/be-ambitious: A Claude Skill That Pushes the Model Beyond Safe, Small Outputs
dr_cintas · x · 2026-11-02
drcintas shares a Claude skill called /be-ambitious that counters the model's tendency to give a safe small version of any task.
It forces the agent through three dimensions before starting:
- Altitude: what's the goal beyond the goal?
- Depth: what would a real expert do, and what outside check proves it?
- Range: which other fields should weigh in, doing their real jobs?
Install by cloning the repo to /.claude/skills/be-ambitious, then invoke with /be-ambitious [task]. The screenshot comparison shows the same "5-day intro to AI course" prompt producing a routine syllabus normally, but an ambitious capstone-driven design with principles like "use it before you understand it" and "know when it's lying" with the skill.
More from coding & agent
- Install a Gmail connector on ChatGPT to avoid output-misreading mistakes — jxnlco · 2026-11-02
- DeepSeek Harness Super-agent design: the bottleneck isn't smarter models, it's your attention — sujingshen · 2026-11-02
- tito: the hidden tokenizer bugs breaking RL training, and a Lean-verified fix — VoidAsuka · 2026-11-02
- Build an Agentic Knowledge Graph from Scratch — No Graph DB, No Extraction Model — adnan_hashmi · 2026-11-02
- One Vault, Two Sides: An Obsidian + Claude Agent Workflow for Personal Knowledge — adnan_hashmi · 2026-11-02
- Vercel engineer open-sources Security Audit skill you trigger via @bot reply — brandon_galang · 2026-11-02