7 practical rules to drastically improve Claude's writing, from iterative drafting to cross-model review
EXM7777 · x · 2026-10-18
A practitioner shares 7 rules for getting much better writing out of Claude: force it to dumb things down (it loves overcomplicating), push it to write as little as possible, request contractions/asides/ellipses for a human touch, use one idea per sentence and one sentence per line, have it write like chatting with a friend over coffee, iterate section by section instead of one-shotting the full copy, and let another model judge the final piece and flag anything unclear.
More from coding & agent
- 51 real-world AI agent setups analyzed: narrow tasks, drafts not sends, file-based handoffs — abe17124 · 2026-10-18
- User says $200 OpenAI plan drained in a day, then reset oddly to zero — alexcovo_eth · 2026-10-18
- Anthropic tip: one prompt sentence changes how Claude subagents pace speed vs thoroughness — yacinelearning · 2026-10-18
- wavoice: open-source CLI connects WhatsApp voice calls to LiveKit agents in 90s — yashubhakt · 2026-10-18
- "I want an agent to minimize my diffs" — even GitHub's web UI is obsolete now — davidcrawshaw · 2026-10-18
- Dev team drops PRs entirely: push to main, review after the fact with Shelley — davidcrawshaw · 2026-10-18