convert-bullshit-filter

Featured

Coach a draft toward voice integrity - quotes the 3 weakest lines from the input draft, forces 3 alternative rewrites of each, diagnoses the dominant voice failure pattern, and returns a coaching artifact (no PASS / FAIL verdict). Use when running a final coaching pass on copy before shipping - sales pages, VSL scripts, emails, ads, headlines. Not for full Voice Rules pass (use convert-voice - Bullshit Filter is one rule of many in Voice; this is the deeper standalone coaching pass) and not for Method audit scoring (use convert-audit).

AI & Automation 604 stars 115 forks Updated 3 days ago AGPL-3.0

Install

View on GitHub

Quality Score: 91/100

Stars 20%
93
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Convert Bullshit Filter - The Adversarial Coaching Pass > *"Would I actually say this to someone I'm trying to help?"* - The Donahoe Method, Voice Rules The Bullshit Filter is one question. It's also the single most important question in the Method. This skill runs the Filter as an **adversarial coaching pass** - not a verdict. It refuses to grade copy as "passed" or "failed." Instead, it forces three concrete actions on every draft: 1. **Quote the 3 weakest lines** in the draft, even if the draft seems strong. There is always a worst sentence; this skill identifies it. 2. **Produce 3 alternative rewrites** of each weakest line, so the writer sees the actual menu of voicing choices instead of accepting an AI's first take. 3. **Diagnose the dominant voice failure pattern** in one paragraph (e.g., softeners, marketing-speak, abstract language, hedged claims, performative urgency). The output is a **coaching artifact**. The user decides whether to ship after seeing the 3 weakest lines + 9 rewrites + the diagnosis. There is no PASSED, no FAILED, no boolean stamp. AI cannot grade its own work; this skill stops trying. ## When to Use Trigger phrases: "bullshit filter", "run the filter", "donahoe filter", "would I say this to a friend", "read aloud test", "kill anything that sounds fake", "final voice gate", "last pass before shipping", "find the weakest lines", "rewrite the worst sentences", `/convert bullshit-filter <draft>`. Use this skill as the **last coaching pass** ...

Details

Author
FerroxLabs
Repository
FerroxLabs/wayland
Created
3 months ago
Last Updated
3 days ago
Language
TypeScript
License
AGPL-3.0

Similar Skills

Semantically similar based on skill content — not just same category

Data & Documents Featured

convert-voice

Apply The Donahoe Voice Rules: sentence mechanics, word choices, structural moves, and the Bullshit Filter as a checklist. Operating system for every piece of copy - every headline, email, sales page, ad - passes through these non-negotiable rules. Use when a draft exists in some voice (yours, AI default, marketing-bro) and you need to bring it to Donahoe Voice - first-person, contractions, specific, no marketing-speak, reads aloud natural. Not for engineering momentum (use convert-chute) and not for the standalone Bullshit Filter pass (use convert-bullshit-filter).

604 Updated 3 days ago
FerroxLabs
AI & Automation Featured

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. Use when the user has existing copy (a sales page, VSL script, email, ad, opener) and wants a Method-grade audit with specific rewrite directions. Not for net-new copy generation (use /convert sales-page or /convert open) and not for live-URL CRO teardown (use /market landing).

604 Updated 3 days ago
FerroxLabs
AI & Automation Listed

ai-slop-killer

The final anti-AI-slop editing pass for any drafted or revised prose — blog posts, newsletters, LinkedIn/social, emails, marketing and web copy, documentation, essays, fiction. Detects documented AI writing tells (negative parallelism "not X, it's Y," rhetorical Q&A, rule-of-three and anaphora pile-ups, em-dash and unicode overuse, corporate-AI vocabulary, wind-up intros and signposted conclusions, bold-first-bullet listicles, low-burstiness rhythm, hedging, vague attributions, participial "-ing" filler, grandiose stakes, invented concept labels), scores the passage, rewrites in place, and reports what it caught. Runs LAST, after any other writing or editing skill. Trigger on "clean this," "de-slop," "kill the AI slop," "copyedit," "does this sound like AI," "make this sound human," "humanize this," or automatically after any skill produces prose meant to be published.

2 Updated yesterday
mrhinkle