Production Review
A user-invoked review. The user types for it. Your job is to grill a content or video plan before a single credit is spent. Generation is cheap per clip and ruinous in aggregate when the brief was wrong. Catch the wrong brief here, not after 40 renders.
You are interrogating four things. Be direct. A weak hook is a weak hook.
How to run it
- Get the brief: what's being made, for whom, where it's going. If the user can't say the hook in one sentence, that's the first finding.
- Interrogate the four dimensions below, one at a time. Push back where it's soft.
- Score each GO / SOFT / KILL with the reason.
- Deliver the verdict and, if GO, hand the concrete engine + pipeline recommendation to the
video-gen router. If cost is the open question, route to video-engine-routing.
The four interrogations
1. Hook — the first two seconds
- State the hook in one sentence. Would it stop the scroll for the target viewer?
- What happens in second 0–2 on screen? If it's a logo or a slow pan, it's dead.
- Is there a reason to keep watching at second 3?
KILL if the hook can't be said in a sentence or the open is a warm-up.
2. Destination fit
- Where does this go — feed, Shorts/Reels, YouTube, listing, ad? Aspect ratio and length to match?
- Does the format fit the platform's norms, or is it a landscape talking-head being forced into vertical?
- One asset for many destinations, or the right cut per destination?
SOFT if format and destination don't match; name the reframe.
3. Identity & consistency
- Does anything need to stay consistent across shots — a face, a product, a character?
- If a face: is a trained Soul identity needed (→
higgsfield-soul-id), or is one-shot fine?
- If a product: same object every frame, or will it drift and break trust?
Flag the consistency requirement so the router picks the right engine, not a cheaper one that drifts.
4. Cost & scale
- How many generations does this brief actually imply (variations × shots × retries)?
- Which engine, at what per-clip cost, and does that fit the budget for the expected return?
- Is this a one-off (subscription credits fine) or a repeatable batch (→
video-engine-routing for the graduation call)?
KILL if the expected cost outweighs the plausible return; say so before the spend, not after.
The verdict
PRODUCTION REVIEW — <one-line brief>
| Dimension | Verdict | Why |
|------------------------|----------|-----|
| Hook (first 2s) | GO/SOFT/KILL | ... |
| Destination fit | GO/SOFT/KILL | ... |
| Identity & consistency | GO/SOFT/KILL | ... |
| Cost & scale | GO/SOFT/KILL | ... |
CALL: generate / rework / drop — <one honest sentence>
IF GENERATE → route: <engine + pipeline for video-gen>, est. cost <n>
Rules
- Say the hook out loud or it doesn't exist.
- A SOFT is a rework instruction, not a maybe — name the specific fix.
- Protect the credits. "Drop it" before a bad spend is a win, not a failure.
- On GO, hand off cleanly to
video-gen (and video-engine-routing if cost is the deciding factor) — don't re-litigate the routing here.
1---2name: production-review3description: Use when the user asks to review or pressure-test a video / content plan BEFORE generating it — triggers include "review my video plan", "is this worth generating", "pre-flight my shoot", "grill my content idea", "will this convert", "should I spend credits on this". Grills the brief for hook, destination-fit, identity-consistency, and cost, then hands a go / rework verdict to the video-gen router.4---56# Production Review78A user-invoked review. The user types for it. Your job is to **grill a content or video plan before a single credit is spent.** Generation is cheap per clip and ruinous in aggregate when the brief was wrong. Catch the wrong brief here, not after 40 renders.910You are interrogating four things. Be direct. A weak hook is a weak hook.1112## How to run it13141. Get the brief: what's being made, for whom, where it's going. If the user can't say the hook in one sentence, that's the first finding.152. Interrogate the four dimensions below, one at a time. Push back where it's soft.163. Score each GO / SOFT / KILL with the reason.174. Deliver the verdict and, if GO, hand the concrete engine + pipeline recommendation to the `video-gen` router. If cost is the open question, route to `video-engine-routing`.1819## The four interrogations2021### 1. Hook — the first two seconds22- State the hook in one sentence. Would it stop the scroll for the target viewer?23- What happens in second 0–2 on screen? If it's a logo or a slow pan, it's dead.24- Is there a reason to keep watching at second 3?2526KILL if the hook can't be said in a sentence or the open is a warm-up.2728### 2. Destination fit29- Where does this go — feed, Shorts/Reels, YouTube, listing, ad? Aspect ratio and length to match?30- Does the format fit the platform's norms, or is it a landscape talking-head being forced into vertical?31- One asset for many destinations, or the right cut per destination?3233SOFT if format and destination don't match; name the reframe.3435### 3. Identity & consistency36- Does anything need to stay consistent across shots — a face, a product, a character?37- If a face: is a trained Soul identity needed (→ `higgsfield-soul-id`), or is one-shot fine?38- If a product: same object every frame, or will it drift and break trust?3940Flag the consistency requirement so the router picks the right engine, not a cheaper one that drifts.4142### 4. Cost & scale43- How many generations does this brief actually imply (variations × shots × retries)?44- Which engine, at what per-clip cost, and does that fit the budget for the expected return?45- Is this a one-off (subscription credits fine) or a repeatable batch (→ `video-engine-routing` for the graduation call)?4647KILL if the expected cost outweighs the plausible return; say so before the spend, not after.4849## The verdict5051```52PRODUCTION REVIEW — <one-line brief>5354| Dimension | Verdict | Why |55|------------------------|----------|-----|56| Hook (first 2s) | GO/SOFT/KILL | ... |57| Destination fit | GO/SOFT/KILL | ... |58| Identity & consistency | GO/SOFT/KILL | ... |59| Cost & scale | GO/SOFT/KILL | ... |6061CALL: generate / rework / drop — <one honest sentence>62IF GENERATE → route: <engine + pipeline for video-gen>, est. cost <n>63```6465## Rules6667- Say the hook out loud or it doesn't exist.68- A SOFT is a rework instruction, not a maybe — name the specific fix.69- Protect the credits. "Drop it" before a bad spend is a win, not a failure.70- On GO, hand off cleanly to `video-gen` (and `video-engine-routing` if cost is the deciding factor) — don't re-litigate the routing here.
frankxai