Atlas / Skills / wondelai / Influence Psychology

Influence PsychologyCAUTION

skills/wondelai/influence-psychology

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.

Verdict
CAUTION
Grade
B
Trust score
89 /100
Version
1.4.1
Hosts
—
License
MIT
Stars
2,377
01

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.

Read from source at commit c502026d022aOBSERVED · 2026-10-10
02

What 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: influence-psychology
description: 'Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment and consistency", "shared identity", "in-group", "make my copy more persuasive", "increase trust", or "get more people to say yes". Also trigger when designing testimonial sections, crafting urgency messaging, or improving trust signals on landing pages. Covers the principles, when each applies, and ethical limits. For deal negotiation tactics, see negotiation. For viral word-of-mouth, see contagious.'
license: MIT
metadata:
  author: wondelai
  version: "1.4.1"
---

# Influence Psychology Framework

Apply six decades of persuasion science — Cialdini's research into why people say "yes" — to product, copy, and sales, ethically.

## Core Principle

**People don't make decisions rationally — they use mental shortcuts (heuristics) that can be triggered to influence behavior.** These shortcuts evolved because they're usually reliable, but they can also be exploited. Understanding them lets you design products, messaging, and experiences that align with how people actually decide.

## Scoring

**Goal: 10/10.** When reviewing or creating persuasive elements (features, copy, flows, campaigns), run the Quick Diagnostic, then score against the bands below and apply the ethics gate. Always report the current score and the specific change needed to reach 10/10.

- **9-10** — Multiple principles deliberately layered; every claim truthful; users can reverse the decision; passes the transparency test (still works if the user knows the strategy); safe for vulnerable users.
- **7-8** — Principles deliberately layered and honest, but one gap (e.g. weak reversibility, or a single principle where layering was possible).
- **5-6** — One principle present but generic, or leverage left on the table.
- **<=3** — No principle deliberately designed (relying on luck), OR any tactic is deceptive/coercive. Any fabricated proof, fake scarcity, or hidden-cost dark pattern caps the score at 3 regardless of other strengths.

## The Seven Principles of Influence

### 1. Reciprocity

**Core concept:** People feel obligated to give back to those who have given to them first.

**Why it works:** Humans are wired to avoid being indebted — the obligation to repay can overpower personal preference, and the return favor often exceeds the original gift.

**Key insights:**
- The gift must come first (before the request)
- Unexpected, personalized gifts beat expected, generic ones
- Even small gifts create obligation

**Product applications:**

| Context | Reciprocity Trigger | Example |
|---------|---------------------|---------|
| **Free trials** | Full access first, then ask to pay | Spotify Premium trial → subscription |
| **Content marketing** | Value upfront (guides, tools) | HubSpot free CRM → paid tools |
| **Referral programs** | Reward both referrer and referee | Dropbox: both get extra storage |

**Copy patterns:**
- "Here's a gift for you..." (before asking)
- "As a thank you for signing up..."
- "We noticed you needed help with X, so we..."

See [references/reciprocity.md](references/reciprocity.md) when building free trials, lead magnets, or referral rewards — gift tiers, email templates, day-by-day reciprocity-stacking, and A/B variables.

### 2. Commitment & Consistency

**Core concept:** People want to be consistent with their past statements, beliefs, and actions.

**Why it works:** Inconsistency is psychologically uncomfortable; once we take a stand, personal and interpersonal pressure pushes us to behave consistently with it.

**Key insights:**
- Small initial commitments lead to larger ones (foot-in-the-door)
- Public > private; written > verbal; active (user-generated) > passive
- Self-perception: we infer our attitudes from our behavior

**Product applications:**

| Context | Commitment Trigger | Example |
|---------|-------------------|---------|
| **Onboarding** | Easy yes, then larger asks | Duolingo: "Can you commit to 5 min/day?" |
| **Goal setting** | User publicly states a goal | Strava: "I want to run 50km this month" |
| **Habit formation** | Track streaks publicly | Snapchat streaks, GitHub contributions |

**Copy patterns:**
- "What's your biggest challenge with X?" (commitment to a problem)
- "How much would you like to save per month?" (numerical commitment)
- "You said you wanted to achieve X. Let's start with..."

**Onboarding sequence:** micro-commitment ("What brings you here?") → small action (click, choice) → public/written commitment (goal) → reinforce ("Based on what you told us...").

**Ethical boundary:** Make every commitment freely chosen and easily reversible — no trick opt-ins or locked-in defaults the user can't undo.

See [references/commitment-consistency.md](references/commitment-consistency.md) when designing onboarding or goal-setting flows — foot-in-the-door sequences and public-commitment tactics.

### 3. Social Proof

**Core concept:** People determine what's correct by finding out what others think is correct.

**Why it works:** When uncertain, we use others' behavior as a guide — "if everyone's doing it, it must be right."

**Key insights:**
- Most powerful when observers are uncertain; similar others = stronger proof
- Negative social proof backfires ("9 out of 10 don't...")
- Specific numbers beat vague claims ("2,347 users" > "thousands")

**Types of social proof:**

| Type | Definition | Example |
|------|------------|---------|
| **Wisdom of crowds** | Many people use/buy | "Join 50,000+ marketers" |
| **Wisdom of friends** | People you know use it | "3 of your friends use Notion" |
| **Expert** | Authorities endorse | "Recommended by Y Combinator" |
| **Celebrity** | Famous people use it | "Used by Elon Musk"
03

Trust audit

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryWARN
L1Static analysis of the codeNA
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found

Findings (9)

MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/37signals-way
.agents/skills/37signals-way
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/architecture-optimization
.agents/skills/architecture-optimization
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/blue-ocean-strategy
.agents/skills/blue-ocean-strategy
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/clean-architecture
.agents/skills/clean-architecture
Why it matters. link not followed
MEDIUMInventory / provenance · inv.symlink · CWE-1104
.agents/skills/clean-code
.agents/skills/clean-code
Why it matters. link not followed
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
SKILL.md:44
| **Free trials** | Full access first, then ask to pay | Spotify Premium trial → subscription |
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
references/liking.md:251
| "You've reached your free limit" | "Wow, you've been busy! You've used all your free credits this month. Upgrade for unlimited access." |
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
references/reciprocity.md:48
1. Offer full access with zero friction (no credit card)
INFOPrompt injection · prompt.authority_framing · CWE-94, CWE-1427
references/reciprocity.md:258
| Day 0 | Full access, no credit card required | Initial goodwill |

Gates applied: no_behavioural_pass.

Audited 2026-10-10 · audit v0.4.1 · source sha c502026d022afull audit observations/trust-audit/skill/wondelai__influence-psychology.json · Report an issue / request a re-scan
04

Audit history

Every audit this skill has had.

DateSourceVerdictGradeScoreChange
2026-10-10c502026d022aCAUTIONB89first audit
05

Questions

What does the Influence Psychology 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 Influence Psychology safe to install?

With care. The audit graded it B (89/100) and found 9 things worth knowing before you trust this skill, listed below with the exact line each was found on.

What can Influence Psychology 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 2026-10-10. The repository is watched, and a new audit runs when it changes — this is the first audit.

Advertisement