wonder

Solid

Question the work before doing it — the interview that turns a raw idea into a confirmed problem statement. Use when a tracked piece of work is at its wonder stage, or when starting the Working Genius flow on a new idea.

AI & Automation 5 stars 0 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 80/100

Stars 20%
26
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Wonder The genius of questioning. Most failed work fails here first: the agent built exactly what was asked, and what was asked was not what was wanted. Wonder closes that gap before any design exists. Run the `genius-file` skill: create the work file (or read it if it exists) and work in its Wonder section. ## The interview The interview runs until the problem statement survives restatement — the user says "yes, that's it" to words *you* wrote back to them. It proceeds in **rounds**: each round a small batch of questions the user answers together, their answers seeding the next, deeper round. Walk the branches below through the rounds — earlier branches anchor later ones, and a round may span branches when its questions are independent. Rules of the interview: - **The interview is live dialogue in every mode — the mode invariant.** `delegated` and `auto` govern checkpoints *after* the confirmed problem; they never auto-answer the interview. Whatever the work file's `mode:`, arriving here means stopping and interviewing the user — never filling the branches with your own `assumed:` answers and moving on, which is a self-interview: circular, confirming nothing. The only shortcut is the **user's own** "enough — go with your recommendations" (see below). User unreachable? The work waits at Wonder. - **Open with the story, not the questions.** Real reviews start with the walkthrough; play it back: before Round 1, tell the user the story you'd build as you currently unders...

Details

Author
donald-ada
Repository
donald-ada/workinggenius
Created
3 weeks ago
Last Updated
4 days ago
Language
Shell
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category