Retention Curve Decoder
Pull relative-retention peaks and matched comment themes from competitor videos to tell your script writer what to keep and cut.
Before & after
Same prompt, same agent — the only difference is the skill.
That's a great question to help improve your content strategy. Studying competitor videos is definitely smart. I'd suggest watching a few of their top-performing videos and taking notes on what keeps you engaged—things like pacing, editing cuts, hooks, and how they structure information. You might also look at the comments to see what resonates with viewers. Different niches have different retention patterns, so it helps to focus on channels in your specific space. Do you have specific competitors in mind?
RETENTION ANALYSIS REPORT Top 3 Competitor Videos: 00:00-00:15 HOOK ZONE (Critical) → Peak: 92% retention at 0:03 (cold open joke) → Matched comment: 'Laughed so hard I subscribed' → Pattern: Unexpected contrast to expected intro 00:15-01:00 CREDIBILITY BUILD → Valley: 71% retention at 0:45 (slow explainer section) → Matched comment: 'Speed this up' (3x likes) → Fix: 30s max on background, cut jargon 01:00-END ENGAGEMENT PEAKS → Peaks: 89% at 3:12 (demonstration), 85% at 5:40 (real-world result) → Comment theme: Reaction to proof, not theory Do/Don't Rules for Next Script: • DO: Open with counterintuitive claim (first 3s) • DO: Show proof immediately, skip theory • DON'T: Explain context before hook • DON'T: Slow pacing in first 90 seconds
About this skill
name: retention-curve-decoder description: Use when Pull relative-retention peaks and matched comment themes from competitor videos to tell your script writer what to keep and cut.
Retention Curve Decoder
The play bar's transparent up/down curve is public data most creators ignore. This skill takes a competitor URL list, scrapes the retention curve, aligns each peak/dip with the transcript at that timestamp, cross-references top comments, and outputs a briefing your script writer can act on: which hooks work, what makes people jump, which segments generate comments, and what to steal for the next script. Use monthly on your top 5 competitors to keep script quality rising.
What you get
- Retention peak/valley timestamps
- Transcript excerpt per peak
- Matched comment cluster
- Hook pattern library
- Do/don't rules for the next script
- Video-level retention score
Customize your output
- Competitor URL list: comma
- Niche: dropdown
- Language: en, es, pt, other
- Retention threshold to flag: 5, 10, 20 percent above/below baseline
- Comments to pull per peak: 5, 10, 25
- Output format: markdown, HTML
Example output
'Video A: peak at 03:12 (the jury reaction). Matched comment cluster on juror body language. Valley at 06:40 (procedural recap). Recommendation: keep human-reaction beats every 3m, cut procedural summaries under 20s.'
Best for
Faceless YouTube script leads, channel managers, agency retention coaches.
SKILL.md preview
---
name: retention-curve-decoder
description: Use this skill to pull relative-retention peaks and matched comment themes from competitor videos to brief a script writer on what to keep and cut.
version: 1.0.0
category: YouTube/Video
author: AgentVolt
license: proprietary
tags:
- youtube
- video
- p4
---
# Retention Curve Decoder
Reads a competitor video's public retention curve, aligns its peaks and dips with the transcript and top comments at those exact timestamps, and produces a briefing on what to steal and what to avoid for the next script.
## When to use
… (sign up to view the full skill)