Home / kenny589 / gtm-flywheel · GitHub

winning-copy-extraction SKILL.md skillA

winning-copy-extraction from kenny589/gtm-flywheel is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add kenny589/gtm-flywheel/winning-copy-extraction@git:20260216.983c93b

Pins git:20260216.983c93b in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: kenny589/gtm-flywheel
Path: campaign-analytics/winning-copy-extraction/SKILL.md
Versions recorded: 1
Latest version: git:20260216.983c93b, committed Feb 16, 2026
Size: 10,932 bytes
Repository stars: 69
License: MIT

Extract, analyze, and replicate the patterns behind your highest-performing email copy. Turn individual campaign wins into repeatable copy frameworks your team can deploy across every campaign.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Winning Copy Extraction

## When to Use
- After accumulating 30+ campaigns with performance data
- When onboarding a new copywriter or SDR who needs to learn "what works here"
- Building AI-assisted copy generation systems that learn from your data
- Creating a copy playbook for a specific vertical, persona, or campaign type
- Quarterly copy audits to identify trends and refresh stale templates

## Framework

### The Copy Extraction Pipeline

Winning copy doesn't come from brainstorming — it comes from data. Here's the systematic process for extracting what works from what you've already sent.

```
Step 1: Pull Campaign Data
    → All campaigns with 200+ sends and at least 14 days of data
    ↓
Step 2: Rank by Positive Reply Rate
    → Sort descending. Top 10% = your winners.
    ↓
Step 3: Analyze the Winners
    → What patterns emerge across your best copy?
    ↓
Step 4: Codify the Patterns
    → Turn patterns into reusable frameworks
    ↓
Step 5: Test Against New Copy
    → Use pattern-based copy in new campaigns. Measure.
    ↓
Step 6: Update the Playbook
    → Add new winners. Remove copy that stopped working.
```

---

### Step 1: Define "Winning" Copy
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add kenny589/gtm-flywheel/winning-copy-extraction@sha256:115cfbfde8b2ca5a

The line at the top of this page pins the label git:20260216.983c93b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_asm6eyfgpscckj75.svg)](https://markdownregistry.com/a/art_asm6eyfgpscckj75)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Feb 16, 2026.

version	committed	commit	size	audit
git:20260216.983c93b latest	2026-02-16	983c93b	10,932 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (10932 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

kenny589/gtm-flywheel · 69 stars · license MIT · pushed 2026-02-17 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_asm6eyfgpscckj75
GET https://markdownregistry.com/api/v1/resolve?ref=kenny589/gtm-flywheel/winning-copy-extraction
GET https://markdownregistry.com/api/v1/blob/115cfbfde8b2ca5a16a868703e74641b436b1d9be7cb4f5a6c4414b68ba5a459

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.