New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Convert Open

by FerroxLabs in FerroxLabs/wayland

Generate Four-Layer Opens for any direct-response asset: Layer 1 Nerve Strike + Layer 2 Side Door + Layer 3 Skin in the Game + Layer 4 Fingerprint.

MITAuto-check passed

Install Convert Open

skills CLI
$ npx skills add FerroxLabs/wayland --skill convert-open -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install FerroxLabs/wayland convert-open --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/FerroxLabs/wayland.git skills-src && mkdir -p .claude/skills && cp -r skills-src/resources/bundled-extensions/business-conversion/skills/convert-open .claude/skills/convert-open && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
convert-open
GitHub stars
608
Token cost
~3.2k tokens
SKILL.md length
1,376 words
Files
1
Skills in repo
1,194
Repo updated
First seen
Licence
MIT

At a glance

Generate Four-Layer Opens for any direct-response asset: Layer 1 Nerve Strike + Layer 2 Side Door + Layer 3 Skin in the Game + Layer 4 Fingerprint.

  • Works in 5 steps: Establish the One Person → Identify the Nerve → Generate 5 Open candidates → …
  • Authoring a sales page
  • SKILL.md covers When to Use, Inputs, The Four Layers (full method) and Workflow, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Convert Open is an agent skill from FerroxLabs/wayland. Generate Four-Layer Opens for any direct-response asset: Layer 1 Nerve Strike + Layer 2 Side Door + Layer 3 Skin in the Game + Layer 4 Fingerprint. Produces 5 ranked opens with section-by-section breakdown. Use when authoring a sales page, VSL, email, ad, or any opener that must make the reader physically unable to stop reading. Not for headline-only generation (this is a 3-5 sentence multi-layer open, not a single headline) - sub-skill of /convert sales-page when called as part of full Method deployment.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Wayland - The AI Agent That Perceives. Reasons. Acts. Evolves. The licence is MIT.

When your agent uses it

  • Authoring a sales page
  • Any opener that must make the reader physically unable to stop reading

Example prompts

  • “/convert-open”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Establish the One Person
  2. Identify the Nerve
  3. Generate 5 Open candidates
  4. Apply Voice Rules
  5. Bullshit Filter

What it can do on your machine

Read from SKILL.md and the folder at commit 4c030c7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Convert Open loads about 3.2k tokens when it runs. Until then it costs about 131 tokens; SKILL.md has 1,376 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~131
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from FerroxLabs/wayland at commit 4c030c7, republished under its MIT licence (© FerroxLabs). 1,376 words, ~3,167 tokens.

Download SKILL.mdSave it as .claude/skills/convert-open/SKILL.md (or your agent's skills folder).
name
convert-open
description
Generate Four-Layer Opens for any direct-response asset: Layer 1 Nerve Strike + Layer 2 Side Door + Layer 3 Skin in the Game + Layer 4 Fingerprint. Produces 5 ranked opens with section-by-section breakdown. Use when authoring a sales page, VSL, email, ad, or any opener that must make the reader physically unable to stop reading. Not for headline-only generation (this is a 3-5 sentence multi-layer open, not a single headline) - sub-skill of /convert sales-page when called as part of full Method deployment.
slash_command
false
pack
business-conversion
family
donahoe_method
triggers
write me an opener, four-layer open, donahoe open, opening for my sales page, hook for cold traffic, lead-in for my email, nerve strike opener, how should I…
negative_triggers
just write a headline, score my existing opener, rewrite my hook (use convert-rewrite)
tags
conversion, copy, donahoe-method, four-layer-open, hook, opener
priority
100
version
1.0.0
author
Wayland Business Pack
license
MIT

Convert Open - The Four-Layer Open

"Your opening has one job: make them keep reading. Not impress them. Not 'build rapport.' Make them physically unable to stop." - The Donahoe Method, Framework 1

This skill generates openings using all four layers of The Donahoe Method's signature open. Four layers, 3-5 sentences, every word load-bearing.

When to Use

Trigger phrases: "write me an opener", "donahoe open", "opening for my sales page", "hook for cold traffic", "nerve strike opener", "how should I open this", /convert open <topic-or-product>.

