agentleFS
kiku-jwkiku-jw/codex-skills/video-builder/SKILL.md

video-builder

Skill0 starsChanged 4 months agoMITView on GitHub

Create short narrated videos from text scripts, simple timelines, or still images using Python and ffmpeg, with optional edge-tts voiceover. Use when the user asks for an MP4 render, narration generation, or a simple explainer video build.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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:

    Do not use when: the user only wants storyboarding or copywriting with no actual render pipeline involved.

    line 10
  2. Very specific:

    If a child lane is unavailable in the current run, continue here with the same split: first define the smallest honest spec, then render it …

    line 18
  3. Distinctive:

    If fonts or narration assets are missing, the skill says so instead of silently substituting broken defaults.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Video Builder

Metadata

  • Trigger when: the task is to render a short narrated or slide-like video from script or still assets.
  • Do not use when: the user only wants storyboarding or copywriting with no actual render pipeline involved.

Skill Purpose

Stay as the entrypoint for video work, then route into the narrowest lane: build a clean render spec or run the renderer from an existing spec.

Instructions

  1. Classify the request first. If the user needs help turning script/assets into a minimal JSON spec, prefer $video-spec-builder. If the user already has a spec and needs an actual render, prefer $video-render-run.
  2. If a child lane is unavailable in the current run, continue here with the same split: first define the smallest honest spec, then render it with ~/.codex/skills/video-builder/scripts/render_video.py using python3 ~/.codex/skills/video-builder/scripts/render_video.py --spec /absolute/path/to/spec.json --out /absolute/path/to/out.mp4.
  3. Validate the render with ffprobe or an equivalent playback check. Confirm duration, pacing, narration alignment, font availability, and whether the output needs one targeted iteration or is ready to ship.

Non-Negotiable Acceptance Criteria

  • ffmpeg and ffprobe must be available, or the missing dependency is stated clearly.
  • The first render starts from a minimal spec instead of a giant kitchen-sink configuration.
  • Voice mode, narration timing, and output size are explicit.
  • If fonts or narration assets are missing, the skill says so instead of silently substituting broken defaults.

Output

  • The spec path and rendered video path.
  • The narration mode used: edge-tts or existing audio.
  • A short validation note on duration, pacing, and any needed follow-up tweak.
  • Next skill options (only if needed): $video-spec-builder — turn script/assets into a minimal render spec; $video-render-run — render and validate an MP4 from an existing spec.

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.