A /be-ambitious Claude skill turns Ethan Mollick's 'more ambitious' AI advice into a workflow
daniel_mac8 · x · 2026-10-26
Daniel Nguyen shipped /be-ambitious, a Claude skill adapted from a prompt shared by Anthropic's Felix Rieseberg, operationalizing Ethan Mollick's advice to keep asking how to make your AI task more ambitious.
Before rewriting your prompt, the skill answers four questions for the task's field: what a top professional would do that you aren't asking for; what rawest material they'd start from; which specific methods and tools they'd use; and what besides you or the model would show the result is right.
More from coding & agent
- Claude Motion prompt galleries let you copy and recreate trending AI videos — CodeByPoonam · 2026-10-26
- Prime Intellect's self-improving agent harness hits 95.5% on ARC-AGI-3 in 2.5h deep dive — yacinelearning · 2026-10-26
- Google Research's Harness² lets agents build their own harness per task — thisiskp_ · 2026-10-26
- How to measure the human cost of agent work: review time, rework and cost per task — bibryam · 2026-10-26
- Dev shares 7 Claude + 3 Codex subs across 12 machines with CLIProxy — itsOmSarraf_ · 2026-10-26
- Don't Give Your AI Agent the Keys to Everything: Scope Permissions First — alifcoder · 2026-10-26