Devs slam Claude Design for not shipping as a Claude Code skill, creating two separate systems
BLUECOW009 · x · 2026-09-04
A developer argues one of the biggest recent product mistakes is that Claude Design wasn't built as a skill you can run directly inside Claude Code. Instead, users now have two separate systems to manage, which creates an artificial boundary and unnecessary inconsistency with Claude Code's skill-based extensibility model.
Related event: Users Slam Claude Design's Disconnect from Claude Code(2 posts)→
More from coding & agent
- Design systems weren't built for AI agents, so this designer built an AI-first one — AIandDesign · 2026-09-04
- Feeding all your business context to GPT-6 Astra produced 'the most useful AI response ever' — sherwinwu · 2026-09-04
- Agent Flywheel: beads todos, an ntm-managed agent swarm, and MCP Agent Mail messaging — doodlestein · 2026-09-04
- I shipped a broken install command for my MCP server — an honest postmortem — Left-Yellow1047 · 2026-09-04
- Why agents fail in production: right data, missing tacit judgment — Anxious-Variation508 · 2026-09-04
- Matt Shumer shares Manager Loop that got GPT-6 Astra to build Manhattan in Unreal over a week — SEO · 2026-09-04