Use before letting AI or an agent act on a marketing or GTM task without human review, or when writing an AI review policy. Places each workflow in AI-primary, collaborative or human-primary by stakes and reversibility.
Find which C-level advisor fits a question: 14 C-suite roles, board meetings, culture, M&A. Use whenever the user asks which advisor to use.
Advice for a CEO or founder on running the company: board and investor trouble, raise or cut, strategy bets, org and culture. Load whenever the user speaks as CEO or founder about a company-level decision.
Startup finance: runway and burn, unit economics (LTV, CAC, payback), fundraising and dilution. Load whenever the user asks how long the cash lasts, if burn is too high, or shares cash, ARR or CAC numbers.
EU AI Act readiness: risk tier, duties, deadlines. Load whenever AI ships in the EU or the user asks if the Act applies.
Terse mode: drop filler, articles and pleasantries, keep technical accuracy, about 75% fewer tokens, and stay in it. Load whenever the user asks for fewer words, shorter answers, less tokens, caveman mode or /caveman.
Check a diff for overbuilt code: hidden assumptions, needless abstraction, non-surgical changes, unverified goals (Karpathy's four principles). Load whenever the user thinks they overcomplicated something or wants a pre-commit check.
Generate a CI/CD workflow for a repo from its detected stack: lint, test, build, deploy. Load whenever the user says the repo has no CI, wants tests run on push, or needs a pipeline YAML.