agentleFS
miguelclavelmiguelclavel/ux-research-skills/skills/jobs-to-be-done/SKILL.md

jobs-to-be-done

Skill1 starsChanged 39 days agoMITView on GitHub

Frame user needs as jobs to be done: the progress people are trying to make, the forces that push and hold them, and job statements a team can design against. Use when someone mentions JTBD, wants to understand why people switch products, or needs need statements that are not tied to features.

23 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use proto-persona, acquisition-channel-advisor and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • nandanosqlSkill

    proto-persona

    Create hypothesis-driven user personas before doing full research. Uses behavioral attributes, goals, and frustrations to model target users quickly for early-stage alignment.

    Also in 4 projects that use this

  • nandanosqlSkill

    acquisition-channel-advisor

    Evaluate and recommend customer acquisition channels based on product type, target audience, budget, and stage — covering organic, paid, referral, partnerships, and product-led growth.

    Also in 3 projects that use this

  • brainbytes-devSkill

    balanced-scorecard

    Also in 3 projects that use this

  • +8 more from nandanosql

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 20 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Don't write jobs that name your product or a feature.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Jobs to be done

People don't want the product, they want the progress. Frame the need as the job, and the product becomes one way to get it done.

Steps

  1. Find the moment of switching in the research: when someone started looking for a new way, what triggered it, what they compared, and what they chose.
  2. Write the main job statement: "When [situation], I want to [motivation], so I can [expected outcome]." For example: "When my insurance renewal goes up, I want to see quickly whether I'm overpaying, so I can switch without risking worse cover."
  3. Map the four forces:
    • Push of the current situation (what's wrong now)
    • Pull of the new solution (what they hope for)
    • Anxiety about the new (what could go wrong)
    • Habit of the present (why staying is easy)
  4. List related jobs: functional (get it done), emotional (feel in control), social (look responsible).
  5. Desired outcomes: what "done well" means, measurable where possible ("know my real price in under two minutes").

Output

The main job statement, the four forces as a two by two list, related jobs, and the desired outcomes, each linked to the research it came from.

Don't

  • Don't write jobs that name your product or a feature. Don't skip anxiety and habit: they're why people don't switch.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.