Finding Unknowns Skills — Development skill for Claude Code

Finding-Your-Unknowns Claude Code Guidelines

Maintained by [泊舟 Bozhou](https://x.com/bozhou_ai) — I write about AI and agentic coding on X, follow me at [x.com/bozhou_ai](https://x.com/bozhou_ai).

English | [简体中文](./README.zh.md)

A single `CLAUDE.md` file that turns [Thariq's (Anthropic) field guide](https://x.com/trq212/article/2073100352921215386) — *A Field Guide to Fable: Finding Your Unknowns* — into behavioral guidelines for Claude Code.

The Problem

From Thariq's article:

Working with Claude Fable 5 keeps re-teaching me an old lesson: the map is not the territory.

The difference between the map and the territory is what I call unknowns. When Claude runs into an unknown, it needs to make a decision based on its best guess of what I want.

Fable is the first model where I find the quality of the work is bottlenecked by my ability to clarify its unknowns.

Your prompt is a map. The codebase is the territory. Everything you didn't say — and everything you didn't know to say — is an unknown, and every unknown forces Claude to guess. Accumulated wrong guesses are how long tasks go badly off course.

The Solution

Make Claude an active partner in discovering your unknowns, at every stage:

Technique	Stage	Uncovers
Blindspot Pass	Pre-implementation	Unknown unknowns
Brainstorm & Prototype	Pre-implementation	Unknown knowns
Interview	Pre-implementation	Known unknowns
References	Pre-implementation	What you can't put into words
Implementation Plan	Pre-implementation	Decisions you'll want to tweak
Implementation Notes	During implementation	Deviations from the plan
Explainer & Quiz	Post-implementation	What actually changed

The Four Kinds of Unknowns

• Known knowns — what's in your prompt.
• Known unknowns — what you know you haven't figured out yet.
• Unknown knowns — what's so obvious you'd never write it down, but you'd recognize it if you saw it.
• **Unkno