# De Slopify

> Remove AI-writing tells from README, docs, and user-facing text. Must be done line-by-line, no regex. Use after agents write any user-visible prose.

- Skill: `hoangsonww/de-slopify` (Agent Skill)
- Install (CLI): `npx skillmds@latest add hoangsonww/de-slopify`
- Raw SKILL.md: https://api.skillmd.com/api/skills/hoangsonww/de-slopify/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: hoangsonww (https://skillmd.com/u/hoangsonww)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/hoangsonww/de-slopify

---


Use the verbatim prompt at `.flywheel/prompts/de-slopify.md`.

Hard rule: **no regex, no scripts.** Read each line and revise
manually. Automation fails because fixes are context-dependent.

Strip: emdashes, "It's not just X, it's Y" contrasts, "Here's why"
lead-ins, "Let's dive in," "At its core," unnecessary hedges, forced
enthusiasm.

Preserve: technical specifics, command names, exact flag names,
actual counts. Strip tone, not information.

