Skills & Setups
These are copyable configurations — Claude Skills and Projects, custom GPTs, Gemini Gems — that put this site's decision framework inside the AI you already use. Each one comes with the config itself and the reasoning behind every constraint, because a system prompt you don't understand is a tool you can't fix. They're deliberately opinionated: they ask before they answer, they demand counted numbers over felt ones, and they'll decline to do the thing that usually goes wrong. That's not a limitation. That's the product.
A skill is something an AI becomes — a standing role, installed once, with rules it applies every conversation whether or not you remember to ask. What you'll find in The Prompt Library is what you say: one-run artifacts where you hold the discipline. Everything on this page earns its place by needing to exist as behavior — a refusal that survives being argued with, a question order that can't be peeked at, a limit that holds on every input. If it only needed saying once, it would be a prompt, and it would live over there.
One rule governs all three: the configs are self-contained. The AI running one can't read the books and can't visit this site — so every rule it executes is written into the instructions themselves, and the book reference inside each config exists for exactly one job: giving the model a scripted answer when a user asks where does this come from, instead of letting it improvise about a book it's never seen. A config that leans on an outside reference is a config that makes things up. These don't.
4 of 4 skills
All skills
- Claude Skill · GPT · Gem
The Kickoff — AI Project Planner
A planning assistant that runs the thirty-minute kickoff most AI projects skip — scope, chunks, sequence, verification, recovery — and won't start the actual work until the plan exists.
PlanningProject setupView skill - Claude Skill · GPT · Gem
The Triage — Tool, Toy, or Trash
The site's sixty-second triage as an interviewer — for people who live inside ChatGPT or Claude and want the call rendered where they already work. It asks the behavioral questions one at a time, keeps the scoring invisible, and ends with the call, the tells from your own answers, and the yearly math.
Decision-makingAuditingView skill - Claude Skill · GPT · Gem
The Pitch Decoder — AI Vendor Pitch Analyzer
Paste any AI vendor pitch — a landing page, sales email, or proposal — and get it translated into plain language, tested for label inflation, and turned into the six questions to ask that specific vendor.
Vendor evaluationDecision-makingView skill - Claude Code · CLAUDE.md
The Guardrails File — Claude Code CLAUDE.md
The standing rules an autonomous coding agent becomes — scope, git discipline, secrets, workspace hygiene, context management, testing, stopping conditions, and cost control. Claude Code auto-loads it from the project root, so you don't run it, you install it.
Autonomous codingAgent guardrailsView skill
No skills match. Try a different platform or term.