Use for any direct-response asset that needs to capture a reader inside the first 3-5 sentences: sales pages, VSL scripts, email leads, ad copy, article intros, webinar opens, presentation hooks.

Do NOT use for:

  • Standalone headlines without context (the Open is multi-sentence; a single headline lives inside Layer 1)
  • Rewriting an existing opener (use convert-rewrite instead - it preserves voice while applying the Method)
  • Auditing an existing opener (use convert-audit for full Method scoring)

Inputs

Required:

  1. Product / topic / offer - what are we selling or saying?
  2. Target reader - one specific human (Donahoe Voice Rule #1: The One Person Rule). NOT "marketers" - "Mike, an agency owner in Ohio who's burned through $40k on Facebook ads with nothing to show". If the user gives a vague audience, ask for specificity in one short prompt: "Describe the one person you're writing this for."
  3. The Nerve - what's the specific raw pain? Not "they're frustrated with X". "They woke up this morning, opened their dashboard, saw zero leads, and felt that sick feeling because rent's due Tuesday."

Optional:

  • Asset type - sales page / VSL / email / ad / article (calibrates length and rhythm)
  • Author voice notes - tone, vocabulary, signature phrases. If absent, default to The Donahoe Voice Rules.
  • out_path - caller-controlled output. Defaults via build_report_path("business-conversion", instruction).

The Four Layers (full method)

Layer 1 - The Nerve Strike

The first sentence hits a nerve that's already raw. The thing that bothered them this morning. The thing they're quietly frustrated about but haven't admitted to anyone.

You're not introducing a problem. You're naming one they already have. That's the difference between "here's why you should care" and "I know exactly what's going on with you."

Specifications:

  • One sentence
  • Specific (numbers, scenarios, sensory detail) - never abstract
  • Names the pain they already feel, not pain you're convincing them they have
  • No marketing-speak, no "Are you struggling with...?" softeners

Examples (Donahoe-style):

  • ✓ "If you made less than $10K last month from your online business, there's a specific reason - and it's probably not what you think."
  • ✓ "You woke up this morning, checked your inbox, and counted seventeen unread emails from clients all wanting the same thing - and you still don't know how to say no."
  • ✗ "Are you struggling to grow your business?" (vague, performative, no nerve)
  • ✗ "In this comprehensive guide, we'll explore..." (corporate stock opener)
Layer 2 - The Side Door

You don't walk in through the front door announcing "I'M HERE TO SELL YOU SOMETHING." You come in through the side door. Casual. Like you're mentioning it in passing.

Specifications:

  • 1-2 sentences
  • Conversational tone - like a friend mentioning something
  • Tone says "I noticed something you should probably know about"
  • Defenses stay down because it doesn't sound like a pitch

Examples:

  • ✓ "I was going through some numbers the other day and noticed something weird about the way most of these courses are priced..."
  • ✓ "A buddy of mine - runs a chiropractic clinic in Tampa - sent me a screenshot last week that I haven't been able to get out of my head."
  • ✗ "Today I want to introduce you to a revolutionary breakthrough..."
  • ✗ "Let me share with you the secrets that the gurus don't want you to know..."
Layer 3 - Skin in the Game

Within the first 3-4 sentences, the reader must know why you're telling them this. Not "because I'm an expert" - because you've been there. You went through it. You discovered something. You nearly missed it. You fucked it up first.

Specifications:

  • 1-2 sentences
  • First-person, specific scenario from your past
  • Answers the unconscious question: "Why is this person telling me this?"
  • The answer can never be "because they want my money"

Examples:

  • ✓ "Three years ago I was staring at the same dashboard, trying to figure out why my $12K/month copywriting business felt like it was running on fumes - and what I figured out changed everything."
  • ✓ "I learned this the hard way in 2019 when I burned through $84,000 in ad spend on a launch that flatlined - and the post-mortem revealed something I'd been doing wrong for five years."
  • ✗ "As a leading expert in direct-response marketing..." (credential dump, not Skin in the Game)
Show full SKILL.md (619 more words)Show less
Layer 4 - The Fingerprint

Something in the opening that could only come from YOU. An opinion. A contrarian take. A vivid image. A way of seeing the situation that's distinctly yours.

