papperrollinggery/Paperrolling-DIRcreative-SKILL / skills/dircreative
dircreative
VerifiedUse 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.
routes/delivery-audit.md
View on GitHub# Delivery Audit Route Card
Use only when real generation, a formal asset/version handoff, client-visible
delivery, or a validated Specialist Exchange is actually in scope.
## Budget
- Load this card and no more than two route-specific references.
- Add evidence only for a real side effect or completion claim.
- Keep one state owner: DIR in standalone work, ADCO in an exchange.
- Operational detail may expand here, but the requested asset or decision still
leads the response.
## Execution
1. Re-read the current artifact and only its direct inputs before a completion
claim.
2. For whole-film generation, require the active visual asset matrix and verify
that it covers every scene, approved shot, director-storyboard cell, and
generation unit. If it is absent, derive it before calling a media tool. A
representative smoke set cannot satisfy this scope.
3. Resolve the one remaining external gate only if the user's current instruction
has not already supplied that authorization.
4. Check rights, exact execution surface, references, claims, continuity, and
output identity in proportion to the action.
5. Hash and version only actual delivery inputs and outputs. Do not bind unrelated
control-plane fields or historical project debt.
6. Validate the scoped deliverable first. Report unrelated global debt separately
and never convert it into a failure of an independent scoped result.
7. For ADCO, execute inline, forbid nested dispatch, and return domain output plus
domain QA. ADCO retains host truth, versions, adoption, client readiness, and
completion ownership.
Legacy v1 records are read-only evidence. They never become the checklist for a
new v2 delivery.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |