agentleFS
Sign inStart free
surasakchosurasakcho/claude-skills/run-clips/SKILL.md

run-clips

Skill0 starsChanged 5 months agoMITView on GitHub

Generate the video clips for a content item by running the project's configured clip-generation command, after animation prompts are drafted. Thin runner for the generate stage of a content-pipeline shorts project. Use when advancing an item whose clips need generating.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Ensure animation prompts exist: If flow_prompts.txt (or the project's T2V-prompt file) isn't drafted for the locked keyframes, run …

    line 15

≈ “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

Thin runner for the generate stage: turn locked keyframes into video clips by running the project's own generation script. It owns running and recovering, not the craft — prompts come from draft-asset-prompts, the command from project.md.

This stage is usually the video dollar spend. It runs only after the upstream review gate is approved (the orchestrator enforces this) — never generate clips before that gate clears.

Steps

  1. Ensure animation prompts exist. If flow_prompts.txt (or the project's T2V-prompt file) isn't drafted for the locked keyframes, run draft-asset-prompts to write it first. Animate the locked composition; don't redesign it.
  2. Gate on animatability before spending. Confirm every shot passed draft-asset-prompts' animatability screen. A keyframe with many independently- moving components (armies, crowds, players on a field) must be recomposed before it reaches clip generation — not micromanaged in the prompt. Do not spend clip budget on a shot flagged for recomposition; send it back first.
  3. Run the configured command. Take commands.generate from project.md, substitute {item} with the item's directory, and run it. This is the authoritative command — don't guess a different one from prose. If commands.generate is missing, stop and ask for the command.
  4. On failure, re-run only the owning unit (the failed shot/subcommand), not the whole batch — clips cost money. Use any free retry path the charter documents before re-spending.
  5. Report what was produced (clip files in playback order) and the spend if the command reports it. Leave pipeline.md updates to the orchestrator.

Respect all pipeline conventions in context.md (output filenames, playback-order numbering, 9:16/resolution). context.md overrides on conflict.

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