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.
tests/fixtures/episodes/grimwater-ep1.json
View on GitHub{
"_comment": "The FIRST multi-take episode on this format, and it breaks the rule SKILL.md opens with. Critical knowledge 1 says ONE generation per video, never assembled, and that rule is not wrong: it was paid for by five rejections caused by stitching. It is scoped to a SINGLE-TAKE cut. An episode is a different object and the operator approved it explicitly for this run, so the guards move rather than disappear: every take must be one generation with its manifest on disk, every take must be the same model, and every take's prompt must carry the IDENTICAL location clause. check-cut.py's check C enforces all three and still fails a cut with a missing manifest. See SKILL.md 'Critical knowledge 24'.",
"episode": "ep1",
"brand": "Grimwater",
"slug": "gw",
"title": "What's in the can",
"_output_comment": "The output name carries all three seeds ON PURPOSE. build_looks.py's look filenames do not carry a seed, and on 2026-09-30 a seed-4816 build silently overwrote street-gw-clean.mp4, which was seed 4815's shipped deliverable. A name that cannot collide is free.",
"output": "episode-gw-ep1-seed4817-4818-4819",
"takes": [
"grimwater-4817",
"grimwater-4818",
"grimwater-4819"
],
"brand_layer": {
"logo": "assets/grimwater/logos/grimwater-logo-3840.png",
"end_card": [
"NOTHING TO FEAR.",
"IT'S ONLY WATER."
]
},
"_grade_comment": "Not stored. The episode is graded ONCE on the concatenated cut, and the black lift is solved against that file by fit_grade.py at build time (--black-lift, or --fit to solve it here). A grade constant measured on one take outlives the take it was measured on: that is SKILL.md Critical knowledge 19, and the ambience gap made the identical mistake before it (Critical knowledge 13). Grading each take separately would also be wrong for a different reason - three different curves across three joins is a visible step.",
"_ambience_comment": "Not stored either, for the same reason, and this one has bitten twice (Critical knowledge 13 and 21a): the speech-free window belongs to a FILE. build_episode.py finds it on the finished concatenation with the envelope detector and asserts it is speech-free before cutting a bed or an end-card room tone from it."
}
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 |