Browse Skills

Drive Motivation designs intrinsic motivation systems using Autonomy, Mastery, and Purpose for products and teams. Use when gamification, rewards, or engagement loops aren't working and you need onboarding progression or team structures that sustain performance.

Good Strategy Bad Strategy helps formulate and audit real strategy using Richard Rumelt's kernel of diagnosis, guiding policy, and coherent action. Use it to detect the four hallmarks of bad strategy and turn goal lists or pitch decks into a working strategic kernel.

Grow App guides an existing product from leaking activation and churn to a retention engine by orchestrating eight phase skills and recording decisions in docs/. Use it when users sign up then disappear, or to build a habit loop and one trusted metric.

Grow Business guides a company from unpredictable revenue to a repeatable growth engine by orchestrating nine marketing and sales skills phase by phase, recording decisions and artifacts in docs/ so the journey resumes across sessions. Use it when revenue is real but lumpy and you need growth that repeats.

Grow Website orchestrates eight marketing and conversion frameworks in sequence to turn an existing website's traffic into more leads, buyers, referrals, and a sharper offer, recording every decision in docs/ so the journey resumes across sessions. Use it when a site has traffic but under-converts.

High Output Management applies Andy Grove's framework to measure a manager's output by their organization's output, using high-leverage activities, production indicators, meetings, OKRs, and task-relevant maturity. Use for 1:1s, OKRs, delegation, performance reviews, and manager calendars.

High Performance Browser optimizes web performance through network protocols, resource loading, and browser rendering internals. Use it when diagnosing slow pages, Core Web Vitals, HTTP/2 or HTTP/3, resource hints, render blocking, TCP/TLS, or caching strategies.

Hooked UX designs habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment). Use when users aren't coming back, designing engagement loops, building streaks or progress systems, or analyzing why users stop after signup, with ethics evaluation and onboarding for habits.

Karpathy LLM Wiki builds and maintains a personal LLM-powered knowledge base by ingesting sources into raw/ and compiling durable wiki articles with citations. Use it to query wiki knowledge, lint consistency, and compound a knowledge base over time.

Fleet Auditor detects installed agent systems, collects token usage data, identifies waste patterns, and recommends fixes with dollar savings estimates. Use it when running multiple agent systems, spending $2-5/day on agents, or suspecting idle heartbeats are burning tokens.

Resume Checkpoint fetches a prior session's checkpoint on demand when continuing prior work, returning fenced, source-labeled recovery context. Call it when a user says continue or resume and the SessionStart pointer was not enough.

Token Coach analyzes a Claude Code or Codex setup and provides personalized token-efficiency coaching with measured numbers. Use it before building something new, when an existing setup feels slow, or for a quick health check.