clear-writing
Clear Writing
Clear writing is just clear writing. It doesn't pad around substance. It doesn't perform.
This skill works by subtraction. The AI's natural patterns are: elaborate, balance, summarize, kicker. Strip those away and what's left sounds human.
Copy Voice (The Disease)
The default register every LLM produces when you don't give it something specific to aim at. It reads like the offspring of a TED talk and a LinkedIn post. You recognize it when you see it: the sentences are all the right length, the paragraphs each make one point, and every section ends on something that sounds like it should be cross-stitched onto a throw pillow.
Specific hallmarks:
- Crafted kickers - last sentence resolves into an aphorism. "The constraints don't create the voice. They protect it."
- Negation cascades - "No rules. No curriculum. Just curiosity." Three things something isn't, then a landing on a warm noun.
- Antithesis pairs - "Not X. Y." as a mic drop. The training data is marinated in this.
- Performative simplicity - lists the complicated things, waves them away, lands on the simple thing with a flourish.
The fix is not listing don'ts (that makes the model organized around its prohibitions). The fix is writing TOWARD a specific register - load a style reference and let the examples teach. The constraints below catch drift back toward copy voice. They don't create a voice. They prevent the default from creeping back in.