agentleFS
lalulalilalulali/vespyr/.agents/skills/jtbd/SKILL.md

jtbd

Skill11 starsChanged 11 days agoMITView on GitHub

Formulate Jobs-to-be-Done statements and map How Might We opportunity questions in a single canvas. Use when the user says "what job is the user hiring this for", "turn the research into opportunities", "generate How Might We questions", or invokes /jtbd before ideation.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before ideation or solution design

    line 22
  2. Very specific:

    Run this before the complete call below, so a non-conformant canvas is never recorded as delivered.

    line 101

“Common” is measured: kept by at least 6 in 10 of the 6 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 + How Might We

What this skill does

Formulates JTBD statements using the "When/I want to/so I can" template and maps HMW opportunity questions for each job. Outputs to artifacts/output/02-research/jtbd-hmw.md.

Persona delegation

This skill delegates to @user-researcher. The user-researcher facilitates JTBD formulation and HMW mapping from human-gathered research data. The skill provides the template; @user-researcher provides the synthesis — and when no human data exists, the outputs are labeled hypotheses to validate (never observed findings).

When to use

  • "What job is the user hiring this product for?"
  • "Turn our user research into actionable opportunities"
  • "Generate How Might We questions from our findings"
  • Before ideation or solution design

Workflow

Step 1: Identify the jobs

From research data (interviews, observations, analytics), identify the functional, emotional, and social jobs users are trying to accomplish. A job is stable over time — it exists whether or not your product exists.

Step 2: Formulate JTBD statements

For each job, use the template:

When {situation/context}, I want to {functional job}, so I can {emotional/social outcome}.

Rules:

  • The "When" anchors the job in a real context (not "Whenever I feel like it")
  • The "I want to" describes the functional action (not the solution)
  • The "so I can" reveals the deeper motivation (emotional or social)

Step 3: Generate HMW questions

For each JTBD, generate 1-3 How Might We questions. HMW questions:

  • Are open-ended (not yes/no)
  • Suggest a direction without prescribing a solution
  • Reframe the job as an opportunity

Example: JTBD "When I'm running late for a meeting, I want to find the fastest route, so I can arrive without stress." → HMW: "How might we reduce the cognitive load of choosing a route under time pressure?"

Step 4: Output

Write artifacts/output/02-research/jtbd-hmw.md:

# Jobs-to-be-Done + HMW Canvas — {product/feature}
**Date:** YYYY-MM-DD
**Evidence basis:** {interviewed N / observed / analytics / support-tickets / survey / hypothesis — pick one, and label unvalidated content in the body}

## Job Stories
| # | When | I want to | So I can | Type |
|---|---------------|---------------------------|-------------------|------|
| 1 | {situation} | {action} | {motivation} | Functional/Emotional/Social |

## How Might We Opportunities
| JTBD # | HMW Question | Opportunity Size |
|--------|-------------|-----------------|
| 1 | How might we {opportunity}? | Large/Med/Small |

## Priority Matrix
| | High Impact | Low Impact |
|---|---|---|
| **Low Effort** | {quick wins} | {fill-ins} |
| **High Effort** | {strategic bets} | {money pits} |

Done when — checked mechanically

These canvases shipped for the whole life of this repo with no gate at all: the template in the Output step could be written to disk verbatim and nothing would notice. discovery_canvas_check.js now checks form and evidence declaration:

node .agents/scripts/discovery_canvas_check.js check --kind jtbd --file artifacts/output/02-research/jtbd-hmw.md --json

It requires:

  • no unfilled template placeholders — {direct quotes} and {pain point} are the template, not an artifact
  • **Evidence basis:** declared — one of interviewed / observed / analytics / support-tickets / survey / hypothesis. A canvas that does not say where it came from cannot be read as research, and nothing downstream can tell your finding from your guess
  • when the basis is hypothesis, the body must say so too — announced only in a header, a hypothesis reads as a finding three paragraphs later
  • the kind's structural minimum, below

A green result is not a research finding. The gate checks form and one declaration. It cannot tell you whether the analysis is correct, and it does not pretend to.

Exit 0 conformant · 1 failures · 2 usage/IO error, fail-closed, never a silent pass.

Run this before the complete call below, so a non-conformant canvas is never recorded as delivered. JTBD minimums: at least one job statement with three substantive clauses; every job typed Functional/Emotional/Social, without which the canvas collapses into a feature list; and at least one How Might We row.

State machine integration

At start: Run node .agents/scripts/orchestrator_state.js status At end: Run node .agents/scripts/orchestrator_state.js complete --agent user-researcher --artifact 02-research/jtbd-hmw.md

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.