Narrated Evidence

    1

    Record narrated screen videos (voice + subtitles) of bugs and features from a JSON script, using the free open-source narrate CLI and Playwright.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Narrated Evidence

    Example session with this skill installed

    Record a narrated video of the passengers form bug in our demo app: it says "Passenger saved" even when the server returns 500. Use the bug template and a Spanish voice.

    • Read your context and instructions
    • Compiled the narrated evidence

    Done. I wrote the script from the bug template, validated it and recorded it with the headless Playwright recorder.

    Result

    ItemValue
    Videoout/narration/narration.mp4 (49.8 s, H.264 + AAC + soft subtitles)
    Subtitlesout/narration/narration.srt
    Voiceedge-tts es-CO-SalomeNeural, no fallback needed
    Recorderplaywright (headless Chrome)

    Scenes

    SceneWhat is shown
    contextoChapter card: "Bug: false save in Passengers"
    pasosName and phone filled, Save clicked
    esperaBackend wait, sped up x4
    actualRed callout: shows "Passenger saved"
    esperadoGreen callout: should show an error
    evidenciaPOST /api/passengers -> 500 from evidence.json
    impactoChapter card: users believe data was saved

    Evidence captured

    • 1 failed response: POST /api/passengers returned 500.
    • 2 console errors: the 500 resource error and POST /api/passengers failed with 500.

    I checked frames at each scene start: the screen matches what the voice says.

    Next steps

    • Watch the video once before attaching it.
    • Attach the MP4 and SRT to the bug report or PR.
    from evidence.json

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

    About this skill

    Screenshots cannot show a sequence, a timing problem or a state that changes. This skill makes your agent produce a narrated video instead: it writes a short script, records the browser and delivers an MP4 with voice and subtitles that you can attach to a bug report or a pull request.

    What it does

    • Writes the script for you: one scene per idea, each with the sentence to narrate and the browser actions (go to, click, fill, wait).
    • Keeps voice and screen in sync: the voice is generated first and every scene waits until its narration ends, so the voice never runs ahead of the screen.
    • Bug and feature templates: context, steps, actual result (red callout), expected result (green callout), evidence and impact.
    • Speeds up slow waits (backend calls, loading) without touching the narration.
    • Collects evidence: failed network responses and console errors from the run, ready to quote in the video.
    • Delivers an H.264 MP4 with AAC audio and soft subtitles, plus an .srt file.

    How it works

    1. The agent checks the requirements and asks before installing anything.
    2. It installs the open-source CLI: npm install -g github:jeider05/ai-video-evidence.
    3. It writes narration.json from the matching template and validates it.
    4. It runs narrate run narration.json: free neural voices (edge-tts), headless Chrome recording, ffmpeg assembly.
    5. It checks frames and audio, then hands you the video and a scene timeline.

    Requirements

    An agent with a local terminal (Claude Code, Codex CLI, Cursor, Gemini CLI). Node.js 22+, ffmpeg and ffprobe, Google Chrome and Python with edge-tts. No paid API is needed; Deepgram is an optional paid fallback voice.

    Safety

    • The agent never types passwords: for apps behind a login you sign in yourself with narrate login <url>.
    • Test data only, with a QA_ prefix; existing records are never edited or deleted.
    • Outputs and session files stay out of git.

    Known limitations

    • Headless recording cannot show native <select> popups or OS dialogs.
    • The experimental gdigrab recorder (Windows + ego-browser) is for those cases and needs a visible window.
    • Web-only chats cannot run it: the CLI runs on your machine.

    Source code (MIT): https://github.com/jeider05/ai-video-evidence

    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.

    Needs an agent with a local terminal, Node.js 22+, ffmpeg/ffprobe, Google Chrome and Python with edge-tts. Headless recording cannot show native <select> popups or OS dialogs; the experimental gdigrab recorder (Windows + ego-browser) covers them. The agent never types passwords: you sign in with narrate login.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 day ago

    • Free with an Agensi account

    Software
    Node.js 22+FFmpegffprobeGoogle ChromePythonedge-ttsPlaywright
    Optional
    Deepgram API key (paid fallback voice)ego-browser (experimental gdigrab recorder, Windows)

    The agent installs the narrate CLI from GitHub (npm install -g github:jeider05/ai-video-evidence) after asking you. edge-tts needs internet.

    Permissions

    Browser
    Read Files
    Write Files
    Terminal / Shell
    Network Access
    Environment Variables

    Terminal to run the narrate CLI and ffmpeg; files to write the script and the video; browser to record the app; network for edge-tts voices and the GitHub install; environment variables only for the optional Deepgram key.

    Listed1 day ago

    What's inside

    Frequently Asked Questions

    This skill automates the creation of narrated bug reports and feature demos by synchronizing screen recordings with synthetic voiceovers, eliminating the need for manual video editing or recording your own voice.

    The skill (SKILL.md) with bug and feature script templates. Your agent installs the free, open-source narrate CLI (MIT) from GitHub after asking you: npm install -g github:jeider05/ai-video-evidence.

    Node.js 22+, ffmpeg and ffprobe, Google Chrome and Python with edge-tts, plus an AI agent with a local terminal (Claude Code, Codex CLI, Cursor, Gemini CLI). Web-only chats cannot run it.

    Yes, you can choose between different text-to-speech engines like edge-tts or Deepgram to adjust the voice profile, and the JSON script allows you to customize the timing and content of the narration.

    Yes. It records web apps in a browser: headless Chrome by default, or the real ego-browser window with the experimental gdigrab recorder on Windows. It does not record other desktop applications.

    Skill updates arrive through Agensi. CLI updates are published on GitHub; reinstall with the same npm install command to get them.

    New in Testing & Debugging

    Free