This is the moment they decide you're worth their time - because you don't sound like everyone else.

Specifications:

  • One distinct moment of voice - could be a single phrase, a comparison, an opinion
  • Test: if you swap your name for a competitor's, would anyone notice? If yes, the Fingerprint is missing.
  • Often comes through: contrarian take, signature comparison, profanity-as-precision (if matches user voice), vivid image, dismissive aside

Examples:

  • ✓ "Most of the advice out there is - and I'm being generous here - complete horseshit."
  • ✓ "It hit me like a slap from someone who actually liked me: every funnel guru is selling you the machine and forgetting the bait."
  • ✓ "This is the part where I'm supposed to tell you my system is the secret. It's not. The secret is so much dumber than that."
  • ✗ "I'm passionate about helping entrepreneurs succeed." (zero distinctive voice)

Workflow

Step 1 - Establish the One Person

If the user hasn't given you a specific reader, ask once. "Describe the one person you're writing this for. Not a segment - one specific human. What's their name, what's their day look like, what's keeping them up at night?"

If they give you a segment ("agency owners"), don't proceed - re-ask with: "Pick one. Describe Mike specifically - his city, his stack, his last failed campaign. The Method requires it."

Step 2 - Identify the Nerve

What's the specific, raw, this-morning pain? Test:

  • Is it a feeling, not an abstraction? ("That sick stomach feeling" not "frustration with results")
  • Is it specific enough that the reader would nod and say "yeah, that's exactly my problem"?
  • Is it something they've felt this week, not something hypothetical?

If the nerve isn't sharp enough, the Open will fail. Push for sharpness.

Step 3 - Generate 5 Open candidates

Each candidate = all 4 layers, 3-5 sentences total. Mix the layer construction across candidates so the user sees range:

  • Candidate 1: Direct Nerve Strike → Side Door anecdote → first-person Skin → contrarian Fingerprint
  • Candidate 2: Question-form Nerve Strike → casual observation → "I learned this the hard way" → vivid metaphor
  • Candidate 3: Specific-number Nerve Strike → friend-of-mine Side Door → vulnerable admission → dismissive Fingerprint
  • Candidate 4: Sensory Nerve Strike → industry-observation Side Door → past-mistake Skin → opinion Fingerprint
  • Candidate 5: Pattern-interrupt Nerve Strike → off-handed Side Door → discovery-moment Skin → signature comparison Fingerprint
Step 4 - Apply Voice Rules

Every candidate must pass The Donahoe Voice Rules baseline:

  • First person ("I", "you" - never "we" or "customers")
  • Contractions throughout
  • Mixed sentence length (short punch, longer breath, short again)
  • No marketing-speak ("leverage", "optimize", "revolutionary", "unlock potential" - banned)
  • Reads natural out loud (read it; if you stumble, rewrite)
Step 5 - Bullshit Filter

Final pass: would I actually say this to someone I'm trying to help? If a candidate sounds like writing instead of talking, kill it and rewrite.

Output template

markdown
# Four-Layer Open: <Topic / Product>

**Reader:** <One specific person - name, city, situation>
**Nerve:** <The specific raw pain>
**Asset type:** <sales page / VSL / email / ad>

---

## Candidate 1 - <one-line variant descriptor>

> <The full 3-5 sentence open, written as it would appear>

**Layer breakdown:**
- **Nerve Strike:** "<the first sentence quoted>"  → <why it strikes the nerve>
- **Side Door:** "<the next 1-2 sentences quoted>" → <how it slips defenses>
- **Skin in Game:** "<the personal moment quoted>" → <what it earns>
- **Fingerprint:** "<the distinctive moment quoted>" → <what makes it only-you>

**Voice check:** First person ✓ | Contractions ✓ | No marketing-speak ✓ | Reads aloud natural ✓
**Bullshit Filter:** run separately via `convert-bullshit-filter` (coaching pass - no inline pass/fail stamp)

---

## Candidate 2 - <variant>
... (same structure)

## Candidate 3 - <variant>
...

## Candidate 4 - <variant>
...

## Candidate 5 - <variant>
...

---

## My pick

Recommended: **Candidate <n>** because <reason - connects most directly to the stated Nerve / fits the asset type / has the strongest Fingerprint>.

