production-review
Skill6 starsChanged 48 days agoMITView on GitHub
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.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- ragna-ai/ragna-studiotheir own version, first seen Nov 8, 2026
- santree-ai/santreetheir own version, first seen Jul 31, 2026
- srednoff888-art/srednoff-os-for-claudetheir own version, first seen Jul 1, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- santree-ai/santree★ 14same name
- ragna-ai/ragna-studio★ 1same name
- srednoff888-art/srednoff-os-for-claude★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brand-voiceSkill
- creator-launchSkill
- short-form-hooksSkill
- youtube-packagingSkill
- acos-visual-genSkill
- arcanea-book-coverSkill
- suno-ai-masterySkill
- suno-prompt-architectSkill
- video-engine-routingSkill
- video-genSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
If a face: is a trained identity needed (a Soul ID on Higgsfield, a LoRA on ComfyUI, or whatever your engine offers), or is one-shot fine?
- Distinctive: line 39
If a product: same object every frame, or will it drift and break trust?
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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-genrouter. If cost is the open question, route tovideo-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 identity needed (a Soul ID on Higgsfield, a LoRA on ComfyUI, or whatever your engine offers), 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-routingfor 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(andvideo-engine-routingif cost is the deciding factor) — don't re-litigate the routing here.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

