gooseworks-ai/goose-skills / skills/video/render-street-interview
render-street-interview
VerifiedWrite a street-interview ad from a complete inspected commercial interaction and current brand facts. Render product guessing, or prepare mic-only, prepared-sample or visible-task conversation script/prompt previews. Premise, actions and ad connection vary; capture rules stay fixed. Conversation media delivery is unverified.
TAKES.md
View on GitHub# Project take-ledger guidance
**Summary.** Keep approved takes and their measured or reported limitations in the
project they belong to. Shared skill instructions describe the checks; they do not
carry a client's take history. A seed alone is not a quality or reproducibility guarantee.
## Record the actual run
For each take, retain its media and generation manifest together. Record:
- Brand, exact product, project and take identifier.
- Provider, model and revision when available, seed, prompt version and exact prompt.
- Input reference assets and the generation request identifier when available.
- Measured successes, defects and frame or audio timestamps.
- Approval scope: which properties were reviewed and which remain unverified.
- Source and inspection status for observations reported by someone else.
Mark missing run details as unknown. Do not invent scale measurements or treat reported
frame references as measured defect boundaries. Keep successes and limitations together.
## Reuse within the selected project
Inspect the actual media before reusing it. Check product scale and fidelity, visible
print, handling, faces, the complete spoken read, location and ambience. Use that project's
own evidence; another brand's seed or result does not establish suitability.
Preserve approved media bytes, exact dialogue and the original manifest. Changed prompts
or inputs need a distinct take record and quality review. A new seed or prior approval
does not authorize a paid re-roll; follow the current run's spending approval.
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: 323k | 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: 323k | 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: 323k | Updated | Claude CodeCodex | Verified | Install |