agentleFS
coleschaffercoleschaffer/copywritingskills-rmbc/skills/vsl-script/SKILL.md

vsl-script

Skill32 starsChanged 8 months agoMITView on GitHub

Generate RMBC-structured video sales letter scripts with timing markers — the highest-converting long-form format in direct response.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 7 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read rmbc-context/SKILL.md to load RMBC framework definitions.

    line 30
  2. Distinctive:

    Use pattern interrupts every 2-3 minutes (story, question, visual shift)

    line 60
  3. Distinctive:

    Soft CTA: after proof cascade (~60% mark) — for ready buyers

    line 68
  4. Distinctive:

    Main CTA: after offer stack — full close with urgency

    line 69
  5. Distinctive:

    Every CTA must restate the guarantee

    line 116
  6. Distinctive:

    Specificity gate: Every claim in the script must include a number, name, or timeframe — no "get results" or "feel better"

    line 120
  7. Distinctive:

    Mechanism quantification: When referencing the mechanism, include at least one specific data point (number, timeframe, study reference)

    line 121
  8. Distinctive:

    Proof diversity: Use at least 2 different proof types (testimonial, statistical, authority, case study) — do not rely on a single proof mode

    line 123
  9. Very specific:

    Run /mechanism-ideation first to develop the core mechanism

    line 128
  10. Very specific:

    Run /hook-battery for hook options to open the VSL

    line 129
  11. Very specific:

    Run /lead-writer for alternative opening approaches

    line 130
  12. Very specific:

    Use /ingredient-research for proof points and clinical data

    line 131

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

vsl-script

Purpose

Generate a complete VSL (Video Sales Letter) script structured around RMBC principles. VSLs are the highest-converting long-form format in direct response — they combine the persuasive power of long-form copy with the engagement of video. Every VSL follows the same proven arc: hook → problem → mechanism reveal → proof cascade → offer → close. Scripts include timing markers so the client or editor knows pacing at a glance. Mobile-first: 80%+ of VSL viewers watch on phones.

Inputs

InputRequiredDescription
product_descriptionYesWhat the product is, what it does, key features/ingredients/components
target_audienceYesWho the prospect is — demographics, pain points, desires, sophistication level
key_mechanismYesThe product's unique mechanism (output from /mechanism-ideation)
price_pointYesProduct price and any payment plan options
guaranteeYesMoney-back guarantee details (duration, conditions)
proof_pointsNoTestimonials, case studies, clinical data, expert endorsements
target_lengthNoOne of: short (10-15 min), standard (25-35 min), long (45-60 min). Default: standard

Execution Protocol

Step 1 — Load Framework Context

Read rmbc-context/SKILL.md to load RMBC framework definitions. VSLs deploy all four RMBC phases sequentially — Research informs the hook and problem section, Mechanism drives the core revelation, Brief structures the argument, Copy executes the persuasion.

Step 2 — Map the VSL Arc

Build a structural outline with timing markers before writing:

SectionTiming (standard)Purpose
Hook0:00–0:30Stop the scroll, open a loop
Problem Agitation0:30–3:00Make the pain vivid and urgent
Failed Solutions3:00–5:00Disqualify alternatives
Mechanism Reveal5:00–10:00Introduce the unique mechanism
Proof Cascade10:00–18:00Stack evidence — testimonials, data, demos
Product Introduction18:00–22:00Bridge mechanism to product
Offer Stack22:00–27:00Value stack with price anchoring
Risk Reversal27:00–29:00Guarantee removes objection
Close + Urgency29:00–32:00Final CTA with scarcity/urgency
PS / Second Close32:00–35:00Recap for skimmers, restate guarantee

Scale timing proportionally for short or long formats.

Step 3 — Write Each Section

For each section, write:

  • Screen direction — What's shown on screen (text slides, b-roll, talking head)
  • Voiceover script — Exact words to be spoken
  • Transition cue — How this section flows into the next

Rules:

  • One idea per slide. Mobile screens are small.
  • Use pattern interrupts every 2-3 minutes (story, question, visual shift)
  • Mechanism section must use analogy or metaphor — make the complex simple
  • Proof cascade: lead with strongest proof, alternate types (testimonial → data → expert → testimonial)
  • Offer stack: anchor high, reveal real price as a contrast

Step 4 — Write CTA Blocks

Include 3 CTA insertion points:

  1. Soft CTA after proof cascade (~60% mark) — for ready buyers
  2. Main CTA after offer stack — full close with urgency
  3. PS CTA at end — recap, guarantee restatement, final push

Each CTA must include: what to do, what they get, guarantee reminder.

Output Format

## VSL Script: [Product Name]

**Audience:** [target audience summary]
**Mechanism:** [key mechanism name]
**Format:** [short | standard | long] (~XX minutes)
**Price:** [price point]
**Guarantee:** [guarantee summary]

---

### [0:00–0:30] HOOK

**Screen:** [visual direction]
**Script:**
[voiceover copy]

**→ Transition:** [bridge to next section]

---

### [0:30–3:00] PROBLEM AGITATION

[...continue for each section...]

---

## Production Notes

- **Total word count:** ~X,XXX words (~XX minutes at 150 wpm)
- **CTA count:** 3 (soft at XX:XX, main at XX:XX, PS at XX:XX)
- **Pattern interrupts:** [list timestamps]
- **Key slides to design:** [list 3-5 critical visual moments]

Quality Criteria

  • Hook must work in the first 5 seconds — no preamble, no "Hi, my name is..."
  • Mechanism section must make a complex idea simple through analogy
  • Proof cascade must include 3+ distinct proof types (not all testimonials)
  • Every CTA must restate the guarantee
  • Script must read naturally when spoken aloud — no written-language constructions
  • Timing markers must be realistic at ~150 words per minute speaking pace
  • Specificity gate: Every claim in the script must include a number, name, or timeframe — no "get results" or "feel better"
  • Mechanism quantification: When referencing the mechanism, include at least one specific data point (number, timeframe, study reference)
  • Audience journey: The script must reference where the reader IS (what they've tried, what's failing) — not just who they are demographically
  • Proof diversity: Use at least 2 different proof types (testimonial, statistical, authority, case study) — do not rely on a single proof mode
  • Objection handling: The script must address at least 2 likely objections with concrete responses (ROI math, proof of similar result, risk reversal)

Related Skills

  • Run /mechanism-ideation first to develop the core mechanism
  • Run /hook-battery for hook options to open the VSL
  • Run /lead-writer for alternative opening approaches
  • Use /ingredient-research for proof points and clinical data
  • Validate the script with /rmbc-copy-audit

Attribution

Generated using RMBC framework by Stefan Georgi. Learn more: copyaccelerator.com/join

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.