customer-discovery-jtbd-synthesis
Skill3 starsChanged 8 months agoMITView on GitHub
Turn interview notes, assumptions, or market context into customer discovery findings, jobs-to-be-done synthesis, and actionable product/GTM recommendations.
In this repository19 other files it gives its agents.
- event-tracking-planSkill
- experiment-design-readoutSkill
- launch-planSkill
- north-star-metricSkill
- onboarding-activation-auditSkill
- positioning-messagingSkill
- pricing-packaging-hypothesisSkill
- retention-diagnosisSkill
- seo-geo-content-briefSkill
- customer-discovery-jtbd-synthesisSkill
- event-tracking-planSkill
- experiment-design-readoutSkill
- launch-planSkill
- north-star-metricSkill
- onboarding-activation-auditSkill
- positioning-messagingSkill
- pricing-packaging-hypothesisSkill
- retention-diagnosisSkill
- seo-geo-content-briefSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
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
- Distinctive: line 9
Use this skill when the user wants to turn messy customer research into structured insights about problems, motivations, switching …
- Distinctive: line 37
If actual research is absent, create a discovery plan and a provisional synthesis from assumptions.
- Distinctive: line 42
Treat people as experts in their problem, not the solution.
- Distinctive: line 44
Look for the switching moment and the forces around it.
- Distinctive: line 46
Keep outputs concise enough for product and GTM teams to actually use.
- Distinctive: line 72
Write job stories in this structure:
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Customer Discovery + JTBD Synthesis
Use this skill when the user wants to turn messy customer research into structured insights about problems, motivations, switching triggers, and recommended actions.
What this skill must produce
Always produce:
- Research objective
- Customer segments
- JTBD synthesis
- Switching / buying forces
- Job stories
- Insight summary
- Implications for product
- Implications for marketing / sales
- Open questions / next interviews
Inputs to gather
Use any provided:
- interview notes / transcripts
- survey responses
- founder assumptions
- support tickets
- sales calls
- win/loss notes
- persona docs
- feature requests
If actual research is absent, create a discovery plan and a provisional synthesis from assumptions.
Working rules
- Focus on the problem and progress the customer seeks, not requested features.
- Treat people as experts in their problem, not the solution.
- Distinguish what they want from why it matters.
- Look for the switching moment and the forces around it.
- Capture situations, motivations, and outcomes in job-story form.
- Keep outputs concise enough for product and GTM teams to actually use.
Step-by-step method
Step 1: define the research objective
State what decision this discovery is meant to inform.
Step 2: segment the customers
Cluster participants into meaningful groups based on problem shape, context, and buying situation.
Step 3: extract the job
For each segment identify:
- functional job
- emotional job
- social job
- success criteria
- obstacles / anxieties
Step 4: identify switching forces
Capture:
- push of the situation
- pull of the new solution
- habit of the old solution
- anxieties of the new solution
Step 5: convert to job stories
Write job stories in this structure:
When [situation]
I want to [motivation]
so I can [desired outcome].
Step 6: extract implications
Translate into product, onboarding, messaging, sales, and pricing implications.
Output structure
Research objective
- Decision to inform:
- Source material reviewed:
- Confidence level:
Customer segments
| Segment | Distinguishing traits | Main job |
JTBD synthesis
For each segment provide:
- Functional job:
- Emotional job:
- Social job:
- Desired progress:
- Current workaround:
- Main obstacle:
Switching / buying forces
| Segment | Push | Pull | Habit | Anxiety |
Job stories
Provide 3-8 job stories total.
Insight summary
- Repeated pain themes:
- Strongest motivations:
- Surprising contradictions:
- What customers call the problem:
- What they are really comparing against:
Implications for product
- onboarding implications
- feature / workflow implications
- packaging implications
- activation implications
Implications for marketing / sales
- positioning implications
- message / copy implications
- proof needed
- objection handling
- sales discovery questions to add
Open questions / next interviews
List the top unanswered questions and the next interview targets.
If there are no interview notes yet
Produce:
- a discovery plan
- target participant profiles
- 15-20 interview questions
- a synthesis template to fill after interviews
Interview questions must prioritize:
- recent switching moments
- prior solutions
- why the old way became insufficient
- what almost stopped the switch
- what success looks like
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
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.

