ContagiousCAUTION
Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io agents.
Overview
Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io agents.
c502026d022aOBSERVED · 2026-10-09What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: contagious description: 'Engineer word-of-mouth and virality using the STEPPS framework (Social Currency, Triggers, Emotion, Public, Practical Value, Stories). Use when the user mentions "go viral", "word of mouth", "shareable content", "social currency", "why people share", "referral program", "nobody is sharing it", or "make this spread". Also trigger when designing shareable features, crafting social campaigns, or building products that spread through peer recommendation. Covers environmental triggers and high-arousal emotional content. For sticky messaging, see made-to-stick. For persuasion tactics, see influence-psychology.' license: MIT metadata: author: wondelai version: "1.4.0" --- # Word-of-Mouth & Virality Framework A framework for engineering word-of-mouth and making products, ideas, and content contagious, based on Jonah Berger's research into why things catch on. Use it to design shareability into products, campaigns, and content instead of hoping for luck. ## Core Principle **Virality is not born — it is engineered.** Products spread because they were designed — consciously or not — to be shared. Only 7% of word-of-mouth happens online; the other 93% happens in offline conversations, so virality is about the psychology of sharing, not social media mechanics. Those psychological patterns are predictable and can be engineered into anything using the STEPPS framework. See: [references/word-of-mouth.md](references/word-of-mouth.md) when the brief over-indexes on social media — it makes the offline-vs-online case, lists conversation triggers, and gives a WOM measurement/audit method. ## Scoring **Goal: 10/10.** Score each of the six STEPPS drivers (the six Quick Diagnostic rows) — **0** absent, **1** present but weak, **2** strong and deliberate — for a raw 0-12, then map: 11-12 -> 10, 9-10 -> 8-9, 6-8 -> 6-7, 3-5 -> 4-5, 0-2 -> <=3. Bands: - **9-10** — three or more drivers at strength 2, at least one of them Public or Social Currency (the self-propagating ones), and the brand survives the Trojan Horse test. - **6-8** — two drivers genuinely strong, but spread still leans on paid reach or product quality alone. - **<=5** — at most one weak driver; sharing is incidental, not engineered. Report the raw count, the mapped score, and the specific driver(s) to raise next to reach 10/10. ## STEPPS Overview **Not a checklist — a multiplier.** Each principle independently increases sharing; the most contagious ideas activate several at once, but even one or two done well dramatically increase word-of-mouth. | Principle | Core Question | Sharing Driver | |-----------|--------------|----------------| | **S — Social Currency** | Does sharing it make people look good? | Self-enhancement | | **T — Triggers** | What in the environment reminds people of it? | Top-of-mind accessibility | | **E — Emotion** | Does it fire up high-arousal feelings? | Physiological arousal | | **P — Public** | Can others see people using it? | Observational learning | | **P — Practical Value** | Is it useful enough to pass along? | Altruism and helpfulness | | **S — Stories** | Is the brand embedded in a narrative? | Entertainment and identity | ## The STEPPS Framework ### 1. Social Currency **Core concept:** People share things that make them look good — smart, cool, in-the-know. Make people feel like insiders and they'll spread it to boost their own image. **Why it works:** Sharing is self-presentation — listeners infer the sharer's traits from what they pass on, so people curate shares the way they curate clothes. Mechanism: give the sharer a payoff in status or identity and you outsource your marketing to their ego. **Key insights:** - **Remarkability** — surprising, novel, or extreme things make the sharer seem interesting; "Did you know...?" is a powerful sharing trigger - **Game mechanics** — leaderboards, badges, and status tiers create visible accomplishments people want to display - **Exclusivity and scarcity** — secret menus and invite-only access give people "insider knowledge" to share - **Inner remarkability** — even mundane products have a remarkable angle; it's framing, not the product **Product applications:** | Context | Application | Example | |---------|------------|---------| | Content platform | Insider statistics or year-in-review | Spotify Wrapped | | Mobile app | Shareable accomplishment cards | Duolingo streak badges | | B2B product | Benchmarking data users want to cite | HubSpot State of Marketing report | **Copy patterns:** - "Most people don't know that..." - "You're one of the first to try..." - "You've unlocked [achievement]..." **Ethical boundary:** Create real insider value, not false scarcity or manufactured exclusivity that breeds toxicity. See: [references/social-currency.md](references/social-currency.md) when a product feels unremarkable — it has the inner-remarkability exercise, game-mechanic design, exclusivity types, and a scored audit. ### 2. Triggers **Core concept:** Top-of-mind means tip-of-tongue. Link your product to environmental cues — sights, sounds, times, routines — so everyday life keeps reminding people to talk about you. **Why it works:** Most word-of-mouth is driven not by excitement but by whatever happens to be top-of-mind mid-conversation; a product linked to a frequent cue gets mentioned more because it's more accessible in memory. **Key insights:** - **Frequency beats strength** — a daily trigger (coffee) outperforms a powerful but rare one (a holiday); Kit Kat linked itself to coffee breaks - **Habitat matters** — map where and when people encounter contexts related to your product - **Competitive triggers** — link a competitor's moment to your own brand - **Ongoing vs. temporary** — persistent environmental triggers sustain word-of-mouth; event triggers only spike it **Product applications:** | Context | Application | Example | |---------|------------|---------| | Food/Beverage | Link to a daily habit | Kit Kat
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (5)
.agents/skills/37signals-way
.agents/skills/architecture-optimization
.agents/skills/blue-ocean-strategy
.agents/skills/clean-architecture
.agents/skills/clean-code
Gates applied: no_behavioural_pass.
c502026d022afull audit observations/trust-audit/skill/wondelai__contagious.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | c502026d022a | CAUTION | B | 89 | first audit |
Questions
What does the Contagious skill do?
Wondel.ai Agent Skills — Business, Marketing, UX & Coding Frameworks from Bestselling Books. 50 skills + 12 guided journeys for Claude Code, Codex, Cursor & other agentskills.io agents.
Is Contagious safe to install?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Contagious access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (c502026d022a), read on 2026-10-09. The repository is watched, and a new audit runs when it changes — this is the first audit.