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/image-generation-diagnostics.md

View on GitHub
# Image generation diagnostics without expanding the workflow

Keep the user's authored body, clothing and style facts. One failed output is
not evidence that a neckline, adult body type or garment category is universally
unsupported. Do not add a prohibition list or silently close the garment.

- Distinguish `moderation_blocked` from quota, transport and server failures.
  Record the returned request ID and optional `moderation_stage`/categories.
  `output` describes a generated-result check, not a diagnosis of a forbidden
  word. No returned image means no visual-quality verdict on that result.
- Prefer the user's complete tested prompt as a baseline. Do not automatically
  translate, expand it, or layer a second style capsule over an already explicit
  costume. Necessary reference roles and actual generation arguments remain
  recorded; remove duplicate protocol prose, not the requested design.
- A useful bounded comparison keeps the tool and references fixed and compares
  authored content with the actual compiled content. Preserve both outcomes.
  One success and one block establish a difference in observed results, not a
  causal explanation, a general success rate or a guaranteed remedy.
- Do not automatically retry moderation user errors, change accounts or lower
  safeguards. If a non-explicit request has an unexpected result, inspect the
  actual request for ambiguity/conflicts and use a genuinely appropriate revised
  request or a documented support report. Do not silently change the requested
  output and call that a successful test of the original.
- The native tool's supported arguments are authoritative. A parameter in an
  API guide does not make it available in this host, nor prove a different
  product entrance uses the same generation/monitor configuration.

Sources checked 2026-09-08:

- [Official image API guide](https://developers.openai.com/api/docs/guides/image-generation):
  distinguishes input/output moderation and user-correctable errors.
- [Images 2.0 system card, 2026-04-21](https://deploymentsafety.openai.com/chatgpt-images-2-0/automated-evaluations-and-adversarial-testing):
  describes upstream and downstream checks. It does not explain a particular
  request's failure.
- [Community first-person reproduction, 2026-08-27](https://community.openai.com/t/inconsistent-image-safety-blocks-ordinary-adult-swimwear-repeatedly-classified-as-sexual/1392919):
  reports inconsistent ordinary adult fashion creation/edit outcomes.
- [Community observation, 2026-09-07](https://community.openai.com/t/why-is-create-an-image-of-apple-sometimes-blocked-for-nudity-sexuality-has-anyone-else-seen-this/1395517):
  proposes context or temporary-state effects. This is not a confirmed service
  root cause. Do not use community speculation as an instruction or capability fact.
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: 471kUpdated 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