reasons-people-buy
Skill112 starsChanged 7 months agoMITView on GitHub
Ground persuasive writing in a real reason people buy. Use when writing or editing copy meant to make someone buy, subscribe, or act (landing pages, ads, offers, positioning), or when auditing a draft that reads as feature-speak — "why would anyone buy this?", "make this benefit-led", "what's the hook?".
In this repository14 other files it gives its agents.
- adversarial-roleplaySkill
- blind-spot-scanSkill
- corporate-misalignment-finderSkill
- decision-auditSkill
- focal-point-finderSkill
- make-requirements-greatSkill
- orchestrate-pm-alignmentSkill
- rulebook-for-argumentsSkill
- situation-retrospectiveSkill
- team-perspective-revealSkill
- tech-sensemakingSkill
- verbalized-samplingSkill
- vibe-code-leaf-finderSkill
- workflow-trellisSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 42
Write from the 15; check against the 8 that you've found the real driver rather than a surface benefit.
- Very specific: line 52
Read references/sources.md when the top-level guidance isn't enough — it encodes the full source material:
≈ “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
Reasons people buy
People buy to move toward a feeling or an outcome, never to own a feature. Copy that names what a product is or does leaves the reader to supply the reason themselves, and most won't. Name the reason first; let the feature prove it.
The move
For every line meant to persuade:
- Name the reason. Match the line to a reason on the list below. A line that maps to none is feature-speak — cut it or rewrite it. Done when every retained line traces to one named reason.
- Say the outcome, not the mechanism. What the buyer gets ("stop losing an hour a day to this"), not how it works ("automated workflow engine").
- Lead with the reason, prove with the feature. Reason in the headline or first line; the feature sits underneath as evidence.
The list
The working spine — 15 reasons people buy stuff:
- To avoid effort
- To feel happier
- To save time
- To be comfortable
- To escape pain or guilt
- To make money
- To save money
- To get recognition
- To be healthier
- To feel secure
- To alleviate fear
- To feel special
- To increase status
- To feel loved
- To get knowledge
Beneath every reason sits one of eight deeper drives (Josh Kaufman, The Personal MBA) — the reason wearing work clothes:
money · status · power · love · knowledge · protection · pleasure · excitement
Write from the 15; check against the 8 that you've found the real driver rather than a surface benefit.
Checks
- One primary reason per asset. A page that argues five reasons equally makes the reader feel none. Pick the primary; demote the rest to support.
- Match the reason to the journey stage. Effort, time, pain, guilt, and fear pull people who don't yet know they have a problem; recognition, status, love, and feeling special close people already deciding.
- Test the phrasing against how a real buyer talks — their vocabulary, not yours. Language accuracy is what makes a line land; guessed language reads as an ad and gets skipped.
References
Read references/sources.md when the top-level guidance isn't enough — it encodes the full source material:
- The 15 reasons people buy stuff (the original list)
- The core human drives — Josh Kaufman, The Personal MBA
- Buyer psychology cheatsheet — 19 biases mapped to buyer-journey stages, each with an action (Customer Camp)
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.

