Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsReel Script Retention Auditor
Diagnose retention friction and rewrite short-form video scripts to maximize watch time and completion rates.
$6.99
Reel Script Retention Auditor
Example session with this skill installed
Audit this 30-second Reel script:
"Hey guys, welcome back. Today I want to talk about
three ways you can improve your Instagram content.
First, you should post consistently. Second, you should
use better hooks. Third, make sure your captions are good.
So that's it. I hope these tips help. Follow for more."
Views are good, but retention is low.
Find
- Hook problems
- Time-to-value problems
- Pacing issues
- Repetition
- Weak curiosity
- Payoff problems
- CTA problems
Then rewrite the Reel for better retention.
Don't invent analytics.
- Read your context and instructions
- Compiled the reel script retention
REEL RETENTION AUDIT
Quick Diagnosis
P0 — Weak Opening
"Hey guys, welcome back" delays the actual value.
P0 — Slow Time-to-Value
The viewer doesn't receive a useful point immediately.
P1 — Generic Information
"Post consistently" and "use better hooks" are broad
without a specific insight.
P1 — Weak Progression
The three points feel like a list rather than a sequence
that creates anticipation.
P2 — Weak Payoff
The ending doesn't deliver a memorable conclusion.
P2 — Generic CTA
"Follow for more" provides little reason to continue.
Retention Friction Map
0–3s:
Greeting before value → remove.
3–10s:
Generic setup → compress.
10–22s:
Three broad tips → add specific examples.
22–27s:
No strong payoff → summarize the key insight.
27–30s:
CTA → make it relevant to the content.
REWRITTEN VERSION
0–3s — Hook
"If your Reels get views but people leave quickly,
check these three things."
3–8s
"First: get to the actual point immediately.
Skip the long introduction."
8–15s
"Second: don't just give advice—show the viewer
what it looks like in practice."
15–22s
"Third: create a reason to watch the next section.
Each point should lead naturally into the next."
22–27s — Payoff
"Views get people in. Your structure gives them
a reason to stay."
27–30s — CTA
"Save this before you write your next Reel."
Test Plan
Test the original and rewritten versions while
keeping other variables as stable as practical.
Compare actual
• Early retention
• Average watch time
• Completion rate
• Rewatch signals
Do not assume the rewrite will produce a specific
percentage improvement before testing.
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Short-form videos often get initial views but suffer from steep drop-offs in the first three seconds. Creators struggle to identify exactly where viewers lose interest or why the hook fails to convert into watch time.
What it does
- Identifies specific retention friction points in scripts, transcripts, or storyboards.
- Conducts time-to-value audits to minimize setup and deliver insights faster.
- Maps actual retention graph data to script elements to explain observed viewer behavior.
- Generates A/B hook variants and structural rewrites focused on open loops and pacing.
- Provides a prioritized P0-P3 fix list to resolve structural issues before cosmetic ones.
Why this beats prompting it yourself
General LLMs often suggest generic marketing fluff or artificial engagement tricks. This skill applies a specific retention framework (Hook, Expectation, Setup, Value, Pacing) to diagnose structural failure, ensuring every recommendation is rooted in viewer psychology and information density rather than just "better wording."
Use cases
- Auditing a finished TikTok script to find and cut filler before filming.
- Analyzing an existing Reel's retention graph to fix high early drop-off rates.
- Restructuring educational content to ensure the "payoff" matches the hook's promise.
- Planning a scene-by-scene storyboard to ensure visual pacing matches the narrative.
Known limitations
Cannot predict virality or final performance metrics. Script-only audits are hypotheses until confirmed by actual platform analytics.
⭐ Core Features 🔥 Hook Auditor Checks clarity, curiosity, specificity, relevance, credibility and payoff alignment. ⏱️ Time-to-Value Analyzer Finds unnecessary introductions and identifies where useful information starts. 📉 Drop-Off Analyzer If actual retention timestamps are supplied, maps drop-offs against the script. ✂️ Pacing Auditor Finds filler, repetition, long explanations and weak transitions. 🧠 Open-Loop Analyzer Finds legitimate opportunities to create curiosity without deceptive clickbait. 💥 Payoff Auditor Checks whether the Reel actually delivers what the opening promised. 📝 Retention Rewrite Rebuilds the script while preserving the original message and legitimate claims. 🧪 A/B Hook Testing Creates alternative hooks while keeping the rest of the Reel stable for cleaner testing.Does not guarantee specific virality or completion rates. Script-only audits are hypotheses until validated by actual platform data. Requires manual input of timestamps for data-driven analysis.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Permissions
No special permissions declared or detected