AI copy can sound polished and still feel predictable. This skill file helps catch the…
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
AI copy can sound polished and still feel predictable. This skill file helps catch the tells. Stop Slop is a skill file for Claude or another LLM that helps remove recognizable AI patterns from prose. It helps you revise generated text with a concrete set of instructions and reference files, so you can check phrasing, structure, and sentence-level habits instead of relying on a vague “make it sound human” prompt. Key features: • Core skill instructions – gives the model the rules for reviewing prose • Phrase reference – flags throat-clearing openers, business jargon, adverbs, and vague dec
Posted by Dan Kornas (99.3k followers) 15 h ago · 0 likes · 282 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- 🔥🔥🔥 Claude 限时优惠，可以直接领取 $250 云端会话额度 — @kafkaup
- This inspired us! — @heyaskr
- The agent answered correctly. Then it tried to send the email. — @AiswaryaVenkit1
- Product work gets messy when every AI prompt starts from zero. — @DanKornas
- 两个视频让你直观看到 Opus 5.5 和 6 SOL 的差距有多大。 — @0xLogicrw
- mizchi/vlmkit が破綻なくUIを実装できるデモの一つ、 excalidraw クローンが作れる — @mizchi
- Lovable’s agent infrastructure records ~500M events on a typical weekday. — @FabianHedin
- 500 million agent events per day. That’s the scale behind Lovable’s new Chats experience. — @TomasHalgas
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 23.4k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 10:22 UTC. Full method.