agentleFS
Sign inStart free
dileepgaganrdileepgaganr/instagram-autopilot-skill/skills/ig-analyze/SKILL.md

ig-analyze

Skill0 starsChanged 30 days agoMITView on GitHub

Analyze a short-form video before it goes to Instagram - Reels specs, aspect, scene cuts and the time to the first cut, frozen stretches, dead air at the start and end, loudness - and produce a fixed copy. Use when the user asks "is this video ready", "check my reel", "why does this lose people", "fix the audio/aspect", or before approving any video.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. nicojunk/claude-ig★ 17same name
    2. workflownicojunk/claude-skills★ 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.

  • In this repository3 other files it gives its agents.

The file

Create a free account to mount
Files
SKILL.md

ig-analyze

igap analyze <file|id>          # human report
igap analyze <file|id> --json   # everything, for reasoning
igap tweak <file|id> [--cap]    # writes ~/.instagram-autopilot/media/tweaked/<name>.ig.mp4

Needs ffmpeg and ffprobe on PATH. The original file is never modified.

Reading the report

linemeaningwhat to do
ERRORInstagram will reject it (too short/long, wrong container)re-export; autopilot blocks it
FIXautopilot fixes it on a copy before postingnothing, or run tweak to preview
WARNneeds judgement, not a filtertell the user plainly; suggest an edit

The timing features, and why they matter:

  • first_cut_s — the first visual change. The hook window is about three seconds; a first cut at 5s on talking-head footage usually means the opening runs long.
  • longest_frozen_s — the longest stretch where the picture does not change. Static stretches are where viewers swipe. Motion-graphics videos often have zero hard cuts and that is fine; this is the number that matters for them.
  • lead_silence_s / tail_silence_s — dead air. The tweak trims both (never below 3s total).
  • lufs — integrated loudness. Instagram plays loud; -14 LUFS is the usual target.
  • sound_coverage — share of the clip above -35 dB. Near zero means music-free or broken audio.

--cap trims the end to video.target_max_s. It can cut mid-sentence, so only use it when the user agrees, and listen to the result first.

Learned targets (from ig-learn) override the defaults once there is enough data; igap config shows the defaults, igap report shows what the playbook changed.

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