Create tool-neutral scene previz plans with geometry, entrances, exits, actors, paths, props, eyelines, camera setups, screen direction, and cut order using stable project IDs.
Scanned 9/9/2026
Install to Claude Code
npx -y skills add badgids/Story-Film-Skills --skill previz-plan --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Previz Plan?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/badgids-previz-plan)More formats (shields.io, HTML) on the badges page.
---
name: previz-plan
description: Create tool-neutral scene previz plans with geometry, entrances, exits, actors, paths, props, eyelines, camera setups, screen direction, and cut order using stable project IDs.
disable-model-invocation: true
author: Alan Guice (Badgids)
license: Apache-2.0
---
# Previz Plan
## Workflow
1. Read the standalone contract, core contract, previz schema, screenplay scene, director book, continuity, references, and planned shot scope.
2. Decide whether previz adds value. Use it for difficult geography, blocking, action, eyelines, moving cameras, vehicles, or coverage problems.
3. Separate verified geometry from planning assumptions.
4. Create `03_preproduction/previz/SCN-###.json` using the portable schema.
5. Record actor start and end states, important paths, entrances, exits, obstacles, important props, eyelines, camera setups, axis side, and screen direction.
6. Use metric coordinates only when known or intentionally chosen. Mark estimates as approximate.
7. Add a short `SCN-###.md` explanation of the scene geography and any unresolved staging problem.
8. If previz reveals a shot problem, update shot design and run `project-impact` for that scene scope.
## Done
The scene can be blocked or reconstructed in a generic 3D or diagramming tool without reading the chat, and no invented measurement is presented as known fact.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling