The Shelf / Growth / Short-Form Video Growth Engine
Short-Form Video Growth Engine
Ready-to-shoot video ideas, scripts and a posting calendar that point people at your app. No camera.
The job: turn short video — TikTok, Reels, Shorts — into app installs, without ever standing in front of a camera. You tell it what your app is worth to people, who those people are, and what they struggle with. It hands back the whole plan: your video topics, a bank of opening lines, shot-by-shot scripts, captions, the route from video to install, and a dated calendar. It plans. You (or an editor) film.
Most short-form advice fails one of three ways. You post whenever you feel like it, hear nothing back, and blame the algorithm. You paste a "give me viral content" prompt into a chatbot and get openers that could be selling anything, which means they sell nothing. Or you buy a faceless-content course that names the video styles and leaves you to write every script yourself. All three skip the only part that matters: the opening line has to name your app's value and your user's actual problem, or it's noise in a crowded feed.
What's on the tag:
- Your 3 or 4 video topics, worked out from what your app is worth and what hurts without it — each one handed the style that proves it best (screen recording, hands and phone, words on screen), picked by what it has to prove, not by what's trending.
- A bank of opening lines: several per topic, each aimed at a real problem your app fixes, each short enough to land in the first three seconds.
- Scripts of 30 to 60 seconds, written shot by shot. Every shot names what to film, the words on screen, how long it runs, the kind of sound to use (never a named copyrighted track), and a reminder to keep the captions on screen, since most people watch with the sound off. No talent, no face.
- Captions and hashtags written separately for each platform, plus a real route from video to install: one trackable link in your bio, a pinned comment, and wording that matches your store listing.
- A dated 2-to-4-week calendar that groups the filming so you shoot once and post three places — and a way to read your numbers that tells you where you're losing people: the opening line, the call to action, or the listing.
Who it's issued to: indie operators who want installs from video and have no interest in being on camera, and small teams who want a posting system instead of a fresh script every Sunday night.
Why not a free content prompt? A free prompt writes one clever script and stops. This is a system — openers tied to your app, faceless styles, a calendar, and a rules check before you post (the TikTok disclosure toggle alone saves you a quiet drop in reach). It also says the part the hype merchants won't: posting short video for free is a grind, reach is falling, and nobody can promise you a hit. What it promises is a lot of good tries and a way to learn from them. It gets updated as the platforms move their limits, and the field report shows a full run before you pay.
Runs in Claude Code, claude.ai, or any assistant that can open a markdown file — that's a plain text file. No camera, no course.
FIELD REPORT real output, not a promise
Setup: the engine run end-to-end (SKILL.md Steps 0–7) for Dripwise, a fictional plant-care app — photo plant ID plus a personalized watering/fertilizing schedule — targeting anxious new plant parents who keep killing their plants, at 5 posts/week across TikTok/Reels/Shorts.
Honest frame, stated up front (the skill requires it): this is a repeatable system for many good at-bats, not a virality guarantee. Reach is falling industry-wide, reliable signal takes ~60–90 days of consistent posting, and no per-video reach or install number is promised.
Step 1 — Value ⇄ Pain matrix
| Value prop | Pain it kills | Trigger moment |
|---|---|---|
| Snap a photo → instant plant ID + care profile | Don't know what the plant is/needs | Bring home an untagged plant, zero info |
| Personalized watering schedule (species+light+pot+season) | Forget to water | Day 9, can't remember the last watering |
| Overwater/underwater symptom check-in | Overwater/underwater confusion | Leaves yellowing/drooping, no idea which way to correct |
| Personalized fertilizing schedule | Don't know what it needs (feeding) | Plant's alive but not growing, no idea why |
| Per-plant push reminders | Forget to water (at scale) | 6 plants, 6 needs, can't track any of them |
Step 2 — Content pillars (format-fit rule applied)
- Demo/Proof (proves it works) → Screen-record, Silent-satisfying
- Pain-POV ("that's me") → POV/hands+phone, Text-listicle
- Myth/Objection (corrects a wrong belief) → Myth-bust, React-over-screenshot
- Outcome/Transformation (before→after) → Before/after, Tutorial
Step 3 — Hook bank (excerpt: the 3 strongest of 15)
The full pass produced 15 hooks — all ≤14 spoken words / ≤7 on-screen words, ≥3 trigger types per value×pain pair. The three the summary flags as strongest:
- #7 "POV: you find your plant on day 11 of no water." — on-screen: "day 11. no water. oops" (Pain-POV)
- #11 "Yellow leaves don't mean what you think they mean." — "yellow leaves ≠ what you think" (Myth/Objection)
- #4 "One photo told me more than 3 months of Googling did." — "1 photo > 3 months of googling" (Demo/Proof)
Step 4 — One shot-listed faceless script (of three produced)
Script 1 — Pain-POV · POV/hands+phone · TikTok · ~27s · Hook #7
| # | Time | Visual source | On-screen text | VO |
|---|---|---|---|---|
| 1 | 0–2s | POV: hand pulls a droopy, forgotten plant from a corner, crispy leaves | day 11. no water. | "You find the plant you forgot existed." |
| 2 | 2–5s | POV: hand touches bone-dry soil | still alive?? | "Somehow it's still alive. Somehow." |
| 3 | 5–10s | Screen-record: open Dripwise, tap +, photograph the plant | scan it once | "So I scan it—" |
| 4 | 10–16s | Screen-record: app IDs "Pothos," generates care card + watering countdown | tells you what it needs | "—and it tells me exactly what this thing needs. Not a guess. A schedule." |
| 5 | 16–22s | Screen-record: lock-screen notification "Water your Pothos today" | reminder for THIS plant | "Then it just reminds me. For this exact plant." |
| 6 | 22–27s | Same plant weeks later, new leaf, healthy | [Dripwise] — link in bio | "It's called Dripwise. My plants stopped dying by accident." |
Audio: low-stakes relatable-comedy beat. Loop: "day 11" ↔ "stopped dying by accident." Disclosure: ON.
Step 6 — Compliance pass
Disclosure ON all 5 posts · real Dripwise UI only, no mocked results · no virality/earnings claims present · music = track-type only, no named songs · native re-export per platform, no watermarks.
Step 7 — Measurement
KPI ladder: 3s hold → completion% → profile visits → link taps → installs. Decision rules: weak completion (<50%) = rewrite the hook; good completion but low taps = sharpen the CTA; good taps but low installs = it's the listing, not the video. Judge on 9–12 posts (~2–3 weeks) per pillar before deciding, then double down on the top ~20% by completion+saves pattern — not the one exact video.
The honest closing call
The biggest risk to installs isn't the videos — it's that the App Store listing is still a placeholder. Until its first screenshot and subtitle literally say "photo ID + personalized watering schedule," every post pre-sells a click that lands on an unconfirmed promise. The engine flags this and hands off to ASO; it doesn't paper over it.
SERVICE RECORD living gear — updated as the factory learns
v1.0.1 — 2026-08-25
Corrected YouTube Shorts link mechanics, verified against YouTube's own help doc (support.google.com/youtube/answer/13748639). URLs in Shorts descriptions and comments have been non-clickable since August 31, 2023 (YouTube's stated reason: reducing spam and scam attempts) — so the v1.0.0 claim that a description link is clickable, counts as engagement, and makes Shorts "the friendliest of the three for a near-direct store link" was wrong, and was wrong at authoring. Fixed in four places: the Step 4b Shorts guidance and the CTA→install path in SKILL.md, the at-a-glance matrix row and the Shorts "Links / description" section in references/platform-playbook.md, the clickable-path bullet in references/conversion-and-measurement.md, and the Shorts CTA-wording bullet in references/faceless-formats.md. Store links on Shorts now route through the clickable paths that actually exist — channel-profile links (up to 14, shown near the Subscribe button) and the related-video link — the same bio/profile link-hub model the skill already prescribes for TikTok and Reels. No other content changed.
v1.0.0 — 2026-07-17
First issue. Authored from scratch: the end-to-end SOP (intake → value⇄pain matrix → pillars → hook bank → shot-listed faceless scripts → caption/CTA path → dated calendar → measure-and-iterate loop), the eight faceless format families, the hook-bank rubric, three reference cheatsheets, and worked mini-examples. Platform defaults stamped current as of 2026-07 with a verify-the-live-doc instruction so the numbers age gracefully. No invented metrics, no virality promises.
Every update ships free to owners — your locker always serves the latest version.
QUESTIONS
Does it shoot or post the videos for me?›
No. It writes the plan — topics, opening lines, shot-by-shot scripts, captions, and a dated calendar. You or an editor film it and post it. It never films, edits, or posts anything.
Will this make my videos go viral?›
No, and anyone promising that is selling hype. Posting short video for free is a grind: reach is falling, and a few videos carry most of the result. What this gives you is a lot of good tries and a way to learn from what people actually watched. Expect about 60 to 90 days of steady posting before the numbers tell you much.
Do I really never have to be on camera?›
Correct. Every style here is faceless — screen recording, hands and phone, words on screen. No one has to be on camera. That's the design, not a workaround.
What do I have to give it, and where does it run?›
Tell it what your app is worth to people, who those people are, and the problems they have. Without those it stops and asks you, because tying the opening line to a real problem is the whole point. It runs in Claude Code, claude.ai Projects, Codex, or any assistant that can open a markdown file — that's a plain text file. The cheat sheets travel with it.