jtbd
Skill4 starsChanged 7 months agoMITView on GitHub
Frame a vague goal as the job to be done, so the outcome is explicit before you build or choose. TRIGGER when: user says 'what's the job', 'JTBD', 'frame the outcome', 'what are we actually trying to do'; or a goal, feature, or decision is stated as a solution with the progress underneath it unnamed.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- denormans/claude-code-workflowtheir own version, first seen Nov 8, 2026
- kasperjunge/skillstheir own version, first seen Nov 8, 2026
- lalulali/vespyrtheir own version, first seen Nov 6, 2026
- ajstars1/founder-stacktheir own version, first seen Oct 25, 2026
- ironyjk/strategy-frameworkstheir own version, first seen Oct 17, 2026
- denchik2245/Skillstheir own version, first seen Oct 9, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- glebis/claude-skills★ 410same name
- neurofoo/agent-skills★ 111same name
- ironyjk/strategy-frameworks★ 14same name
- lalulali/vespyr★ 11same name
- kasperjunge/skills★ 7same name
- ajstars1/founder-stack★ 1same name
- denchik2245/Skills★ 1same name
- denormans/claude-code-workflow★ 1same name
- ajstars1/startup-coach★ 0same name
- JAVICHILEON/claude---Skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-soulSkill
- audit-transcripts-for-learningsSkill
- best-answerSkill
- check-coherenceSkill
- compress-fileSkill
- deep-modulesSkill
- design-critiqueSkill
- durable-docs-updateSkill
- execute-chatSkill
- execute-planSkill
- explain-deeplySkill
- explain-simplySkill
- find-gapsSkill
- fix-verify-loopSkill
- generate-mockupsSkill
- grill-meSkill
- handoffSkill
- interview-meSkill
- map-design-languageSkill
- memory-pruneSkill
- multi-agent-analysisSkill
- place-factSkill
- post-purchase-ui-extensionSkill
- product-interviewSkill
- prove-behaviorSkill
- refine-fileSkill
- second-opinionSkill
- sentry-analysisSkill
- shopify-dev-mcpSkill
- structure-proseSkill
- tech-designSkill
- test-completed-planSkill
- tighten-fileSkill
- tighten-instructionSkill
- tldrSkill
- triageSkill
- trim-specSkill
- two-pass-reviewSkill
- validate-answerSkill
- vet-factSkill
- write-planSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
2
Distinctive
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 24
Check the outcome is progress, not a restated feature: Test: could a completely different solution deliver the same outcome?
- Distinctive: line 51
Ask: "Add a bulk-export button to the orders page."
“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.
Files
JTBD — Job To Be Done
Primitive: JTBD — name the job the user is hiring for, then judge every option by job-fit.
People hire a product to make progress in a situation — the job is that progress, not the feature they ask for or who they are.
The lens — a job is one story:
when [situation], I want to [motivation], so I can [outcome], without [constraint].
- Situation — the trigger and context they're in.
- Motivation — what they reach for; the core desire.
- Outcome — the progress that ends the story.
- Without — the pain or constraint they're avoiding; often where the real insight sits. Name it when it sharpens the job.
Steps
- Find and draft the job. Read the thread for the job in play. If several are live, list them and ask which — or name the primary; don't silently pick. Write it in the lens format, marking any unsupported part
[unclear]— never fill a slot with a guess. - Check the outcome is progress, not a restated feature. Test: could a completely different solution deliver the same outcome? If not, it's a feature — ask "so they can what?" until it lands on progress.
- Score the options by job-fit — not elegance, effort, or novelty; the without usually separates them. If only the asked-for path is live, add 1–2 alternatives. Then state it back in the format below.
Job frame — the shape to state back:
Job: when [situation], I want to [motivation], so I can [outcome], without [constraint]
(any unsupported part → [unclear])
Confidence: 0.00–1.00 — how well the thread supports the job; blanks and assumptions lower it
Options (when choosing):
| Option | Job-fit 0–1 | Serves the *without*? |
|---|---|---|
Winner: the option that best gets the job done — one line(Write Job unclear — [which parts are blank and why] when the thread doesn't support a job.)
Examples
Job statements — the format filled across domains
- Milkshake — when I face a long, boring commute, I want a thick, filling treat, so I can keep a hand busy and my stomach full, without making a mess in the car.
- Spotify Discover Weekly — when I want music while I work, I want fresh tracks I'll probably like, so I can stay in flow, without stopping to curate a playlist.
- PayPal — when I'm buying online, I want a fast, trusted way to pay, so I can check out in seconds, without re-entering my card or fearing fraud.
A worked reframe — from a solution-shaped ask to the output format
Ask: "Add a bulk-export button to the orders page."
- Job — when I'm reconciling last month's sales in my accounting tool, I want my order data out of the app, so I can close the books, without having to remember to pull it every month.
- Confidence — 0.6: the thread gave the ask and the reconciling context, but the monthly without is inferred, not stated.
Options —
Option Job-fit 0–1 Serves the without? Export button (asked for) 0.5 No — relies on remembering to click each month Scheduled CSV email 0.9 Yes — arrives monthly, no memory needed - Winner — scheduled CSV email: gets the job done without the user remembering, so the asked-for feature loses to a better fit.
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.

