Menu
Skills How it works Pricing
Free ToolFootage videos

Footage Edit Director

Edit existing footage with a word-level transcript, precise cuts, captions and a persistent project record.

Local edit example · synthetic narration and original graphics · full listening review pending 16:9 · 0:21

Download the editable example

What you get

  • Edited MP4 and an inspectable edit decision list
  • Word-level transcript, captions and revision notes

You will need

  • Python 3, FFmpeg and FFprobe
  • Optional Python dependencies for visual timeline inspection
  • Your own footage and word-level transcript, or your own ElevenLabs account for paid transcription

Good fit

  • Talking footage, tutorials and multi-take edits
  • Keeping source media intact while revising the cut

Not for

  • An included transcription account or stock-media license
  • Treating synthetic test footage as real talking-head acceptance

You say

“Read the installed SKILL.md. Use my actual inputs, preserve evidence and source media, and produce the declared deliverables. Report missing inputs and unperformed service calls.”

After installing, say something like this to your agent with your own topic and assets. It asks only for what is missing.

FAQ

Do I need an account?

No. Copy the install prompt into your agent, or download the free ZIP.

What does it cost to run?

The Skill is free. It needs the tools listed under “You will need”. Any voice, model or media service you choose bills you directly; FeedSkills does not include provider credits.

Can I use the videos commercially?

Videos you make are yours to use, including commercially. The Skill package is licensed as: MIT. Fonts, music, footage and services you add keep their own terms.

Which agents does it work with?

Agents that read SKILL.md files, such as Codex or Claude Code. What FeedSkills has actually tested is listed under Tested scope below.

Tested scope

Version
0.1.2
Acceptance
Acceptance for this version is still pending. It remains installable; check what has been tested before relying on it.
Tested
Local cutting, transcript packing, captions, revision and full decode were exercised with synthetic speech and graphics. Source-protection regressions pass. ElevenLabs transcription, real human speaking footage and full listening acceptance remain unverified.
Runs on
Codex · macOS · see dependencies
License
MIT

Details

Edit the footage you already have

Bring your recordings and tell the agent what the finished cut should achieve. The workflow inspects the material, proposes an editing strategy, and uses a word-level transcript to select takes, remove repetitions, preserve useful pauses and build an editable cut.

After you approve the strategy, local helpers produce an edit decision list, an MP4, output-timed captions and a project record. Keep the original footage and create a new output for each revision. Timeline inspection helps review a cut; it cannot replace watching and listening to the complete result.

Choose a transcript path

Use your own word-level transcript, or supply your own ElevenLabs account for Scribe transcription. The online path uploads audio to ElevenLabs and can incur charges. Local editing needs Python, FFmpeg and FFprobe; visual timeline inspection also needs the Python dependencies listed in the installed instructions.

The Skill retains the upstream editing method and executable helpers, with local checks to protect source files and reject stale transcript caches. It does not include a transcription subscription, stock footage or music rights.

Inspect a revision

Start with a small section. Compare the retained words, cut edges, caption timing and final duration with the edit decision list. A second edit should change the requested region while preserving the original sources. Test a missing source and an invalid cut as well as a successful render.

The included examples use synthetic speech and original graphics with manually supplied word timings. They demonstrate local editing and revision, not acceptance of real human talking-head footage or the online transcription service.