More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Reeldigest: Videos into clean, searchable transcripts

    1

    Captions first, audio and Whisper when there are none, chunked and resumable, merged by timestamp offset, then a digest of original articles or verbatim quotes, with a leak check before commit.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Reeldigest: Videos into clean, searchable transcripts

    Reeldigest: Videos into clean, searchable transcripts

    Example session with this skill installed

    Reeldigest: transcribe the 12 cooking tutorials in manifest.json and write one original article per topic for our recipe wiki.

    • Read your context and instructions
    • Compiled the reeldigest

    Reeldigest audit: recipe wiki batch (example data)

    Mode: knowledge (original articles). Manifest: 12 videos, 3 topics.

    Fetch

    RouteVideosNotes
    Captions (.vtt verified on disk)81 reported success but wrote no .vtt, moved to audio
    Audio + Whisper31 livestream of 2h48m split into 12 chunks
    Failed1vid_09: HTTP 403, browser cookies expired

    Transcription

    • 11 of 12 videos have transcript.json.
    • Audio chunks: 14 min mono Opus, all under 4 MB; cache resumed after a stop at chunk 7 of the livestream.
    • Offsets spot-checked: one timestamp per long video matches the source.

    Digest

    TopicTranscriptsArticle
    Bread basics4articles/bread-basics.md
    Knife skills3articles/knife-skills.md
    Sauces4articles/sauces.md

    Sample of 6 paragraphs checked against transcripts: no invented facts.

    Leak check: 0 URLs, 0 video ids, 0 channel names or handles in articles/. Transcripts and audio gitignored. Audit doc written; source list kept private.

    Next steps

    • Re-export browser cookies and rerun vid_09; cached work is skipped.
    • Owner pass on the 3 articles before they go into the wiki.
    • Open the PR with the audit doc.

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

    About this skill

    The knowledge you need is spread across dozens of tutorials and long livestreams, and you cannot search a video. Captions are missing for some languages, downloads return HTTP 403 and a six hour transcription stops halfway with no way to resume. Reeldigest turns a curated list of videos into clean transcripts and a usable digest.

    What it does

    • Manifest first with id, url, topic, language and duration, and an output mode chosen up front: knowledge or signals.
    • Captions first with yt-dlp, then checks that a .vtt file actually exists for each id instead of trusting the exit code.
    • Audio fallback for videos without captions, using a logged-in browser profile for cookies.
    • Chunked, resumable transcription with mono Opus chunks of about 14 minutes, cached by video id and chunk index.
    • Offset merge adds each chunk's offset to its timestamps for one transcript per video.
    • Leak check greps the output for URLs, video ids, channel names and handles before commit.

    How it works

    1. Curate the video list and freeze it in manifest.json.
    2. Fetch captions, or audio when there are none, then chunk with ffmpeg.
    3. Transcribe with Whisper locally or a hosted API with a failover provider, then clean rolling-caption duplicates.
    4. Digest into original articles per topic (knowledge) or verbatim quotes with timestamps in signals.json (signals), spot-checked against transcripts.

    Frameworks & tools

    Uses yt-dlp, ffmpeg and Whisper (whisper.cpp, faster-whisper or a hosted endpoint). Discovery of channels can use search or Playwright.

    Why this beats prompting it yourself

    A prompt cannot resume a stalled six hour job or notice that a caption was never written. Reeldigest verifies files on disk, caches every chunk and records an explicit failure reason for any video it could not transcribe.

    Use cases

    • Knowledge base from tutorials as original articles with no source credits shown.
    • Signal or sentiment corpus of verbatim quotes with timestamps.
    • Batch analysis through your own transcription service.

    Known limitations

    Not for republishing someone else's video or a single short clip. Scheduled runs need a pipeline that works without a logged-in browser session. Transcripts and audio stay gitignored.

    Not for republishing someone else's video or a single short clip. Scheduled runs need a pipeline that works without a logged-in browser session. Transcripts and audio stay gitignored.

    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 any payment.

    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 29 days ago

    Requires

    yt-dlp
    ffmpeg
    Whisper
    whisper.cpp
    faster-whisper
    Playwright

    Permissions

    Browser
    Network Access
    Write Files
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    yt-dlp and ffmpeg, plus Whisper locally (whisper.cpp or faster-whisper) or access to a hosted transcription API. Videos without captions need a logged-in browser profile for cookies.

    No. Knowledge mode rewrites facts into original articles with no quotes, links or credits, and a leak grep runs before every commit.

    Chunks are cached by video id and chunk index, so a rerun skips what is done. Any video that still fails gets an explicit failure reason.

    SKILL.md, the skill your agent follows, and LICENSE.md.

    New in Research & Analysis