agentleFS
Sign inStart free
kiku-jwkiku-jw/codex-skills/video-spec-builder/SKILL.md

video-spec-builder

Skill0 starsChanged 4 months agoMITView on GitHub

Build a minimal JSON render spec for the local video pipeline from script lines, still images, or narration assets. Use when the spec artifact must exist before any MP4 render can run.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not use when: a spec JSON already exists and the real job is running the renderer.

    line 10
  2. Distinctive:

    Write a minimal JSON spec with explicit size, fps, voice/input mode, and line structure.

    line 18
  3. Distinctive:

    If key assets or timing inputs are missing, the blocker is stated directly.

    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 Spec Builder

Metadata

  • Trigger when: the user has script lines, images, or narration assets and needs a clean render spec before rendering.
  • Do not use when: a spec JSON already exists and the real job is running the renderer.

Skill Purpose

Turn raw video inputs into one minimal, explicit JSON spec that the renderer can execute without guesswork.

Instructions

  1. Gather the smallest honest input mode first: text plus TTS, script plus image backgrounds, or existing narration plus explicit timing. Lock the required asset paths before writing anything.
  2. Write a minimal JSON spec with explicit size, fps, voice/input mode, and line structure. Keep the first spec lean instead of anticipating every future tweak.
  3. Validate the spec: confirm referenced files exist, required fields are explicit, and the next rendering command is obvious. If the spec is ready, hand off to $video-render-run.

Non-Negotiable Acceptance Criteria

  • The spec is minimal but complete enough for the renderer to run.
  • Asset paths, timing assumptions, and narration mode are explicit.
  • The skill does not render the video itself; it stops at the spec artifact.
  • If key assets or timing inputs are missing, the blocker is stated directly.

Output

  • The spec JSON path.
  • A short note on the chosen input mode and required assets.
  • Next skill options (only if needed): $video-render-run — render and validate the MP4 from this 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.

Check your setup, free