Menu
Skills How it works Pricing
Members Video skillinvestigation15–60 sec

Visual Investigation · Feed

Build a sourced vertical investigation from document transcriptions, measured evidence cards and original schematics, with local English narration.

Two 18-second English A/B investigation films with local narration. 9:16 · 0:18

What you get

  • 1080×1920 / 30 fps MP4, cover, burned captions and SRT
  • A self-contained editable project, measured layout and scene render report

You will need

  • Node.js 22+, FFmpeg and FFprobe
  • Pinned HyperFrames 0.8.181 and a browser
  • Local Kokoro for default narration; explicit silent export is supported
  • Rights-cleared sources and human review

Good fit

  • Source-backed technical or historical explainers

Not for

  • Unverified allegations or simulated historical photographs
  • Automatic publishing or paid generation

You say

“Use Visual Investigation · Feed to make a sourced vertical video. Inspect the input, preserve source records, measure the real layout and show a preview before publishing.”

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?

Yes. Members Skills install from a signed-in FeedSkills account with an active Founding Membership.

What does it cost to run?

The Skill is included with Founding Membership. 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: FeedSkills Source-Available License 1.0 · upstream MIT preserved. 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
This version has a recorded acceptance entry.
Tested
Two 18-second 1080×1920 / 30 fps English A/B films and one scene edit were rendered with Chrome, HyperFrames 0.8.181, local Kokoro and FFmpeg/AAC. Feed checks report 0 fail, 0 warn and 0 not-measured; source, input, media and edit-frame bindings pass. Technical double review passed on 2026-10-29. Human audiovisual review and customer adoption are not claimed.
Runs on
Codex · macOS · Node.js 22+ · FFmpeg
License
FeedSkills Source-Available License 1.0 · upstream MIT preserved

Details

Two vertical examples

Visual Investigation Feed turns source-backed facts into a vertical investigation with evidence cards, bounded claims and local English narration. The supplied A/B films demonstrate the format with English local narration.

Make a sourced investigation

Start from an included brief and work in a new project directory outside the installed Skill. Bring rights-cleared documents, primary source URLs, transcripts and a clear known/unresolved boundary. Keep every claim linked to its source, preview the evidence map and render locally with Kokoro narration. Outputs include MP4, cover, burned captions, SRT, measured layout and a render report.

Do not use this Skill for unverified allegations, invented historical photographs or a claim that a still capture proves continuous activity. Replace the example facts before making a new investigation.

Access, dependencies and credit

This is a Members Skill. An active Founding Membership is required; this page provides sample previews only. The package needs Node.js 22+, FFmpeg/FFprobe, HyperFrames 0.8.181, a browser and a local Kokoro environment. No paid media-generation API is required.

The pinned LemoLab visual-investigation grammar (commit 413a6bd6d78ebd3bdd5abaec9538a26867f890df) supplies the MIT visual grammar. The package keeps upstream notices and its own FeedSkills Source-Available License; read STYLE.md, references/sources.md and THIRD_PARTY_NOTICES.md for the adaptation and rights boundary.