Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

JTBD Discovery Techniques · nwave-ai | DecimalAI

researchby nwave-ai

JTBD Discovery Techniques

nwave-ai/nw-jtbd-interviews

Source nwave-ai/nwave ↗License MIT

JTBD discovery techniques adapted for AI product owner context. Four Forces extraction, job dimension probing, question banks, and anti-patterns for interactive feature discovery conversations.

SkillScore100Maintained

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Product Management pack

Last verified 8/16/2026

What it changes

Passed 24 of 24 test cases with the skill, and 20 of 24 without it.

Without skill83%

With skill100%

Checks it passed that the model alone missed

Select scale probe as the deepening technique.
Select contrast probe as the deepening technique.
Select inversion probe as the deepening technique.

and 3 more in the full report

4 fixed20 passed either way0 still failing0 broke

Pass-rate lift: +17 pp
Tokens: +78%
Agent turns: 0%
Response time: -26%

Model gemini-3.6-flashMeasured 8/16/2026v124 of 24 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/nwave-ai-nw-jtbd-interviews/SKILL.md https://app.decimal.ai/s/nwave-ai-nw-jtbd-interviews/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add nwave-ai-nw-jtbd-interviews, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/nwave-ai-nw-jtbd-interviews/ and pins it in .decimal/skills.lock

decimalai skills add nwave-ai-nw-jtbd-interviews

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/nwave-ai-nw-jtbd-interviews/SKILL.md https://app.decimal.ai/s/nwave-ai-nw-jtbd-interviews/SKILL.md

Raw file: /s/nwave-ai-nw-jtbd-interviews/SKILL.md ↗ · machine-readable summary at /s/nwave-ai-nw-jtbd-interviews.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

An interviewee conflates two distinct issues during a call: 'Our weekly summary takes too long to generate, and my boss always complains about the table formatting.' Select the appropriate deepening technique to unpack these conflated concerns and state the question pattern.

What was checked, without and with the skill
Checked	Without skill	With skill
Select contrast probe as the deepening technique.	Missed	Passed
Use a question pattern comparing how one concern differs from the other.	Missed	Passed

case-05 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md137 linessingle file

JTBD Discovery Techniques

Use when conducting interactive discovery conversations to uncover jobs users are trying to accomplish. Adapted from Bob Moesta's Switch interview methodology for AI-guided feature discovery — the user describes their situation, Luna extracts forces and jobs through structured questioning.

Four Forces Extraction

Map user responses to Four Forces of Progress. Each force has characteristic language patterns to listen for and prompts to surface them.

Force 1: Push of Current Situation

User says: "I'm frustrated that..." | "It keeps breaking when..." | "I waste so much time on..." | "The last straw was when..."

Prompts:

"What's your biggest frustration with how things work now?"
"Tell me about the worst experience with the current approach."
"What finally made this intolerable?"
"What triggered this request — was there a specific incident?"

Force 2: Pull of New Solution

User says: "I want to be able to..." | "I imagine being able to..." | "My colleague said it could..." | "I need it to..."

Prompts:

"What would the ideal outcome look like?"
"What could you do that you can't do now?"
"What specific capability excites you most about this?"
"If this worked perfectly, what would change in your workflow?"

Force 3: Anxiety of New Solution

User says: "I'm worried that..." | "What if it doesn't..." | "I'm not sure I can learn..." | "The risk is..."

Prompts:

"What concerns do you have about this new approach?"
"What could go wrong that would make you regret this change?"
"What would need to be true for you to feel safe adopting this?"
"Is there anything that almost made you not request this?"

Force 4: Habit of Present

Track record

Benchmark

24 / 24

test cases passed, vs 20 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

nwave-ai / nwave

nWave/skills/nw-jtbd-interviews/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

JTBD Discovery Techniques

Four Forces Extraction

Force 1: Push of Current Situation

Force 2: Pull of New Solution

Force 3: Anxiety of New Solution

Force 4: Habit of Present

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills