agentleFS
gitethanwoogitethanwoo/video-editing/skills/analyze-video-editing/SKILL.md

analyze-video-editing

Skill4 starsChanged 4 months agoMITView on GitHub

Reverse-engineer an existing video into a timecoded account of its shots, cuts, fades, camera motion, dialogue, subtitles, titles, music, sound transitions, pacing, and editorial structure. Use when the user shares a reference video or local media and asks how it works, why it feels effective, what can be learned from it, how B-roll and interviews are interwoven, or how to translate its grammar into an original edit. Produces machine evidence, visual review artifacts, and an editorial breakdown without confusing estimates with observed facts.

  • Reads credentials

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 1

    1. trku052-png/social-media-youtube-skills★ 1100% same

    Edited · 0

    None found.

    Wrote their own version · 0

    None found.

    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.

  • In this repository5 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When sound design, music continuity, or effects matter, pair semantic listening with signal evidence:

    line 52
  2. Distinctive:

    Read references/audio-and-timing.md before accepting a model's classification of quiet material.

    line 63
  3. Distinctive:

    Keep these labels explicit:

    line 67
  4. Distinctive:

    Never present a motion classifier or music estimate as certainty.

    line 73
  5. Distinctive:

    Read references/editorial-analysis.md for the reporting vocabulary and references/audio-and-timing.md for sound-driven analysis.

    line 87
  6. Very specific:

    Avoid false precision in prose.

    line 104
  7. Very specific:

    If the user wants to apply the result, hand the evidence and selected principles to the find-broll skill for cutaway sourcing and then to …

    line 117
  8. Distinctive:

    Verify the transcript against picture when wording drives the edit.

    line 122
  9. Distinctive:

    Check false cuts caused by flashes, large titles, or camera whip.

    line 123
  10. Distinctive:

    Prefer long-context semantic listening to establish cue identity, then focused passes around transitions.

    line 126
  11. Distinctive:

    Verify alleged silence, ambience, music endings, and fades against the spectrogram and loudness trace.

    line 127
  12. Distinctive:

    Do not redistribute the downloaded reference media.

    line 129

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Analyze Video Editing

Study how a finished video creates attention, emotion, and momentum. Treat the film as synchronized picture, sound, speech, typography, and structure—not merely a list of cuts.

Set SKILL_DIR to the absolute directory containing this file. Use the adjacent video-editing skill when the user wants the resulting ideas implemented in an edit.

Start with a source you can inspect

For a local file:

uv run "$SKILL_DIR/scripts/video_analyzer.py" analyze \
  /path/to/video.mp4 \
  --work-dir /path/to/analysis \
  --subtitles /path/to/captions.vtt

For a public URL, inspect the downloader's real metadata payload before choosing formats. Do not guess fields or stream availability:

uvx --from yt-dlp yt-dlp --dump-single-json --no-playlist URL > source.json
uvx --from yt-dlp yt-dlp --no-playlist \
  -f 'bv*[height<=1080]+ba/b[height<=1080]' \
  --merge-output-format mp4 -o 'source.%(ext)s' URL

Download captions when available. If download rights or site access are unclear, ask the user for a local copy.

Analyze a representative range first when the film is long:

uv run "$SKILL_DIR/scripts/video_analyzer.py" analyze source.mp4 \
  --work-dir analysis-first-three-minutes --start 0 --end 180 \
  --subtitles source.en.vtt --ocr

The script writes:

  • analysis.json: probe facts, shot boundaries, black and quiet intervals, audio levels, beat estimates, transcript cues, motion estimates, and OCR candidates;
  • timeline.md: a compact evidence table;
  • contact-sheet.jpg: visual rhythm across the requested range;
  • frames/: representative shot frames;
  • strips/: dense frames around major cuts, black intervals, and other events.

Scene detection, optical flow, beat tracking, and OCR are candidate generators. They reduce scrubbing; they do not replace watching and editorial judgment.

