Stage-by-stage product management workflow: discovery, positioning, strategy, prioritization, PRD, delivery, launch, and measurement — with framework menus, fill-in templates with quality bars, evidence rules, a shared project workspace, and a built-in critique gate.
10 skills
Uplevel prompts with the right guardrails, verify AI answers before they ship, teach staff to prompt better, and keep the guidance current via a human-approved refresh cycle.
4 skills
Run the eleven gut-check questions from 'It Said It Was Fine' on your own AI-built app, read-only, and get a plain report: what is broken, what it means for you, and what your code can't tell. Works in Claude Code and Codex.
1 skill · 1 agent · hooks
Shows where your AI-built app decides the same thing twice (who sees what, what things cost, who has paid, how money rounds), what each one means for you, and how the app is built. It also warns, on its own, when your app does one job with two or more libraries, or when a JavaScript app lists parts it does not use. Read-only; a review, not an audit.
1 skill
Decision Census is now Build Decisions. This pointer tells you how to install build-decisions and remove this plugin. It runs nothing.
1 skill
A self-development coach for product managers: competency baseline against a behavioral rubric, growth plan with weekly deliberate-practice reps, and evidence-based progress tracking using your real work artifacts.
1 skill
When Claude stops to ask you a technical yes/no or choice, it spells it out first: the ask, where things stand, what each answer changes, whether you can undo it, its pick, the safe answer if you're not sure, and a one-line TL;DR. For people who build with AI but don't read code.
1 skill