Jobs-To-Be-Done (JTBD) Customer Research

What it does

Jobs-To-Be-Done (JTBD) Customer Research is a Cursor skill: a SKILL.md playbook that AgenticKit installs at .cursor/skills/jtbd-interview. Cursor's agent loads it when the task matches the skill description, instead of stuffing the same rules into every chat.

Conducting Jobs-To-Be-Done customer interviews to understand the emotional and functional triggers that motivate users to buy.

Push/pull forces, customer timeline interviews, and outcome-driven specs. The file is domain knowledge, not a slash macro. You do not type it. The agent reads it when the job is jtbd interview.

Why it exists

Default Cursor has no memory of how your team ships positioning, copy, and launch assets. Founders paste the same conventions into chat, then watch the model drift on the next turn. This skill exists so those conventions live on disk and load only when relevant.

It ships in the Marketing Kit. It is wired to the User & JTBD Researcher (market-researcher) and Product Positioning Expert (positioning-strategist) agents. It is wired to the /feature-spec: PRD & Product Feature Requirement Spec and /positioning: Product Positioning & ICP Strategic Framework commands. That graph is the point: the skill is the standard, the agent is the role, the command is the trigger.

When to use it

• Use Jobs-To-Be-Done (JTBD) Customer Research when the work is specifically about push/pull forces, customer timeline interviews, and outcome-driven specs.
• Load it before a long session that will touch this surface more than once. A one-line edit does not need the full playbook.
• Use it when you are writing something a buyer will see: landing copy, launch posts, SEO pages, or positioning docs.

When not to use it

• Do not treat the skill as a replacement for a slash command. Skills teach. Commands run a pipeline.
• Do not paste the whole SKILL.md into chat. If Cursor is not loading it, fix the description or invoke the matching command.
• Do not use it to generate spam or spray the same launch post across every channel.

Example workflow

1. Install the Marketing Kit so .cursor/skills/jtbd-interview lands in the repo.
2. Open a new Cursor agent chat pointed at the files this skill governs.
3. Ask the User & JTBD Researcher (market-researcher) to read the skill, or run /feature-spec: PRD & Product Feature Requirement Spec.
4. Review the first artifact against the practices below. If it violates one, stop and correct the file. Do not prompt 'just finish it'.
5. Commit the skill-guided files with the rest of the slice so the next session inherits the same standard.

Example usage

Example prompt: "Read .cursor/skills/jtbd-interview and apply it to this change. Do not invent extra conventions."

Or trigger the pipeline: /feature-spec: PRD & Product Feature Requirement Spec. That command is written to load this skill.

Check the output against: Investigate the specific moment the user decided to look for a solution

Example output

• The skill itself does not write a single output file. It changes what the agent is allowed to produce in positioning, copy, and launch assets.
• When you run /feature-spec: PRD & Product Feature Requirement Spec, expect repo files plus notes under docs/, not a chat-only answer.

Best practices

• Investigate the specific moment the user decided to look for a solution
• Unpack the 4 forces: Push of current situation, Pull of new idea, Anxiety, Habit
• Focus on past purchasing behavior rather than speculative future wishes
• Extract exact customer verbatim quotes to use directly in hero copywriting

Common mistakes

• Ignoring "Investigate the specific moment the user decided to look for a solution" and hoping a later prompt will clean it up.
• Copying the skill into .cursor/rules as always-on. That burns context and fights Cursor's load-on-match design.
• Running two overlapping skills that contradict each other in the same turn.
• Publishing generated copy without a human pass. The skill is a playbook, not a publisher.