**Use this if:** <when this candidate is right>
**Swap to Candidate <m> if:** <when the alt is better>

---

## How to deploy this Open

1. Drop the recommended candidate into the asset's first 3-5 sentences.
2. Pair with `convert-three-locks` to architect what comes next (Want → Trust → Excuse).
3. Pair with `convert-chute` to engineer momentum into the next section.
4. Run `convert-bullshit-filter` on the full draft before shipping.

## Lineage

The Four-Layer Open is part of **The Donahoe Method** (Wayland-owned operating system).

Lineage references:
- Layer 1 (Nerve Strike) - Halbert's "lead with the pain" canon (Boron Letters, 1984)
- Layer 1 sub-formulas - Caples 35 headline formulas (Tested Advertising Methods, 1932)
- Layer 4 (Fingerprint) - informed by Schwartz's "market sophistication" requiring a unique angle (Breakthrough Advertising, 1966)

Notes

  • Layer 1 should make them stop scrolling. Layer 2 should keep them reading without realizing they're being sold to. Layer 3 should make them trust you. Layer 4 should make them remember you.
  • If the user pushes back on a Nerve Strike for being "too aggressive," that's usually because the nerve isn't actually their target reader's nerve - they're projecting their own discomfort. Push back gently: "This isn't aggressive - it's specific. Specific is what works on this audience. Want me to find a different specific?"
  • The Fingerprint is the hardest layer to teach an AI. If your Fingerprint candidates feel generic, return to the One Person Rule: what would you say to them over coffee? That's the Fingerprint.
  • This is the Open. Pair it with convert-proof, convert-three-locks, convert-bullets, convert-close, convert-chute, and convert-voice to build full assets.

© FerroxLabs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in resources/bundled-extensions/business-conversion/skills/convert-open of FerroxLabs/wayland.

Open the folder on GitHubat commit 4c030c7

Compare with similar skills

Convert Open next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Convert Open compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Convert Open this skillFerroxLabs/wayland608—~3.2kAutomated safety check: PassMIT
Convertremotion-dev/remotion62k—~247Automated safety check: PassCustom licence
Assets Prefab OpenIvanMurzak/Unity-MCP4.4k—~872Automated safety check: PassApache-2.0
Responsive Unitsthedaviddias/Front-End-Checklist74k—~472Automated safety check: PassMIT
Responsive Designwshobson/agents40k2 repos~498Automated safety check: PassMIT
Terminal Openeraffaan-m/ECC274k—~635Automated safety check: PassMIT

Similar skills

  • Convert

    remotion-dev/remotion

    Official

    Start the local @remotion/convert app and open it in the Codex browser.

    62k GitHub stars~247 tokensUpdated today
    Media & CreativeAuto-check passed

  • Assets Prefab Open

    IvanMurzak/Unity-MCP

    Open the prefab edit stage for a prefab instance or prefab asset GameObject.

    4.4k GitHub stars~872 tokensUpdated 3 days ago
    Game DevelopmentAuto-check passed

  • Responsive Units

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing stylesheets, component styles, and responsive behavior related to Use relative units for responsive layouts.

    74k GitHub stars~472 tokensUpdated yesterday
    Frontend & DesignAuto-check passed

  • Responsive Design

    wshobson/agents

    Implement modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first breakpoint strategies.

    40k GitHub starsUsed in 2 repos~498 tokens
    Frontend & DesignAuto-check passed

  • Terminal Opener

    affaan-m/ECC

    Open an executable and its argument array in a visible terminal window through a reusable, shell-free launch plan with dry-run, JSON, capability detection, detached fallback, and standalone recovery…

    274k GitHub stars~635 tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed

  • Game Asset Audit

    Donchitos/Claude-Code-Game-Studios

    Audits game assets against naming conventions, file size budgets and format standards, and finds orphaned assets and missing references.

    26k GitHub stars~2k tokensUpdated 8 days ago
    Game DevelopmentAuto-check passed

More from FerroxLabs/wayland

All 1,194 skills in this repo

  • Star Office Helper

    FerroxLabs/wayland

    Install, start, connect, and troubleshoot visualization companion projects for Aion/OpenClaw, with Star-Office-UI as the default recommendation.

    608 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check: notes

  • Openclaw Setup

    FerroxLabs/wayland

    OpenClaw usage expert: Helps you install, deploy, configure, and use OpenClaw personal AI assistant.

    608 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

  • Tvcontrol Setup

    FerroxLabs/wayland

    Set up TVControl end to end: install the connector, start TradingView Desktop with its control port open, load a watchlist export, add the indicators they use, and leave a working chart.

    608 GitHub stars~5.7k tokensUpdated yesterday
    Auto-check passed

  • Ab Testing Specialist

    FerroxLabs/wayland

    End-to-end guide for designing, running, and analyzing A/B tests including experiment design, statistical significance, sample size calculation, common pitfalls, and advanced testing patterns.

    608 GitHub stars~3.7k tokensUpdated yesterday
    Auto-check passed

  • Academic Writer

    FerroxLabs/wayland

    Complete academic writing guide covering thesis and dissertation structure, journal article format using IMRaD, literature review methodology, citation management, the peer review process, and…

    608 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check passed

  • Accessibility Auditor

    FerroxLabs/wayland

    Web accessibility expertise covering WCAG 2.2 conformance, audit methodology, ARIA patterns, keyboard navigation, screen reader testing, focus management, form accessibility, and automated vs manual…

    608 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed

Questions about Convert Open

What does Convert Open do?

Generate Four-Layer Opens for any direct-response asset: Layer 1 Nerve Strike + Layer 2 Side Door + Layer 3 Skin in the Game + Layer 4 Fingerprint. Convert Open is an agent skill from FerroxLabs/wayland. Generate Four-Layer Opens for any direct-response asset: Layer 1 Nerve Strike + Layer 2 Side Door + Layer 3 Skin in the Game + Layer 4 Fingerprint.

When should I use Convert Open?

Convert Open fits situations like: authoring a sales page; any opener that must make the reader physically unable to stop reading.

How do I install Convert Open in Claude Code?

Run `npx skills add FerroxLabs/wayland --skill convert-open -a claude-code`. Or copy the skill folder (resources/bundled-extensions/business-conversion/skills/convert-open in FerroxLabs/wayland) into .claude/skills/convert-open in your project. Claude Code loads it when a task matches its description.

How do I install Convert Open in Codex?

Run `npx skills add FerroxLabs/wayland --skill convert-open -a codex`. Or copy the skill folder (resources/bundled-extensions/business-conversion/skills/convert-open in FerroxLabs/wayland) into .agents/skills/convert-open in your project. Codex loads it when a task matches its description.

Can I use Convert Open in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add FerroxLabs/wayland --skill convert-open -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/convert-open, .gemini/skills/convert-open, .github/skills/convert-open and .opencode/skills/convert-open in your project.

What does Convert Open need to run?

SKILL.md names no scripts, command-line tools or credentials: Convert Open is instructions for the agent only.

Does Convert Open access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Convert Open safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Convert Open use?

Convert Open is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Convert Open use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Convert Open?

Skills that share tags, products or a category with Convert Open: Convert (remotion-dev/remotion, 62k stars), Assets Prefab Open (IvanMurzak/Unity-MCP, 4.4k stars), Responsive Units (thedaviddias/Front-End-Checklist, 74k stars) and Responsive Design (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Convert Open?

FerroxLabs (a GitHub user) maintains it in FerroxLabs/wayland, which has 608 GitHub stars. The repository holds 1,194 skills in this directory. The repository was last updated on October 6, 2026.

Source: FerroxLabs/wayland on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.