More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Make Your AI Agent Prove UI Changes With Screenshots

    1

    Needs Python, Playwright, Pillow and Playwright's headless Chromium. This skill serves a page locally, drives the states that matter, saves screenshots and an animation strip, compares a second run, and stops its server.

    $5.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Make Your AI Agent Prove UI Changes With Screenshots

    Make Your AI Agent Prove UI Changes With Screenshots

    Example session with this skill installed

    Example request

    I added a search box and a "Open summary" button to the Tidewell page (fictional, in sample/site/). Typing should list matching accounts; the button should slide a summary panel in. Prove both work on a phone-sized screen.

    Command run from this folder (Python 3.12, Playwright 1.60.0, Windows 11):

    python scripts/shoot.py sample/site --steps sample/steps.json --out sample/output --viewport 390x844 --strip 6 --step-ms 120 --check-twice
    
    • Read your context and instructions
    • Compiled the make your ai
    • Generated the UI component

    Example output (real run)

    UI proof: search box and summary panel (8 Nov 2026)

    Command: python scripts/shoot.py sample/site --steps sample/steps.json --out sample/output --viewport 390x844 --strip 6 --step-ms 120 --check-twice

    Script output

    00-load.png                  5970 bytes  d2e2463cea17
    01-typing.png               11149 bytes  febf0a1c88aa
    02-panel-open.png           12071 bytes  e983fae4d378
    strip.png                   35883 bytes  c287385629cd
    deterministic: True
    server stopped, port 49736 free: True
    

    (The port number differs on every run; the file hashes are the ones from this run and repeated in the second run.)

    FileStateWhat it shows
    00-load.pngPage loadedLabel "Search accounts", an empty search field, the green "Open summary" button, no panel and no list
    01-typing.png"tide" typedField holds "tide"; three white result cards: Tidewell Savings, Tidewell Current, Tidewell Joint
    02-panel-open.pngButton pressedThe three results stay; a green panel reading "Summary: 3 accounts match." sits below the button at full opacity

    Strip: strip.png, 6 frames at 0, 120, 240, 360, 480 and 600 ms. Frame 1 has no panel (opacity 0); frames 2 to 6 show the panel getting darker and moving up about 24 px in total; frame 6 matches 02-panel-open.png.

    Determinism: True (all four images were byte-identical in a second run).
    Server: stopped, port 49736 free.

    Verdict

    works. One thing noticed while building this sample: the first version of 02-panel-open.png caught the panel half faded; the script now waits for finite CSS animations to end before each screenshot, and the Gotchas say so.

    00-load.png

    TSX · React component

    Generated

    Example file from a real run - the skill writes it into your workspace.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Needs Python, Playwright, Pillow and Playwright's headless Chromium. This skill serves a page locally, drives the states that matter, saves screenshots and an animation strip, compares a second run, and stops its server.

    The proof

    This is real output copied from example-output.md:

    00-load.png                  5970 bytes  d2e2463cea17
    01-typing.png               11149 bytes  febf0a1c88aa
    02-panel-open.png           12071 bytes  e983fae4d378
    strip.png                   35883 bytes  c287385629cd
    deterministic: True
    server stopped, port 49736 free: True
    

    The same file records what each screenshot shows and describes all six frames in strip.png.

    What you get

    • SKILL.md: the evidence-first UI workflow for Claude Code and OpenAI Codex.
    • scripts/shoot.py: local server, state driver, screenshots, frame strip and repeatability check.
    • sample/site and sample/steps.json: a small interactive worked page.
    • sample/output: three state screenshots, a six-frame strip and manifest.json.
    • tests/test_shoot.py: end-to-end pytest coverage of output files, sizes, repeatability and cleanup.
    • example-task.md and example-output.md: the command and visual report.

    How to use

    1. List the states worth proving in a small JSON file.
    2. Run scripts/shoot.py with the site folder, viewport and output folder.
    3. Add --check-twice to compare image hashes across two runs.
    4. Open every PNG and write one sentence about what it actually shows.
    5. Fix any wrong state and rerun until the evidence matches the change.

    Known limitations

    • Repeatable screenshots prove repeatability, not correctness. A person still has to inspect every image.
    • Live data, remote fonts and other external inputs can make images differ.
    • Font rendering can differ between operating systems.
    • The script writes screenshots and a manifest to the output folder you choose.

    FAQ

    Does it use my everyday browser? No. It launches Playwright's own headless Chromium.

    Does it leave a server running? The script shuts down its own local server and prints whether the port is free.

    Can it capture interactions? Yes. A step can click, fill a field, run JavaScript and advance the fake clock.

    Which agents does it work with? It is a SKILL.md skill for Claude Code and OpenAI Codex.

    Does a clean second run prove the UI is right? No. You must still look at and describe every saved image.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.

    Requires Playwright and Chromium. Font rendering differs by OS. Infinite loops break determinism. Real-time timers require manual advancement via wait_ms.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 4 days ago

    Software
    Python

    Permissions

    Terminal / Shell
    Browser
    Read Files
    Write Files
    Network Access
    Listed4 days ago

    What's inside

    Frequently Asked Questions

    The script replaces Math.random with a seeded generator and installs a fixed clock, so Date.now() and timers repeat. Live data, server timestamps or web fonts loaded from the network can still make two runs differ, so serve them from the same folder. --check-twice tells you when two runs do not match.

    SKILL.md (the workflow), scripts/shoot.py, a test in tests/, a sample page with its steps.json and the saved output (three state PNGs, a six-frame strip and manifest.json), TESTING.md and CHANGELOG.md.

    No. It serves a folder and opens it in headless Chromium, so any page a browser can load from local files works; a React or Vue app needs to be built to static files first. The included sample is plain HTML, CSS and JavaScript.

    Both. --strip N captures N frames of a CSS animation at --step-ms intervals (the sample uses six frames at 120 ms) and joins them into one image you can inspect.

    Yes: Python 3, then pip install playwright pillow and playwright install chromium. Tested with Python 3.12 and Playwright 1.60.0 on Windows 11.

    No. Font rendering differs between operating systems, so compare screenshots made on the same machine.

    New in Testing & Debugging