skill visual-feedback-loop
Manual install
git clone --depth 1 https://github.com/vladmdgolam/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/visual-feedback-loop ~/.claude/skills/visual-feedback-loop

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Visual Feedback Loop

Capture, inspect, and compare visual output from a running web app during iterative development.

## How It Works

```
Agent (CLI)                     Server                            Browser
     |--- GET /api/dev-screenshot -->|--- SSE "capture" ----------->|
     |    ?param=value               |                              |-- capture canvas
     |                               |<-- POST { dataUrl } ---------|
     |                               | writes:
     |                               |   .screenshots/{UTC}.webp
     |                               |   .screenshots/{UTC}.json  (metadata)
     |                               |   .screenshots/latest.webp (convenience copy)
     |<-- { ok, path, latest } ------|
```

Agent can't access the browser directly. Server relays: GET triggers → SSE notifies browser → browser captures and POSTs back → GET resolves.

## Usage

Capture current view:
```bash
curl http://localhost:3000/api/dev-screenshot
```

Capture with params (app-specific — browser client interprets them):
```bash
curl 'http://localhost:3000/api/dev-screenshot?component=header&theme=dark'
curl 'http://localhost:3000/api/dev-screenshot?letter=б&depth=0.8'
```

Then read the result. Response includes `path` (timestamped file) and `latest` (convenience copy):
```
Read .screenshots/latest.webp
```

### Visual Regression (pixel diff)

Compare against a ground truth screenshot using ImageMagick:
Read the full skill on GitHub

Details

Skill name
visual-feedback-loop
Path
skills/visual-feedback-loop/SKILL.md
License
MIT
Repo updated
14 October 2026

FAQ

What does the Visual Feedback Loop skill do?

AI agent visual feedback loop for any web app. Use when iterating on visual code (UI, canvas, 3D, SVG, charts, animations) and you need to SEE the rendered result to evaluate quality. Covers: dev-screenshot API pattern (GET trigger → SSE → client capture → POST back → file saved), parameterized rendering, metadata sidecars, visual regression with pixel diff, WebMCP tool registration, and console fallbacks. Activate on: 'take a screenshot', 'show me the render', 'visual QA', 'compare before/after', 'pixel diff', or any iterative visual work where the agent needs to inspect rendered output.

How do I install the Visual Feedback Loop skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add vladmdgolam/agent-skills --skill visual-feedback-loop. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Visual Feedback Loop popular?

It lives in vladmdgolam/agent-skills, which has 9 GitHub stars and 1 forks.

Related skills

Agent Sessions

9

vladmdgolam/agent-skills

Search, list, and resume AI agent sessions across Claude Code, Codex CLI, Gemini CLI, opencode, Hermes Agent, and Cline CLI. Use when the user asks to find a past conversation, search session history, resume a previous session, list recent agent activity, or check what was discussed in a prior session. Also use when asked to "find that conversation where I...", "resume my last codex session", "read latest convo", "read last messages", "what did I work on yesterday", "search my claude history for X", or gives an agent session id such as `ses_...`, a UUID, or a Cline id like `1782988565588_qqrxi

AI, LLMs & Agents

Apple Books MCP

9

vladmdgolam/agent-skills

Extracts highlights, annotations, and book data from Apple Books via MCP. Use when: user asks to export book highlights, extract annotations with colors, search highlights across books, create highlight summaries, or match books from a reading list against their Apple Books library. Covers efficient batch color extraction (5 calls instead of 150+), annotation-to-book matching, and markdown export patterns.

AI, LLMs & Agents

Blender MCP

9

vladmdgolam/agent-skills

Blender MCP expert for scene inspection, Python scripting, GLTF export, and material/animation extraction. Activate when: (1) using Blender MCP tools (get_scene_info, execute_python, screenshot, etc.), (2) writing Blender Python scripts for extraction or manipulation, (3) exporting scenes to GLTF/GLB for web (Three.js, R3F), (4) debugging material or texture export losses, (5) optimizing GLB files with gltf-transform, (6) using asset integrations (PolyHaven, Sketchfab, Hyper3D Rodin, Hunyuan3D). Covers critical export gotchas, material mapping survival, texture optimization pipeline, headless

Images, Video & Audio

Visual Identity Designer

5

ali4o/visual-identity-designer

Build a professional, precise visual identity (brand identity) for a project, startup, or business — logo direction, color system, typography, application mockups — via a structured 9-stage agency workflow ending in two polished deliverables — a Brand Identity Guide and a Design Language System (built with the docx skill, in the user's chosen language). Trigger any time the user attaches, pastes, or describes a project idea/brief and asks for a "visual identity", "brand identity", "logo", "branding", "brand kit", "brand guide", "design language system", "هوية بصرية", or similar — even without

Frontend & Design

UI Buffet

9

kargnas/skills

Previews several UI/UX design concepts in the browser and builds the pick. Activates when the user asks for several UI/UX options or wants to think over or discuss a design before building.

Frontend & Design

Apple Human Interface Guidelines

9

milistu/agent-skills

Apple Human Interface Guidelines (HIG) reference for designing iOS, iPadOS, macOS, tvOS, visionOS, watchOS apps. Covers UI components, layout, accessibility, typography, navigation, inputs, and platform technologies. Use when designing Apple platform UIs, reviewing SwiftUI/UIKit patterns, or applying HIG design principles to any app.

Frontend & Design

Browse the most popular Claude skills, all frontend & design skills, or write your own with the skills generator.