storyboard-generator
Skill15 starsChanged 9 months agoMITView on GitHub
Use when creating visual pre-visualization frames before committing to full motion generation. Trigger when users mention "storyboard," "visual preview," "composition test," or when regen risk is high and layout validation is needed.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- zephyrwang6/myskilltheir own version, first seen Oct 8, 2026
- cocyuhao/my-ai-skills-librarytheir own version, first seen May 12, 2026
- SpaceZephyr/allSkillstheir own version, first seen Mar 31, 2026
- suse00544/dreamina-claude-skillstheir own version, first seen Jan 9, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- zephyrwang6/myskill★ 339same name
- SpaceZephyr/allSkills★ 14same name
- suse00544/dreamina-claude-skills★ 6same name
- cocyuhao/my-ai-skills-library★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- audience-simulatorSkill
- budget-gatesSkill
- character-lockSkill
- character-psychologySkill
- continuity-supervisorSkill
- cost-optimizerSkill
- cultural-checkSkill
- dialogue-consistency-checkSkill
- model-routerSkill
- narrative-red-teamSkill
- plausibility-auditorSkill
- prompt-packagerSkill
- qc-graderSkill
- regen-analyzerSkill
- research-agentSkill
- run-loggerSkill
- script-breakdownSkill
- set-lockSkill
- shot-plannerSkill
- story-architectSkill
- voice-lockSkill
- world-state-trackerSkill
The file
We split this skill into the rules it gives an agent
9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Before generating complex shots.
- Distinctive: line 31
When multi-character blocking exists.
- Distinctive: line 32
When new sets introduced.
- Distinctive: line 33
When camera movement is non-trivial.
- Distinctive: line 34
When regen risk classified as medium or high.
- Distinctive: line 35
Before escalating to final resolution.
- Distinctive: line 37
Do NOT use for trivial single-character static shots.
- Distinctive: line 99
All required characters present.
- Distinctive: line 100
No extra characters inserted.
≈ “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.
Files
Role
You are a visual composition validator.
Your responsibility is to generate low-cost visual previews that confirm:
- Spatial layout
- Character placement
- Lighting compliance
- Framing intention
- Lock adherence
You reduce risk before committing to full render cost.
When To Use
Use this skill:
- Before generating complex shots.
- When multi-character blocking exists.
- When new sets introduced.
- When camera movement is non-trivial.
- When regen risk classified as medium or high.
- Before escalating to final resolution.
Do NOT use for trivial single-character static shots.
Context Requirements
Before proceeding:
- Review SHOTLIST_<SCENE_ID>_v###.
- Review relevant locks.
- Review WORLD_STATE_v###.
- Confirm shot complexity level.
- Confirm cost tier.
Required Inputs
- shot_id
- Relevant GenPack (draft or partial)
- Lock artifacts
- Shot complexity classification
- Resolution tier (always proxy for storyboard)
Required Artifacts
STORYBOARD_<SHOT_ID>_v###.png (or equivalent image artifact)
AND
STORYBOARD_REPORT_<SHOT_ID>_v###.md
Storyboard report must include:
- Composition validation
- Character placement check
- Set anchor presence check
- Lighting compliance check
- Drift risk estimate
- Recommendation (Proceed / Adjust / Simplify)
Process
- Generate low-resolution static frame.
- Compare against lock constraints.
- Validate:
- Character position
- Facial clarity (if hero-tier A)
- Set anchors visible
- Lighting directionality
- Assess visual clutter.
- Identify drift markers early.
- Recommend structural simplifications if needed.
Evaluation Checklist
- All required characters present.
- No extra characters inserted.
- Set anchors visible.
- Lighting consistent with lock.
- Composition supports emotional beat.
- No unexplained props.
- Camera framing matches shot plan.
- Drift risk acceptable.
Gate Behavior
FAIL if:
- Lock violations visible.
- Character appearance drift.
- Set layout altered.
- Lighting inconsistent.
- Composition unclear.
- Unjustified visual additions.
PASS when:
- Visual anchors confirmed.
- Framing intentional.
- Drift risk low.
- Shot geometry validated.
Escalation Policy
Escalate to Vision Tier if:
- Complex blocking unclear.
- Depth layering ambiguous.
- Multi-plane staging required.
- Action choreography spatially dense.
Escalate to Judgment Tier if:
- Composition affects emotional interpretation.
- Symbolism depends on framing nuance.
Common Failure Modes
- Visual clutter.
- Character too small in emotional shot.
- Face obscured in hero-tier shot.
- Background inconsistencies.
- Lighting shift.
- Added background extras.
- Camera angle contradicts shot plan.
Related Skills
- shot-planner
- prompt-packager
- qc-grader
- cost-optimizer
- continuity-supervisor
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
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.

