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.
references/street-reference-library.json
View on GitHub{
"schema_version": "street-reference-library.v2",
"summary": "Source leads and compact observations. A seed snippet is not sufficient ad-writing context: inspect the complete commercial clip and keep full/private transcripts project-scoped.",
"references": [
{
"id": "proteva-street-1",
"format": "street-interview",
"dialogue_mode": "street-interview",
"execution_modes": [
"product-guess"
],
"language": "en",
"audience_groups": [
"consumer"
],
"buying_contexts": [
"product-discovery"
],
"brand_id": "proteva",
"commercial": true,
"origin": "seed",
"observed": true,
"observed_scope": "transcript",
"source": "assets/reference-ads/proteva-street-1.mp4",
"asset_sha256": "49a2df5ec349ff722b113897eddefa80c833d66d6829dfee39911feae8f5f645",
"observed_at": "2026-10-02",
"observation_method": "faster-whisper base.en ASR and sampled frames at 0/5/12/20/30 seconds; speaker functions inferred from exchange and frames",
"speaker_turns": [
{
"speaker": "interviewer",
"does": "asks participants to identify flavours after tasting"
},
{
"speaker": "participants",
"does": "give short, different guesses rather than reciting specs"
},
{
"speaker": "interviewer",
"does": "reveals an unexpected common source"
},
{
"speaker": "participant",
"does": "acknowledges the explanation briefly"
}
],
"transfer_rule": "Let a real observable test produce the answer; transfer the reveal sequence, not protein claims or scripted endorsement.",
"authorship": "unknown",
"limitations": "Workspace source video, exact public ad id unavailable. ASR can mishear words. Sampled frames are not full delivery review; pauses and vocal naturalness were not listened to. No conversion or author-credit evidence. Product facts do not transfer. The stored turns are partial; inspect the complete clip before using it to write an ad.",
"use_status": "needs-full-context",
"inspection": {
"coverage": "partial",
"modalities": [
"transcript"
],
"method": "faster-whisper base.en ASR and sampled frames at 0/5/12/20/30 seconds; speaker functions inferred from exchange and frames"
}
},
{
"id": "proteva-street-2",
"format": "street-interview",
"dialogue_mode": "street-interview",
"execution_modes": [
"conversation"
],
"language": "en",
"audience_groups": [
"consumer"
],
"buying_contexts": [
"everyday-friction"
],
"brand_id": "proteva",
"commercial": true,
"origin": "seed",
"observed": true,
"observed_scope": "transcript",
"source": "assets/reference-ads/proteva-street-2.mp4",
"asset_sha256": "f8b04677f16d3a026ee0930c366cd5605a2a498689a822615fb87ae61dc10adf",
"observed_at": "2026-10-02",
"observation_method": "faster-whisper base.en ASR and sampled frames at 0/5/12/20/30 seconds; speaker functions inferred from exchange and frames",
"speaker_turns": [
{
"speaker": "interviewer",
"does": "asks how many flavours the participant already keeps at home",
"excerpt": "How many different flavors of protein powder do you have at home?"
},
{
"speaker": "participant",
"does": "answers with a number and adds a storage detail",
"excerpt": "Probably have three different flavors. It's kind of like taking up a whole cabinet."
},
{
"speaker": "interviewer",
"does": "connects that specific storage issue to the proposed product"
},
{
"speaker": "participant",
"does": "responds to the explanation and chooses a flavour"
}
],
"transfer_rule": "The edited ad begins with a later taste reaction. Inspect the visible sampling setup, earned follow-ups and full product connection before adapting; a routine-question snippet alone loses the ad mechanism.",
"authorship": "unknown",
"limitations": "Workspace source video, exact public ad id unavailable. ASR can mishear words. Sampled frames are not full delivery review; pauses and vocal naturalness were not listened to. No conversion or author-credit evidence. Product facts do not transfer. The stored turns are partial; inspect the complete clip before using it to write an ad.",
"use_status": "needs-full-context",
"inspection": {
"coverage": "partial",
"modalities": [
"transcript"
],
"method": "faster-whisper base.en ASR and sampled frames at 0/5/12/20/30 seconds; speaker functions inferred from exchange and frames"
}
},
{
"id": "tal-night-market",
"format": "street-interview",
"dialogue_mode": "street-interview",
"execution_modes": [
"conversation"
],
"language": "en",
"audience_groups": [
"workplace",
"consumer"
],
"buying_contexts": [
"everyday-friction",
"work-routine"
],
"commercial": false,
"origin": "seed",
"observed": true,
"observed_scope": "transcript",
"source": "https://www.thisamericanlife.org/395/transcript",
"observed_at": "2026-10-02",
"speaker_turns": [
{
"speaker": "Henry",
"does": "mentions his dislike of daytime during an overnight work exchange"
},
{
"speaker": "Adam",
"does": "repeats the unexpected detail as a clarification",
"excerpt": "Wait, you hate the day?"
},
{
"speaker": "Henry",
"does": "confirms rather than supplying a prepared explanation",
"excerpt": "Oh, I hate it."
},
{
"speaker": "Adam",
"does": "asks specifically about that dislike",
"excerpt": "What do you hate about the day?"
}
],
"transfer_rule": "An unexpected detail in the answer causes the next question. Do not force agreement, a perfect punchline or a sales request.",
"authorship": "publisher-attributed real field exchange; unscripted-authorship details unknown",
"limitations": "Editorial overnight-market interview, not an ad. Transcript only; no delivery or commercial performance inference. Transfer turn mechanics only.",
"use_status": "excluded",
"exclusion_reason": "Operator rejected this editorial radio excerpt as an ad-writing reference; it lacks an understandable commercial setup and payoff."
}
]
}
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 | Unverified | 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 |