What problem does it solve?
Users often describe solutions ("write me an article", "build me a course") instead of the underlying progress they want, leading to misaligned products, content, and AI outputs. This Skill applies the Jobs to Be Done framework to uncover the real task behind a request, the forces driving switching decisions, and the observable criteria users use to judge solutions.
Core Features & Use Cases
- Task Statement Extraction: Converts surface requests into structured JTBD statements (situation → progress → outcome) across functional, emotional, and social layers.
- Switching Force Analysis: Identifies push, pull, anxiety, and habit forces to explain why users hire or fire solutions.
- Prompt Rewriting for AI Collaboration: Translates vague requests into JTBD-anchored prompts with context, boundaries, deliverables, and acceptance criteria.
- Use Case: A founder says "customers think my course is too expensive." The Skill reframes this as a task clarification problem, identifies the progress customers actually want, and outputs selection criteria plus a minimal validation action.
Quick Start
Ask the agent to use /dbs-jtbd to analyze why users choose a particular solution and rewrite your request as a JTBD-based task statement.