# agent-first-screenshots

The agent-first-screenshots agent drives the live app over CDP and keeps a frame only after structural, pixel and vision checks pass. Built for landing pages, newsletters and decks.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 7523 repo stars
- Author: Devin-AXIS
- License: LicenseRef-Proprietary · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Devin-AXIS/iPolloWork/tree/HEAD/.opencode/skills/agent-first-screenshots/SKILL.md
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/agent-first-screenshots

## What it does

Reload the page, walk the UI the way someone prepping a demo would, hide a stray badge or footer link with `display:none`, capture. A DOM check runs first: the scroll area has to be taller than 100px, hero copy sits inside the viewport, nothing modal is left open. Fail that and you reload instead of patching styles. Overriding flex on structural containers collapses the layout, so the skill forbids it outright.

Then the PNG is decoded and sampled at the hero rects. Variance is the signal, not background share: filled regions sit above ~200, flat ones below 50, and a whole-image background ratio past 0.97 means an empty frame. Stats still miss overlap and clipping, which is why a vision model grades the image against a JSON rubric; if `any_obvious_defect` comes back true, the frame is rejected no matter what the first two layers said.

Two scripts come with the skill: `screenshot-verify.mjs` for an existing PNG, and `capture-verify.mjs`, which shoots at 2x, checks the regions and saves only passing frames. Both lean on `sharp`. The vision gate is mandatory, so an agent with no access to a model that looks at images gets half the pipeline. Runs in Claude and Codex. This is not pass/fail evidence either; the skill points to `fraimz` for that.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/agent-first-screenshots/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/agent-first-screenshots/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/agent-first-screenshots/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/agent-first-screenshots/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install Devin-AXIS/iPolloWork .opencode/skills/agent-first-screenshots
```

2. **Manually: put the files in place**
- File: `.github/skills/agent-first-screenshots/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add Devin-AXIS/iPolloWork --skill agent-first-screenshots -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/Devin-AXIS/iPolloWork --path .opencode/skills/agent-first-screenshots
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/agent-first-screenshots/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Devin-AXIS/iPolloWork/tree/HEAD/.opencode/skills/agent-first-screenshots/SKILL.md

## When to use it
- capture clean app shots for a landing page
- regenerate screenshots after a redesign without hand-cropping
- catch clipped text and collapsed layout before publishing
- fit a frame to a target aspect ratio with a CDP metrics override
- reject blank frames before they reach a deck

## Example prompts
- Take fresh screenshots of the app for the pricing page at 1440x900 with `deviceScaleFactor: 2` and verify each frame before saving.
- Redo the dashboard screenshots after the redesign and drop any frame that fails the vision check.
- Run `capture-verify.mjs` over the settings page and keep only the PNGs that pass.

## Similar
- [web-browser](https://affpapa.org/en/nevibecode/skills/web-browser.md) — skill · 685 installs
- [cdp-bridge-mcp-browser-control](https://affpapa.org/en/nevibecode/skills/cdp-bridge-mcp-browser-control.md) — skill · 218 installs
- [cloudflare-browser](https://affpapa.org/en/nevibecode/skills/cloudflare-browser.md) — skill · 25 installs
- [flow-next-drive](https://affpapa.org/en/nevibecode/skills/flow-next-drive.md) — skill · ★ 730 repo stars
- [aso-appstore-screenshots](https://affpapa.org/en/nevibecode/skills/aso-appstore-screenshots.md) — skill · 869 installs
- [workflow-progress-screenshots](https://affpapa.org/en/nevibecode/skills/workflow-progress-screenshots.md) — skill · 682 installs

From the same set: [devin-axis/ipollowork](https://affpapa.org/en/nevibecode/by/devin-axis/ipollowork.md) — 42 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
