agentleFS
surasakchosurasakcho/claude-skills/showrunner-short/SKILL.md

showrunner-short

Skill0 starsChanged 5 months agoMITView on GitHub

Write the dialogue/voiceover script for a short-form video (≤~60s) from a locked concept, honoring the project's beat structure, hosts, and per-beat timing. Use at the script stage of a content-pipeline shorts project, once concept.txt exists and before asset prompts.

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. Very specific:

    Write script.txt for one short from its locked concept.txt.

    line 6
  2. Distinctive:

    Honor the charter's beat structure and timing exactly: Write each beat inside its time block.

    line 22
  3. Distinctive:

    Write for the voice(s) the charter names: If multi-host, give each a distinct cadence/role.

    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

Write script.txt for one short from its locked concept.txt. This is the shorts-family script skill — it encodes short-form craft but takes the specific beat structure, hosts/personas, duration, and voice from the project charter, so it works for any shorts channel, not one.

Read first (don't invent what these define)

  • concept.txt — what this short depicts (mechanic/subject, narrative beat, setting).
  • project.md + context.md — the charter: format/duration, beat structure and per-beat timing, host personas + their voices, the engagement mechanic (comment bait / CTA), IP/content constraints. context.md overrides on conflict.
  • Any per-project style_guide.md for tone. If the charter doesn't define a beat structure or hosts, ask — don't default to a structure the project didn't set.

Short-form craft (generic — applies whatever the structure)

  • Front-load the hook. The first 1–2 seconds must land in media res — no intros, no "hey guys," no throat-clearing. Open on the most arresting moment.
  • Honor the charter's beat structure and timing exactly. Write each beat inside its time block; don't let a beat run long. Tag every line with its speaker and its timing.
  • Write for the voice(s) the charter names. If multi-host, give each a distinct cadence/role; keep turns short and punchy for spoken delivery.
  • Write for TTS delivery — natural spoken phrasing, no unpronounceable markup in the spoken text; keep any delivery notes separate from the words to be voiced (follow the project's TTS convention in context.md).
  • End on the engagement mechanic the charter defines (a polarizing dilemma, a question, a CTA) — draft it together with the final beat.

Output

  • script.txt — speaker-tagged lines with per-line/per-beat timing.
  • Draft the engagement mechanic (e.g. pinned comment) into publish.md.
  • Apply the beat dependencies internally (hook → middle → payoff); don't interview the user beat by beat unless they ask.

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.