Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add varunk130/ai-customer-discovery-skills --skill jtbd-extractorgit clone --depth 1 https://github.com/varunk130/ai-customer-discovery-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/varunk130/ai-customer-discovery-skills/jtbd-extractor)<a href="https://agentmods.dev/skills/varunk130/ai-customer-discovery-skills/jtbd-extractor"><img src="https://agentmods.dev/badge/skills/varunk130/ai-customer-discovery-skills/jtbd-extractor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/varunk130/ai-customer-discovery-skills/jtbd-extractor"><img src="https://agentmods.dev/badge/skills/varunk130/ai-customer-discovery-skills/jtbd-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.01637 |
| Opus 5 | $0.00025 | $0.00818 |
| Sonnet 5 | $0.00010 | $0.00327 |
| Haiku 4.5 | $0.00005 | $0.00164 |
Grade A, and why
jtbd-extractor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
JTBD Extractor
Turn raw research into Jobs-to-be-Done statements showing what users are really trying to accomplish - reframing feature requests as underlying needs and uncovering innovation opportunities.
Output
Save to discovery/outputs/jtbd-[persona]-[YYYY-MM-DD].md
When to Use This Skill
- Reframing feature requests into underlying needs
- Finding innovation opportunities in saturated markets
- Training your team to think in jobs, not features
What You'll Get
I'll generate a complete Jobs-to-be-Done analysis with:
- JTBD statements - Properly formatted "When [situation], I want to [action], so I can [outcome]"
- Job categories - Separated into Functional, Emotional, and Social jobs
- Opportunity scores - Importance + (Importance - Satisfaction) to show where to focus
- Evidence tracking - Direct quotes and behavior supporting each job
- Feature translation - Mapping what users asked for to what they actually need
- Top opportunities - Ranked list of underserved jobs worth solving
What You'll Need
- Interview transcripts, survey responses, or customer feedback
- Context on your product/market
Process
Step 1: Review Your Context
I'll start by checking your context files to understand what you already know:
- personas.md - What jobs do your existing personas have?
- product.md - What problems does your product solve today?
- Research files - Any prior interview snapshots or feedback data?
I'll share what I find. For example:
"I see your personas in personas.md already have some Jobs-to-be-Done statements. I'll compare what I extract from this research to see if it confirms or expands on those jobs."
Step 2: Request Research Data
If you haven't provided data yet, I'll ask:
"I need research data to extract jobs from. Do you have any of these?
- Interview transcripts or notes
- Survey responses (especially open-ended)
- Support tickets or feature requests
- Customer feedback
You can paste it here or point me to files in your context/ folder."
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/jtbd-overview.png 562 KB
- CHANGELOG.md 558 B
- docs/AUDIO_INPUT_MODE.md 6.3 KB
- docs/jtbd-overview.html 17 KB
- examples/sample-data.json 6.7 KB
- examples/sample-jtbd-sales-marketing-finance.md 20 KB
- examples/sample-output.html 23 KB
- examples/sample-output.md 9.9 KB
- examples/synthetic-interview.md 1.5 KB
- jtbd/__init__.py 298 B runs code
- jtbd/cli.py 2.0 KB runs code
- jtbd/models.py 4.6 KB runs code
- jtbd/renderer.py 15 KB runs code
- pyproject.toml 276 B
- README.md 11 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 185 lines · 50 tokens per session scan A b95038be93e7
jtbd-extractor is a skill published in the GitHub repository varunk130/ai-customer-discovery-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 1,637 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
solution-architecture
Produces a discovery-grade architecture: enough detail to estimate effort, surface technical risks, and explain choices to the client — but not detailed design. Detailed design happens in delivery, not here. Where the BA isn't a tech lead, this skill is best run pair-mode with an architect; otherwise it produces vague…
profile-builder
Produces discovery-context.md — the single source of truth that every other skill in this pack reads. Without it, other skills will warn and offer to bootstrap inline (a 2–3 question mini-interview held in conversation, not written to disk). Running this skill first gives the best, most consistent results.
insight-synthesis
Turns whatever evidence the BA managed to gather into structured insights — weighted by source quality so the team doesn't treat one SME's hunch as equal to five user interviews.
user-interviews
Direct user interviews. Run only when useraccess allows it.
journey-mapping
Turns a persona's lived experience into a stage-by-stage map that surfaces where pain concentrates and where opportunity moments hide. Each pain point is evidence-anchored; each opportunity moment links back to the opportunity-tree.md so journey work doesn't drift from prioritized outcomes.
proposal
Agency-to-client proposal document. The output the client reads, signs (or doesn't), and budgets against.