Thanks for helping improve ceo-skill.
This project is most valuable when it becomes more concrete, more reusable, and more grounded in real decision scenarios.
Examples:
- M&A evaluation
- fundraising trade-offs
- layoffs / restructuring
- international expansion
- key executive departure
- board conflict
Improve evals/evals.json with:
- sharper prompts
- clearer expected outputs
- more objective expectations
Contribute:
- new frameworks
- stronger stakeholder patterns
- better war-gaming techniques
- debiasing improvements
Extend scripts/analysis_tools.py carefully.
Keep helpers:
- lightweight
- dependency-free when possible
- easy to inspect
- easy to reuse in agent environments
- Prefer practical decision quality over abstract business jargon
- Prefer reusable structure over clever wording
- Prefer explicit trade-offs over confident but vague recommendations
- Avoid unverifiable claims
- Is the change actually useful for real executive decisions?
- Does it improve clarity, rigor, or reuse?
- Are examples realistic?
- Are runtime-specific assumptions minimized?
- If you changed scripts, did you test them?