agentleFS
Sign inStart free
legenxxxlegenxxx/video-digest/SKILL.md

video-digest

Skill1 starsChanged 4 months agoMITView on GitHub

Use when you need to know what's inside a local video without watching it — a searchable text summary (video-to-text): the spoken transcript, on-screen text, links and @handles, and contact-sheet montages from one or many video files (.mp4/.mov/.mkv/.webm). Also for cataloguing or searching an archive of clips, reels, talks, screen recordings, or reference footage, or as a captions/subtitles source. Runs fully offline; no API keys, no uploads.

  • Installs packages

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. cycleuser/Skills★ 13same name
    2. bonniegeng-max/video-digest★ 1same name
    3. ONEIRO-codes/video-digest★ 0same name
    4. RobBrautigam/video-digest★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not for: live streams, editing/cutting video, or generating video.

    line 36
  2. Very specific:

    Run scripts/video-digest.sh --help for the full list.

    line 63

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

video-digest

Overview

Turn any video into a single searchable Markdown digest. For each clip the skill produces three things and stitches them into one digest.md:

  1. Transcript — the spoken words (faster-whisper, on-device).
  2. On-screen text — every unique line of text visible in the frames (OCR), with URLs and @handles pulled out separately.
  3. Contact-sheet montages — grids of frames spanning the whole clip, so you can read its visual story at a glance.

Everything runs locally. No network calls, no accounts, no telemetry. The core needs only ffmpeg; transcript and OCR are optional and degrade gracefully.

When to use

  • "What's in this video / these 200 videos?" without watching them.
  • Building a searchable catalogue of reels, talks, tutorials, or footage.
  • Recovering the links and handles flashed on screen in a clip.
  • Getting a fast visual overview (montages) of long or many recordings.

Not for: live streams, editing/cutting video, or generating video. This reads video and emits text + image summaries.

Quick reference

scripts/check-deps.sh                    # what's installed + how to get the rest
scripts/video-digest.sh clip.mp4         # one video → ./video-digest-out/clip/digest.md
scripts/video-digest.sh --out ~/digests *.mp4     # batch a whole folder
scripts/video-digest.sh --lang en talk.mov        # hint the transcript language
scripts/video-digest.sh --no-transcript reel.mp4  # skip audio, just visuals+text
scripts/video-digest.sh --ocr-engine tesseract x.mp4   # force a specific OCR engine
FlagPurposeDefault
-o, --out DIRoutput root./video-digest-out
--fps NOCR frame sampling rate2
--montage-frames Nframes spread across the clip90
--tile CxRmontage grid3x3
--ocr-engine Eauto|vision|tesseract|noneauto
--whisper-model Mtiny|base|small|medium(+.en)small
--whisper-python Pinterpreter that has faster-whisperauto-detected
--lang CODEtranscript language hintauto-detect
--no-transcript / --no-ocr / --no-montageskip a stage—
--forcere-run stages even if cachedoff

Run scripts/video-digest.sh --help for the full list.

How it works

The entry point scripts/video-digest.sh orchestrates three small, independent tools you can also run on their own:

StageScriptEngine
Montagesscripts/montage.shffmpeg tile filter
On-screen textscripts/ocr.sh (+ ocr_vision.swift)macOS Vision (default) or tesseract
Transcriptscripts/transcribe.pyfaster-whisper

Each stage is resumable — completed work is marked .done / cached and skipped on re-runs unless you pass --force. The digest is always rebuilt from whatever stages are present, so partial runs still produce a useful file.

OCR engine selection is automatic: on macOS it uses the built-in Vision framework (no install, on-device), otherwise tesseract if present, otherwise it skips OCR with a warning. See references/setup.md for installing optional backends and references/output-format.md for the exact output layout.

Common mistakes

  • Empty transcript → faster-whisper isn't installed in the interpreter being used. Run scripts/check-deps.sh, then pip install faster-whisper, or point at an existing env with --whisper-python /path/to/python.
  • No on-screen text on Linux → install tesseract (apt install tesseract-ocr); the Vision engine is macOS-only.
  • Huge montage count on short clips → lower --montage-frames (e.g. 30).
  • Wrong language transcript → pass --lang (e.g. --lang sk), or use a non-.en model for multilingual audio.

Example

examples/sample-digest/ contains a tiny generated clip and the digest.md it produces — transcript, one detected URL, one @handle, and a montage sheet. Reproduce it with (the transcript line needs faster-whisper installed):

scripts/video-digest.sh --montage-frames 9 examples/sample-digest/sample.mp4

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free