jtbd

jtbd is a skill for Claude Code from ironyjk/strategy-frameworks. It costs 45 tokens per session (3,391 once invoked), scanned A, original, MIT.

A customer-research framework that asks what practical, emotional, or social outcome people are trying to achieve when they choose a product. It treats a product as something people “hire” to complete a job.

In plain words
What is it for?
Use it to write job statements, investigate purchase decisions, and design products around the outcomes customers need.
Why use it?
It can reveal why customers choose a solution more clearly than demographics or broad product preferences alone.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the strategy-frameworks plugin — 27 skills shipped together

Install

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.

agentmods
npx agentmods add skills/ironyjk/strategy-frameworks/jtbd
Any agent
npx skills add ironyjk/strategy-frameworks --skill jtbd
Clone the repo
git clone --depth 1 https://github.com/ironyjk/strategy-frameworks

Made for: Claude Code.

Or install strategy-frameworks, the plugin that ships this one along with the rest of its 27 skills.

Wrote 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.

agentmods badge for jtbd

README.md
[![agentmods](https://agentmods.dev/badge/skills/ironyjk/strategy-frameworks/jtbd.svg)](https://agentmods.dev/skills/ironyjk/strategy-frameworks/jtbd)
Your own site
<a href="https://agentmods.dev/skills/ironyjk/strategy-frameworks/jtbd"><img src="https://agentmods.dev/badge/skills/ironyjk/strategy-frameworks/jtbd.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,391 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.03391
Opus 5 $0.00023 $0.01695
Sonnet 5 $0.00009 $0.00678
Haiku 4.5 $0.00005 $0.00339

Measured 6d ago against content hash 35741a0874cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

jtbd 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 6d 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.

jtbd/SKILL.md · 334 lines

How it starts

The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Jobs to Be Done (JTBD) Framework

Core Insight: The Milkshake Story

Customers don't buy products — they hire solutions to get a job done.

Clayton Christensen's famous milkshake study: A fast-food chain wanted to sell more milkshakes. Demographics told them nothing. But when they asked "What job are you hiring the milkshake to do?", they discovered two jobs:

  • Morning commuters hired a thick milkshake to make a boring drive interesting and stay full until lunch (competing with bagels, bananas, donuts)
  • Evening parents hired a milkshake to be a treat for their kids (competing with toys, promises, ice cream)

Same product, two completely different jobs. The improvements for each job contradicted each other.

Key principle: The unit of analysis is the job, not the customer or the product.


Job Statement Format

A well-formed job statement follows this structure:

"When [situation/context], I want to [motivation/action], so I can [expected outcome/benefit]"

Examples:

  • "When I'm commuting alone in the morning, I want something to keep me occupied and full, so I can make the drive enjoyable and not be hungry before lunch."
  • "When a production line breaks down unexpectedly, I want rapid expert response, so I can minimize downtime and meet delivery commitments."

Rules for Good Job Statements

  1. Situation first — jobs are triggered by circumstances, not demographics
  2. Stable over time — jobs don't change even when solutions do (people have always needed to "get from A to B")
  3. Solution-agnostic — never mention products or technologies in the job statement
  4. Functional verb — use action verbs (achieve, reduce, maintain, avoid, manage)

Three Dimensions of Jobs

Every job has three layers. Most companies only address the functional layer, leaving emotional and social jobs to competitors.

1. Functional Jobs (기능적 직무)

The practical task the customer wants to accomplish.

  • "Clean industrial tanks to specification within the maintenance window"
  • "Remove sludge without damaging equipment"
  • Measured by: speed, quality, cost, reliability

Read the full file on GitHub · 334 lines

Changes

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.

  1. 6d ago First seen · 334 lines · 45 tokens per session scan A 35741a0874cf

Subscribe to this mod's changes

jtbd is a skill published in the GitHub repository ironyjk/strategy-frameworks (11 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 3,391 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

new-venture

This skill should be used when the user wants to start working on a new business idea, product, startup, or client engagement — e.g. "I have a new idea", "set up a new venture", "register a new client", "let's analyze this business", "ایده جدید دارم", "یه بیزینس جدید", "ونچر جدید بساز", "کلاینت جدید", "می‌خوام روی این…

heyparsadev/claude-venture-plugin · 118 tokens

ceo-skill

CEO decision-making advisor and strategic thinking partner. Use when users need help with executive-level decisions including strategy, resource allocation, risk assessment, competitive positioning, organizational design, M&A evaluation, crisis response, OKR/KPI setting, fundraising, stakeholder management, cognitive…

AIPMAndy/CEOskill · 133 tokens

bill-gates

Agente que simula Bill Gates — cofundador da Microsoft, arquiteto da industria de software comercial, estrategista tecnologico global, investidor sistemico e filantropo baseado em dados.

aboalrejal-ai/skills · 46 tokens

apply-fast-follower-strategy

Use when deciding whether to pioneer a new product category or market first, or deliberately let competitors validate it before entering with superior execution — per Duan Yongping's 敢为天下后 ("dare to follow, not pioneer") principle.

jeffreytse/grimoire-core · 55 tokens

design-kpi-dashboard

Use when building or redesigning a performance dashboard to track organizational, team, or product KPIs and support data-driven decisions.

jeffreytse/grimoire-core · 29 tokens

customers

This skill should be used when the user wants customer discovery work — interview guides, problem validation, personas, jobs-to-be-done, or synthesizing interview/survey feedback — e.g. "make a customer interview guide", "how do I validate this problem", "build personas", "analyze my interview notes", "synthesize user…

heyparsadev/claude-venture-plugin · 132 tokens