CtrlK
BlogDocsLog inGet started
Tessl Logo

oh-my-ai/discovery-interview

Interactive discovery interview → structured product spec. Triggers: spec, PRD, requirements, scoping, brainstorming, new project. Uses AskUserQuestion; WebSearch/WebFetch when user wants research. Outputs user stories, acceptance criteria, constraints.

99

2.28x
Quality

100%

Does it follow best practices?

Impact

96%

2.28x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Overview
Quality
Evals
Security
Files

task.mdevals/scenario-3/

Discovery Interview: Internal Developer Portal

Problem/Feature Description

A platform engineering lead named Sam wants to build an internal developer portal for a mid-sized SaaS company. Developers currently struggle to find documentation, service ownership, runbooks, and deployment status — everything is scattered across Confluence, GitHub, Slack, and Datadog. Sam has a clear vision: a single pane of glass where developers can find what they need and see service health at a glance.

Sam is technically experienced, knows what they want architecturally, and answers questions decisively. Sam has already decided on a tech stack (React frontend, Go backend, PostgreSQL). Sam doesn't need much convincing or research — they just need to be walked through a thorough requirements process so nothing important is missed.

To complete this task, play both roles: conduct the interview as the interviewer and provide Sam's responses. Sam is a decisive, technical respondent who gives clear answers. Conduct the full interview and document everything.

Output Specification

Produce the following files:

  1. interview_log.md — Full transcript of the discovery interview. Label each exchange (Q1, Q2, etc.) and show all answer options for each question, including which option Sam chose.

  2. The final spec file in docs/specs/ using date-prefixed naming.

evals

CATEGORIES.md

SKILL.md

SPEC_TEMPLATE.md

tile.json