agentleFS
badgidsbadgids/Story-Film-Skills/skills/shot-design/SKILL.md

shot-design

Skill4 starsChanged 3 months agoApache-2.0View on GitHub

Design motivated shots from a screenplay scene and director book, giving every shot a purpose, framing, camera behavior, action, continuity state, duration, and sound plan.

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

8 rules. About 0 are common, 3 are distinctive, and 5 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.

  • 5

    Very specific

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

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

    Read core contract, VISIBLE_DIALOGUE_SYNC.md, dramaturgy rules, film grammar, prompt packet schema, screenplay scene, line manifest, …

    line 13
  2. Very specific:

    Write one model-neutral JSON object per shot to 04_generation/shot_briefs.jsonl.

    line 16
  3. Very specific:

    Add end_frame only when chained generation, match on action, last-frame conditioning, or editorial continuity needs an explicit final state.

    line 20
  4. Very specific:

    Add optional frame_regions only when multi-subject screen placement needs explicit control or the downstream route supports regional …

    line 21
  5. Distinctive:

    Check screen direction, eyelines, eye trace, and geography across adjacent shots.

    line 22
  6. Very specific:

    If the requested camera/action combination is unavailable or conditional in production_capabilities.json, redesign, split, or mark the …

    line 23
  7. Distinctive:

    Delete shots that do not change a relationship or emotion, advance action or information, increase pressure, or satisfy an explicit …

    line 24
  8. Distinctive:

    Every shot earns its place in the edit and can be generated independently from its saved brief.

    line 28

≈ “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

Shot Design

Workflow

  1. Read core contract, VISIBLE_DIALOGUE_SYNC.md, dramaturgy rules, film grammar, prompt packet schema, screenplay scene, line manifest, breakdown, director book, continuity, production capabilities when present, performance blocking when present, and approved reference manifest.
  2. Assign stable SHOT-### IDs within the project sequence.
  3. Design the minimum coverage needed for the intended cut.
  4. Write one model-neutral JSON object per shot to 04_generation/shot_briefs.jsonl.
  5. Each shot must include line_ids for the source production units it covers when a line manifest exists, plus purpose, dramatic job, beat, scene ID, duration, subjects, location, continuity, framing, composition, camera, movement reason, eye trace, action, environmental pressure, micro-action, anchor, lighting, dialogue, ambience, music, SFX, references, cut intent, and constraints.
  6. Resolve applicable visual-bible capture behavior into capture_behavior without inventing camera hardware.
  7. When the viewer must see a character speak an exact screenplay line, add the model-neutral lip_sync record with exact LINE-###, speaker, visibility, cut policy, and measured timing when available. Do not force lip sync onto off-screen dialogue. When approved audio exists, preserve its MEDIA-###, SHA-256 authority, and start time and run dialogue timing preflight before expensive generation.
  8. Add end_frame only when chained generation, match on action, last-frame conditioning, or editorial continuity needs an explicit final state. When motion state also matters, add a temporal-continuity handoff that uses the approved previous shot and a visual-only tail; do not import prior-shot audio.
  9. Add optional frame_regions only when multi-subject screen placement needs explicit control or the downstream route supports regional conditioning. Use semantic zones unless normalized bounds were deliberately planned.
  10. Check screen direction, eyelines, eye trace, and geography across adjacent shots.
  11. If the requested camera/action combination is unavailable or conditional in production_capabilities.json, redesign, split, or mark the blocker rather than pretending it is executable.
  12. Delete shots that do not change a relationship or emotion, advance action or information, increase pressure, or satisfy an explicit practical coverage need.

Done

Every shot earns its place in the edit and can be generated independently from its saved brief.

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.