{"id":16529,"plugin_id":"plugins_6a50b49006148191a10a308fbfb6bf7c","kind":"skill","collection_source":null,"comparison_source":null,"observed_at":"2026-09-30T23:13:29.877Z","digest":"605364e729bbf832cc81a10952863ae6c8df17905153b8ab7f8fa2d0fac6925b","against":null,"payload":{"description":"Street interview: a question-and-answer encounter on location with interviewer, guest and shared views, timed reveals such as an answer strip or emoji board, reaction cuts and readable captions per speaker.","included_files":[{"relative_path":"agents/openai.yaml","size_in_bytes":323},{"relative_path":"references/reveal-board.md","size_in_bytes":1729}],"name":"pixverse-street-interview","skill_md_contents":"---\nname: pixverse-street-interview\ndescription: \"Street interview: a question-and-answer encounter on location with interviewer, guest and shared views, timed reveals such as an answer strip or emoji board, reaction cuts and readable captions per speaker.\"\n---\n\n# Street Interview\n\nWhen this workflow generates images or video, apply `../../skills-shared/quality-policy.md`:\nSunburst 2K/high for images, Seedance 2.5 1080p with automatic prompt enhancement for video,\nand a stopped upgrade/fallback choice for Free/Basic or model-entitlement rejection.\n\nA motivated encounter: someone stops someone, asks a question, and the answers arrive as\nreveals the audience collects. The picture alternates interviewer, guest and shared views;\nan answer strip or emoji board fills in on the spoken words; captions identify speakers.\n\n## Installed Command\n\nBefore running helper commands, resolve the absolute plugin root from this `./SKILL.md` path: it is two directories above this skill directory and contains `.codex-plugin/plugin.json`. In every new shell session, set:\n\n```bash\nPVX=\"<absolute-plugin-root>/scripts/pvx\"\n```\n\nRun helper commands through `\"${PVX}\"`. Do not assume the user's current working directory is the plugin checkout, and do not bypass the installed wrapper with a module invocation.\n\n## Set Up The Encounter\n\nResolve the location, the interviewer (often off-camera or a mic-holding hand), the guest,\nthe question and the list of answers. Give the encounter a reason: something the guest has\nor did that makes the question worth asking. Generate the guest's location portrait with the\nphone-capture kit (`../../skills-shared/prompt-kits.md`), then complementary views: a\ntwo-shot over the interviewer's shoulder, a tighter guest view for answers, an environment\nview that shows the motivating detail. Real places and people come from supplied material.\n\n## Script The Reveals\n\nUse `../../skills-shared/semantic-script.md`: `ASKER:` and `GUEST:` turns, a moment on each\nanswer word (`@{rule-one!}Manifest.`), selections around the guest's explanations for\nreaction cuts, cue breaks that isolate the answer words so captions land them alone. Measure\nsegments; keep each answer in its own 5–8 second take so a retake never touches accepted ones.\n\n## Generate\n\nSeedance 2.5 reference takes through the gateway with the guest image, the two-shot image\nfor shared views and a voice reference per speaker. Direct the physical exchange: the mic\nenters from the interviewer's side, the guest looks slightly off-lens toward the asker,\nreactions are small and quick. Handheld energy is welcome; keep the guest's framing region\nstable so the strip and captions have a home.\n\n## Compose\n\nAlign (`../../skills-shared/word-timing.md`) and render with a plan\n(`../../skills-shared/anchored-composition.md`): a `reveal-strip` component whose states\nreveal one slot per answer moment, `ding` or `pop` sounds on the same moments, captions with\n`role_colors` per speaker, an environment still cut in on the motivating detail, a final\n`label` summarizing the answers if the format wants it. Read `./references/reveal-board.md`\nfor the strip and reaction timing.\n\nCheck that each slot reveals on its word, reaction cuts return before the next answer, and\ncaptions never cover the strip. Deliver the clip with script, timeline, plan and graphics;\nnew guests, languages or answer sets are variants (`../pixverse-video-variants/SKILL.md`).\n\n## Execution\n\nRead `../../skills-shared/production-brief.md` for reference roles, prompt construction and revisions.\nFor media execution, follow `../../skills-shared/cli-workflow.md`; load the gateway before manual\nCLI commands or queue specs. Local media, script, timeline and graphics commands spend no credits.\nPrompt-only work ends with the usable plan and prompts; it needs no account or generation calls.\n"},"changes":[],"summary":"First saved snapshot. No earlier version is available for comparison.","summary_kind":"deterministic","summary_metadata":{}}