When sound design, music continuity, or effects matter, pair semantic listening with signal evidence:

python3 "$SKILL_DIR/scripts/audio_listener.py" \
  source.mp4 \
  --work-dir analysis/audio-movement \
  --start 60 --end 172 --mode movement

This optional command extracts direct audio, renders a spectrogram, measures half-second loudness windows, and—unless --prepare-only is supplied—asks Gemini for an editorial sound breakdown. It reads GEMINI_API_KEY from the environment and never accepts credentials as command-line arguments. Use --mode transition for a focused high-sensitivity pass around a cut, dropout, black interval, or suspected fade.

Read references/audio-and-timing.md before accepting a model's classification of quiet material.

Build the breakdown in three layers

Keep these labels explicit:

  1. Measured: timestamps, shot duration, hard-cut score, black frames, silence, audio level, detected beat, transcript words, OCR boxes.
  2. Observed: composition, subject, camera behavior, lighting, lens feel, text treatment, performance, apparent B-roll or interview mode.
  3. Interpreted: tension, release, emphasis, contrast, narrative function, or why a juxtaposition works.

Never present a motion classifier or music estimate as certainty. Say “appears handheld” or “likely music re-entry” when it is an inference.

Analyze the synchronized layers

For every important beat, ask:

  • Picture: What is shown? What changes at the cut? Is the framing wide, medium, close, insert, or abstract?
  • Camera: Static, locked-off, handheld, stabilized walk, pan, tilt, push-in, pull-out, rack focus, or subject motion inside a fixed frame?
  • Edit: Hard cut, match cut, jump cut, dip to black, fade, dissolve, speed change, montage, or an unusually long hold?
  • Speech: What line lands here? Is the next image literal illustration, contrast, reaction, or tonal counterpoint?
  • Sound: Dialogue, room tone, ambience, effects, score, pulse, silence. What enters, exits, or changes level before or after the visual edit?
  • Typography: Subtitle, chapter title, credit, label, or graphic motif? Record position, size, color, case, duration, entrance, and whether it obscures or complements the image.
  • Function: Hook, escalation, orientation, reset, thesis, proof, character introduction, montage, transition, or payoff?

Read references/editorial-analysis.md for the reporting vocabulary and references/audio-and-timing.md for sound-driven analysis.

Report at two scales

Create both:

  • a micro timeline for the most instructive section, often every meaningful change over the first 60–180 seconds;
  • a macro grammar for the whole film: recurring shot families, average shot length, interview/B-roll pattern, graphic system, music arcs, chapter resets, and escalation strategy.

A useful synthetic row looks like:

01:03.875–01:06.167 | hard cut | handheld exterior insert |
score re-enters and beat becomes explicit | large chapter title fills frame |
turns a reflective line into a formal chapter launch

Avoid false precision in prose. Use frame-accurate numbers in the evidence table, then readable mm:ss timestamps in the explanation.

Turn analysis into reusable learning

Extract principles, not imitations. For each device, state:

  • the viewer problem it solves;
  • the preconditions that make it work;
  • the cost or risk;
  • one way to adapt it to a different subject.

Example: “A four-second dip to black works here because the opening movement has accumulated tension and the continuing environmental sound prevents the reset from feeling like the video ended.”

If the user wants to apply the result, hand the evidence and selected principles to the find-broll skill for cutaway sourcing and then to video-editing for production. Do not encode the reference film's exact timings, fonts, or transitions as defaults.

Quality bar

  • Inspect representative frames and event strips yourself.
  • Verify the transcript against picture when wording drives the edit.
  • Check false cuts caused by flashes, large titles, or camera whip.
  • Distinguish source subtitles from platform captions.
  • Describe sound only to the resolution supported by the evidence.
  • Prefer long-context semantic listening to establish cue identity, then focused passes around transitions.
  • Verify alleged silence, ambience, music endings, and fades against the spectrogram and loudness trace.
  • Cite the public source when the report refers to it.
  • Do not redistribute the downloaded reference media.

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.