agentleFS
badgidsbadgids/Story-Film-Skills/skills/dialogue-voice/SKILL.md

dialogue-voice

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Create a reusable voice bible and exact dialogue cue list from screenplay lines, including character voice identity, delivery intent, language, timing, and continuity across scenes.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read core contract, CHARACTER_PROFILE.md, style rules, screenplay, 02_screenplay/line_manifest.jsonl when present, character bible, canon, …

    line 13
  2. Very specific:

    Write 04_generation/voice_bible.md with vocal age range, register, texture, cadence, accent or dialect only when decided, speech habits, …

    line 15
  3. Very specific:

    Write 04_generation/voice_cues.jsonl with the originating LINE-###, exact screenplay text, scene, speaker, language, delivery intent, …

    line 16
  4. Distinctive:

    Do not rewrite dialogue merely to make TTS easier without updating the screenplay.

    line 17
  5. Very specific:

    Every spoken LINE-### in scope maps to one voice identity and exact text source, and measured speech duration is available to the shooting …

    line 21

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Dialogue Voice

Workflow

  1. Read core contract, CHARACTER_PROFILE.md, style rules, screenplay, 02_screenplay/line_manifest.jsonl when present, character bible, canon, and continuity.
  2. Assign one VOICE-### identity per recurring voice. Use the canonical speech signature for cadence, habitual delivery behavior, and language style, while keeping acoustic timbre/accent/reference-audio identity in the voice bible.
  3. Write 04_generation/voice_bible.md with vocal age range, register, texture, cadence, accent or dialect only when decided, speech habits, emotional range, and forbidden drift.
  4. Write 04_generation/voice_cues.jsonl with the originating LINE-###, exact screenplay text, scene, speaker, language, delivery intent, timing target if known, measured duration when available, and target model.
  5. Do not rewrite dialogue merely to make TTS easier without updating the screenplay.

Done

Every spoken LINE-### in scope maps to one voice identity and exact text source, and measured speech duration is available to the shooting script when generated.

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.