/be-ambitious: a Claude skill that stops safe, watered-down outputs
CodeByPoonam · x · 2026-11-02
drcintas shared a Claude Code skill called /be-ambitious that forces the agent through altitude (the goal beyond the goal), depth (what a real expert would do and what outside check proves it), and range (which other fields should weigh in) before starting — fixing Claude's tendency to deliver a safe small version of any task. CodeByPoonam says she's trying it.
Related event: /be-ambitious skill pushes Claude beyond safe minimal outputs(2 posts)→
More from coding & agent
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Sketchy v0.1.6: AI diagrams use 29% fewer output tokens than plain text — Nkgsporty · 2026-11-02
- Avoiding AI brain rot: Miles Cranmer's lecture on learning with AI — _ScottCondron · 2026-11-02
- Scrapling web scraping framework tops 92k GitHub stars, ships MCP server for AI workflows — D4Vinci · 2026-11-02
- Vercel open-sources Agent Desktop: reliable computer use via OS accessibility trees, 7.8k stars in a day — vercel-labs · 2026-11-02
- Karpathy's nanochat: the best ChatGPT $100 can buy, near 60k GitHub stars — karpathy · 2026-11-02