agentleFS
badgidsbadgids/Story-Film-Skills/skills/character-bible/SKILL.md

character-bible

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Create a compact character bible focused on behavior under pressure, goals, contradictions, relationships, speech, appearance, wardrobe, and continuity facts that affect story or production.

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

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, brief, story architecture, existing canon, and current story state when present.

    line 13
  2. Distinctive:

    Keep speech, movement, and stillness as separate performance signatures.

    line 17
  3. Very specific:

    Write 01_story/characters.md and update 00_project/canon.json with only locked identity, performance, relationship-baseline, and continuity …

    line 20
  4. Very specific:

    Run scripts/character_profiles.py <project> and the project validator.

    line 21
  5. Very specific:

    Every recurring character can be recognized by durable identity and behavior, current story state remains separate from baseline canon, and …

    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

Character Bible

Workflow

  1. Read core contract, CHARACTER_PROFILE.md, style rules, brief, story architecture, existing canon, and current story state when present.
  2. Assign stable CHAR-### IDs. Work one consequential character at a time when the cast or context is large.
  3. Resolve story function before biography. Record objective, fear or limit, contradiction, pressure behavior, private knowledge, and only backstory that changes present behavior.
  4. Build canonical identity with physical identifiers, must_preserve, explicit must_not_be exclusions when useful, and may_vary scene-state traits.
  5. Keep speech, movement, and stillness as separate performance signatures. Do not turn acoustic TTS settings into a speech-writing profile.
  6. Record recurring pair behavior as canonical relationship_baselines. Put chronology-specific trust, hostility, power, knowledge, injury, possession, and other current state in story_state.json instead.
  7. Preserve strong user wording. If a consequential creative fact is unresolved, keep it open or use decision-tree-interview; do not invent detailed canon to fill a template.
  8. Write 01_story/characters.md and update 00_project/canon.json with only locked identity, performance, relationship-baseline, and continuity facts.
  9. Run scripts/character_profiles.py <project> and the project validator.

Done

Every recurring character can be recognized by durable identity and behavior, current story state remains separate from baseline canon, and downstream writing/directing/generation work can use the saved profile without reconstructing it from chat.

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.