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/test_cast_advice.py
View on GitHub"""The cast advisory (2026-10-13): thin or copied cast descriptions bring back the same
faces in every brand's video. Advice only: it must never block a take or change a prompt.
Free: no network."""
import copy
import pathlib
import sys
import unittest
SCRIPTS = pathlib.Path(__file__).resolve().parents[1] / "scripts"
sys.path.insert(0, str(SCRIPTS))
import brandkit # noqa: E402
import format_spec # noqa: E402
FULL = ("a stocky Black man in his late thirties with a short greying beard and a shaved head, "
"in a plain grey jumper, with a plain rucksack on one shoulder")
FULL_2 = ("a tall, thin South Asian woman in her sixties with a long grey plait, in a plain navy "
"coat, with an umbrella")
THIN = "a man in his thirties, grey hoodie, with a plain rucksack"
def cfg():
return brandkit.load("oleara-ep1-a2")
class CastAdviceTests(unittest.TestCase):
def test_a_thin_person_is_named_with_what_is_missing(self):
notes = brandkit.cast_advice(cfg())
self.assertTrue(any("shot 1" in n and "hair" in n and "build" in n for n in notes), notes)
self.assertTrue(any("all-white corner" in n for n in notes), notes)
def test_a_fully_written_cast_gets_no_advice(self):
c = cfg()
c["shots"][0]["subject"], c["shots"][2]["subject"] = FULL, FULL_2
self.assertEqual(brandkit.cast_advice(c), [])
def test_a_person_copied_from_another_brand_is_flagged(self):
c = cfg()
c["shots"][0]["subject"], c["shots"][2]["subject"] = FULL, FULL_2
notes = brandkit.cast_advice(c, other_subjects=[FULL.upper()])
self.assertEqual(len(notes), 1, notes)
self.assertIn("another brand", notes[0])
def test_the_same_person_twice_in_one_cast_is_flagged(self):
c = cfg()
c["shots"][0]["subject"] = c["shots"][2]["subject"] = FULL
self.assertTrue(any("repeats shot 1" in n for n in brandkit.cast_advice(c)))
def test_advice_never_blocks_validation_or_changes_the_prompt(self):
c = cfg()
brandkit.validate(copy.deepcopy(c)) # a thin cast still validates
flags = dict(pace=True, guards=True, plain=True, upright=True, one_mic=True, prompt_version=2)
before = format_spec.build_prompt(copy.deepcopy(c), **flags)
brandkit.cast_advice(c, brandkit.other_subjects(c))
self.assertEqual(format_spec.build_prompt(c, **flags), before)
def test_other_subjects_leaves_out_the_brands_own_configs(self):
c = cfg()
own = {s["subject"] for s in c["shots"] if s.get("subject")}
others = set(brandkit.other_subjects(c))
self.assertTrue(others)
self.assertIn(THIN, own)
# another Oleara config may share it, but no other BRAND's list may supply it
self.assertNotIn(THIN, others)
def test_a_garment_or_bag_that_draws_a_logo_is_named(self):
c = cfg()
c["shots"][0]["subject"] = FULL.replace("jumper", "hoodie")
c["shots"][2]["subject"] = FULL_2.replace("an umbrella", "a plain shopping bag")
notes = brandkit.cast_advice(c)
self.assertTrue(any("shot 1" in n and "hoodie" in n and "logo" in n for n in notes), notes)
self.assertTrue(any("shot 3" in n and "shopping bag" in n for n in notes), notes)
def test_a_cape_is_not_a_cap(self):
c = cfg()
c["shots"][0]["subject"], c["shots"][2]["subject"] = FULL + ", capable hands", FULL_2
self.assertEqual(brandkit.cast_advice(c), [])
def test_conversation_mode_has_no_cast_advice(self):
self.assertEqual(brandkit.cast_advice({"mode": "conversation", "shots": []}), [])
if __name__ == "__main__":
unittest.main()
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 |