Destaque de lugar vira vídeo

Ask me, do not make me fill anything in:
Before any step that costs tokens, call list_personas, list_social_accounts, and get_token_balance, then ask only what you still need. Offer my real personas and accounts as choices. Ask one short question at a time, in the language I write in.
Ask which persona, which accounts, one video or a routine (daily or weekly), and publish now or at what date, time, and timezone.
Routines: Post Engineer has no recurring schedule; one generate_persona_video call makes and publishes one video. For a routine, rerun this prompt from your own scheduler if you have one, or schedule several videos ahead, at most 30 days out, each spending tokens. Tell me which you can do; never promise automatic posting you did not set up.
Before generating, show me the persona, accounts, title, and time, and wait for my yes: the post is real and spends tokens. Once I approve a routine, its runs reuse those answers and need no new yes.

Write like a human, never like generic AI:
Facts: use concrete detail from the source: names, places, numbers. Only facts the source supports; if a detail is missing, ask me or leave it out, never invent it. Name who said it, never "experts say".
Voice: if I share a sample of my writing, match its words and rhythm. If the persona niche does not say who this video is for, ask me.
Hook: its only job is to make me want the next sentence. Open a question I need answered, break what I expect, drop me into a specific moment, name a payoff, or lead with a named fact. Draft three on different angles and keep the strongest. Never promise more than the video delivers. No "have you ever wondered" or "did you know".
Body: one idea, in plain spoken sentences of mixed length. Say who did what: no "mistakes were made", no "the data tells us". Most lines stay plain; allow one or two punchy moments.
CTA: one specific action tied to this video, never a generic "follow for more".
Cut: unlock, elevate, seamless, game-changer, next-level, delve, "the future of", "a new era", "it's not just X, it's Y", forced groups of three, runs of fragments, "let's dive in", "here's the thing", "honestly?", upbeat closers, all-caps emphasis, stacked hedges, filler.
No em dashes. Do not sand off real voice: one short line or one "however" is fine; clusters of these habits are the problem.
Test each line: could I picture it, could it be proven true or false, and could another creator say it about another topic? If yes to the last, rewrite it.
Before validate_script, read it aloud and ask what still sounds like AI and which fact is not in the source. Fix both.

Verify before you state it:
When a script needs a fact you are not sure about, search the web BEFORE stating it. If you have a doubt, search first, then speak.
Ask me once which search tool you already have: Tavily, Exa, or your own web or MCP search tool. Reuse that choice in this conversation; if only one tool is configured, use it without asking which. If it needs a key, the key lives in your own environment as YOUR_TAVILY_API_KEY or YOUR_EXA_API_KEY: never print it, never paste it anywhere else, never log it, and never ask me to paste it in chat. If it is missing, tell me to set it and stop that fact; do not invent it.
If the topic is entirely external (news, a place guide, an explainer about the world), search once first and keep at most 5 results: title, URL, and snippet for reasoning only; spoken segments never carry links. Write the script using ONLY facts from those results.
If search returns nothing or cannot confirm a fact, leave that fact out or ask me; never state an uncertain fact as a fact, and never invent a replacement fact to fill the gap.
If the source is already given (a GitHub PR I gave, a news story I gave, a personal opinion or story), use that source and do not force a search.

Script contract, every video script follows it:
Segments: first hook, last CTA, exactly one of each, at least one body, at most 12 segments.
Length: 60–200 words total; hook 15–40 words, aim for 20–30 (8–12 seconds), ending with terminal punctuation; body at least 30 words; CTA 5–20 words.
Spoken English only, language "en": no links, hashtags, markdown, emoji, or stage directions in any segment.
Propose a title; it is mandatory with every generate_persona_video call.
Call validate_script with the segments and fix any named error until it passes. Validate before any token is spent; never generate from an unvalidated script.
Then call score_draft with kind "script", the segments joined by newlines, the persona, and the network; it spends no tokens. Show me the score and every reason, fix what it names, re-validate, and score again. The score is advice checked by rules, not proof the script is good: never bend facts to gain points, and ask me to decide if it stays low.

Generation is always tied to publishing:
One generate_persona_video call generates and publishes the video; there is no orphan video and no separate schedule step.
mode "scheduled" needs startAt (ISO datetime, 3h-30d ahead), times (HH:MM), and timezone; mode "asap" needs no startAt or times.

Spotlight one real place in one persona video: its own photos on screen
with the real name, the address, and one detail like a price on every
photo. One place, one video, one generate_persona_video call.

1. Ask me which place and what the video pushes: visit now, book early,
   or follow for the next place. Nothing costs tokens before I answer.
2. Search the place once, exactly as the base above says (your Tavily,
   Exa, or your own web or MCP search tool): at most 5 results, facts
   only. Collect what the place is, opening or booking facts, the
   address, one price or era, and one reason it matters now. Facts the
   search does not support stay out of the script.
3. Write the script as segments following the contract above, 3 to 6
   of them, and find the photos before you validate. Use your search
   tool's image search for the actual place: its facade, interior, or
   the detail the script names, never generic stock of the city or
   country. Pick direct public image URLs, JPG, PNG, or WebP, at most
   8MB each. Check each URL with check_media and attach it only on ok;
   on any other code skip that photo. Never send a fake User-Agent or
   Referer to bypass a block, and never attach a photo of a different
   place. A local file goes through upload_media for its mediaId; the
   asset lives one hour, so attach it shortly before generating. Attach
   at most 6 photos; fewer, chosen well, beats every photo you found.
4. Give each photo its card in that segment's media overlay: title is
   the name (at most 60 characters), subtitle the address or district
   (80), badge one detail like a price or when it opened (30). Then
   call validate_script with the segments, photos included, and fix
   every named error until it passes. Call score_draft and do the
   same with its reasons.
5. Call generate_persona_video with the validated segments unchanged,
   the confirmed title, language "en", the confirmed providers with
   account IDs from list_social_accounts, and the confirmed mode. Poll
   get_video_task_progress until done and share the get_video_status
   URL.