Skip to content

papperrollinggery/Paperrolling-DIRcreative-SKILL / skills/dircreative

dircreative

Verified

Use after explicit $dircreative for film concepts, stories, scripts, director or creative groups, shot/asset planning, reference-video analysis, and image/video prompts. Real media execution requires the corresponding authorization. Validated ADCO handoffs are supported. DIRcreative source maintenance is outside this Skill.

FileKindSize
SKILL.mdskill md8.3 KB
agents/openai.yamlconfig239 B
assets/visualizations/decision-surface.cssother18.4 KB
assets/visualizations/decision-surface.jsscript32.6 KB
assets/visualizations/stage-surface-registry.jsonconfig7.2 KB
references/asset-foundation-pass.mdmarkdown5.3 KB
references/character-master-sheet.mdmarkdown21.5 KB
references/client-story.mdmarkdown2.3 KB
references/copy-script.mdmarkdown3.7 KB
references/film-development.mdmarkdown8.3 KB
references/generation-delivery.mdmarkdown8.6 KB
references/humanization-workflow.mdmarkdown14.2 KB
references/image-execution.mdmarkdown20.5 KB
references/image-generation-diagnostics.mdmarkdown2.8 KB
references/product-cg-direction.mdmarkdown9.7 KB
references/product-cg/capsules/elastic-fiber-cg.jsonconfig4.8 KB
references/product-cg/capsules/graphic-modular-cg.jsonconfig4.9 KB
references/product-cg/capsules/pastel-dry-powder-cg.jsonconfig5.7 KB
references/product-cg/capsules/precision-hard-surface-cg.jsonconfig4.9 KB
references/product-cg/capsules/sculptural-luxury-cg.jsonconfig4.8 KB
references/product-cg/capsules/viscous-sensory-cg.jsonconfig4.8 KB
references/product-cg/catalog.jsonconfig3.9 KB
references/project-hygiene.mdmarkdown2.7 KB
references/prompt-model.mdmarkdown3.9 KB
references/prompt-structure.mdmarkdown15.7 KB
references/script-to-seedance.mdmarkdown13.1 KB
references/shot-development.mdmarkdown8.0 KB
references/shot-storyboard.mdmarkdown3.2 KB
references/spatial-discussion.mdmarkdown10.0 KB
references/specialist-exchange.mdmarkdown2.3 KB
references/storyboard-coverage.mdmarkdown8.8 KB
references/storyboard-frame-to-jingzao.mdmarkdown12.5 KB
references/storyboard-motion-planning.mdmarkdown8.1 KB
references/video-distillation.mdmarkdown7.2 KB
references/video-quality-prefix.mdmarkdown2.5 KB
references/visual-asset-to-jingzao.mdmarkdown5.6 KB
references/visual-skill-stack.mdmarkdown13.1 KB
routes/delivery-audit.mdmarkdown1.7 KB
routes/fast-task.mdmarkdown1.2 KB
routes/studio-development.mdmarkdown2.4 KB
runtime/review-trust-registry.jsonconfig102 B
runtime/routing-policy.yamlconfig10.6 KB
runtime/state-snapshot.schema.jsonconfig7.3 KB
runtime/visual-asset-plan.schema.jsonconfig15.1 KB
runtime/visual-skill-policy.jsonconfig36.2 KB

references/shot-storyboard.md

View on GitHub
# Shot and Storyboard Craft

Use this card to improve one shot or review a small storyboard set. Lead with the
revised shot card or the highest-impact findings, not a process preamble.

## Review order

1. Narrative purpose: what changes in this shot, and why must the audience see it?
2. Visible action: one readable causal task per shot; a generation unit may join
   connected shots/phases within the selected model's tested capacity.
3. Camera logic: size, angle, lens intent, support, and a movement with a physical
   start target and end target.
4. Blocking: subject start, path, end, eyeline, screen direction, and axis when
   continuity depends on them.
5. Composition: foreground/midground/background, subject hierarchy, movement
   room, readable face/product/text zone, and what stays locked during motion.
6. Sound and edit: dialogue/VO, ambience, SFX, music or silence, plus the cut or
   transition motivation.
7. Continuity and model risk: identity, wardrobe, prop hand, product orientation,
   geography, lighting, state changes, likely model misread, and whether to split.

## Useful shot-card shape

```text
S03 00:08-00:12 | <narrative purpose>
Frame/camera: <size, angle, lens intent, support, start -> end>
Blocking/action: <subject start -> path/action -> end, eyeline/axis>
Composition/light: <layers, hierarchy, readable zone, light change>
Continuity: <identity, prop, direction, state locks>
Sound/edit: <audio layers and cut point>
Model risk: <likely misread and smallest prevention/split rule>
```

For a review, rank only material problems, explain their audience or production
impact, and provide a concrete replacement. Do not turn a few frames into a full
project gate. Do not invent missing wardrobe, product, location, or source facts;
mark the exact unknown that changes the shot.

A scene reference is not a storyboard. A shot may need several action panels;
a hard-cut reverse angle is a different shot. For explicit detailed/full
preproduction, use the panel-coverage stage described in `storyboard-coverage.md`.
Keep planned panels separate from actual PNGs and from clean model-input roles.

## Narrative frames and transition proof

For nine-grid or frame-content work, keep these columns distinct:

- `View`: visible action, object, UI node, or composition;
- `Storyline`: the claim this frame proves and the meaning it hands to the next;
- actual `SUPER`: supplied on-screen copy only;
- `UI/data`: supplied interface or fact evidence only;
- proposal brand line: creative copy, clearly labeled as a proposal.

Do not replace `Storyline` with a pan, push-in, lens, or camera instruction.
L1/L2/L3 and pending claims stay with ADCO/client evidence; never creatively
complete an algorithm, parameter, timing, capability, or product owner.

A Match Cut is `verified` only when both boundary frames exist and geometry,
subject position, subject size, direction, speed, and the visual anchor can be
compared. If either frame is missing—or any comparison is only an intention—mark
it `candidate` or `unverified`. Decodable images plus caller-authored comparison
metadata are still not visual proof: the current local validator remains
`unverified` until a separate trusted host/human image readback is hash-bound to
both frames. A transition label or renderer PASS is not proof.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall