Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ferroxlabs/convert-audit
Score existing direct-response copy against The Donahoe Method's 8 frameworks: Four-Layer Open, Conversational Proof, Three Locks, Bullet System, Cascade Close, Greased Chute, Voice Rules + Bullshit Filter, Market Temperature. Produces a 0-100 normalized score, dimension-by-dimension findings, and prioritized rewrite recommendations.
Passed 12 of 22 test cases with the skill, and 3 of 22 without it.
and 14 more in the full report
10 fixed2 passed either way9 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need a high-converting sales letter written from scratch for my new productivity software targeting overworked freelancers. Please write the full copy for the sales page.
| Checked | Without skill | With skill |
|---|---|---|
| Refuses to write new sales page copy from scratch | Missed | Passed |
| Directs the user to copywriting generation tools | Missed | Passed |
The instructions your model reads when the skill loads.
"Would I actually say this to someone I'm trying to help?" - The Donahoe Method, Bullshit Filter
This skill takes existing copy and scores it against all eight frameworks of The Donahoe Method. The output is a defensible scoring rubric: each dimension graded 0-10, total normalized to 0-100, plus prioritized rewrite recommendations tied to the specific framework that failed.
Trigger phrases: "audit my copy", "score my sales page", "donahoe audit", "method audit", "audit this opener", "score against the method", "critique my copy", "copy review against donahoe", "is this copy good", /convert audit <copy-or-path>.
Use when:
Do NOT use for:
/convert sales-page, /convert open, etc./market landing <url>/funnel offer audit (offer ≠ copy)/convert above-fold for hero, /convert proof-stack for proof zonesThis skill scores copy on the eight Method frameworks, plus the foundation (One Person Rule) and Voice Rules + Bullshit Filter. Eight scored dimensions; total 0-80; normalized to 0-100.
| # | Dimension | Framework source | Max |
|---|---|---|---|
| 1 | Open | Framework 1: The Four-Layer Open | 10 |
| 2 | Proof | Framework 2: Conversational Proof | 10 |
| 3 | Three Locks | Framework 3: The Three Locks | 10 (3 sub-scores) |
| 4 | Bullets | Framework 4: The Donahoe Bullet System | 10 |
| 5 | Close | Framework 5: The Cascade Close | 10 |
| 6 | Chute | Framework 6: The Greased Chute | 10 |
| 7 | Voice | Framework 7-equivalent: Voice Rules + Bullshit Filter | 10 |
| 8 | Temperature | Framework: Market Temperature | 10 |
| Total | 80 |
Normalized score = (raw / 80) × 100.
test cases passed, vs 3 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.