菜单
When the user wants to apply psychology, mental models, or behavioral science to marketing — 'cognitive bias,' 'persuasion,' 'why people buy,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' 'nudge' — or to understand how buyers think and decide.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
When the user wants to write, rewrite, or improve marketing copy for any page — homepage, landing, pricing, feature, about, or product pages; "headline help," "CTA copy," "value proposition," "tagline," "hero section," "make this more compelling," "conversion copy," or complete Figma-ready full-page copy (see Full-Page Mode below). For email copy, see email-sequence. For popups, see popup-cro. For editing existing copy, see copy-editing.
When the user wants to increase conversions on any marketing page — homepage, landing, pricing, feature, or blog; "CRO," "this page isn't converting," "low conversion rate," "bounce rate," "my landing page sucks" — or just shares a URL asking for feedback. For signup flows, see signup-flow-cro; post-signup activation, onboarding-cro; forms, form-cro; popups, popup-cro.
When the user wants to audit or diagnose SEO issues — "technical SEO," "why am I not ranking," "meta tags review," "my traffic dropped," "Google update hit me," "core web vitals," "crawl errors," "indexing issues," or even a vague "my SEO is bad." For pages at scale, see programmatic-seo. For structured data, see schema-markup. For AI search, see ai-seo.
Coder<->reviewer handoff loop (Claude<->Codex, roles swappable) with self-instrumented per-round cost tracking. Loops locally via HANDOFF.md until approved, then opens a PR with the full transcript.
Act as a Senior Accessibility Engineer to audit a page, component, or design against WCAG 2.2 AA. Produces a triaged finding list (critical/serious/moderate), focus-order map, contrast report, ARIA decision tree, and a screen-reader test plan. Use when shipping new UI, hardening an existing flow, or preparing for VPAT/accessibility conformance.
When the user wants to plan, design, or implement an A/B test or experiment — "split test," "variant copy," "multivariate test," "hypothesis," "statistical significance," "how long should I run this test," or comparing two versions. For tracking implementation, see analytics-tracking. For page-level conversion optimization, see page-cro.
| name | marketing-psychology |
| description | When the user wants to apply psychology, mental models, or behavioral science to marketing — 'cognitive bias,' 'persuasion,' 'why people buy,' 'anchoring,' 'social proof,' 'scarcity,' 'loss aversion,' 'framing,' 'nudge' — or to understand how buyers think and decide. |
| category | marketing |
| tier | on-demand |
Apply psychological principles and mental models to explain why people buy, influence behavior ethically, and improve marketing decisions.
Product context: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it first and tailor output to it; only ask for what it doesn't cover.
When helping users: identify which models apply to their situation, explain the psychology, give specific marketing applications, and suggest ethical implementation.
Break problems to basic truths and build up; ask "why" repeatedly (5 Whys) to find root causes instead of copying competitors. Don't assume you need content marketing because competitors do — ask what problem it solves and whether there's a better solution.
People "hire" products to get a job done; focus on the outcome, not features. A drill buyer wants a hole — frame your product around the job it accomplishes, not its specifications.
Stay within what you're good at; venture out only with proper learning or expert help. Don't chase every channel — double down where you have genuine expertise and competitive advantage.
Ask "What would guarantee failure?" and avoid it. List everything that would make your campaign fail — confusing messaging, wrong audience, slow landing page — then systematically prevent each.
The simplest explanation is usually correct. If conversions dropped, check the obvious first (broken form, page speed) before assuming complex attribution issues.
~80% of results come from 20% of efforts. Find the 20% of channels, customers, or content driving 80% of results; cut or reduce the rest.
Don't get stuck optimizing the wrong thing. Optimizing email subject lines (local) won't help if email isn't the right channel (global) — zoom out before zooming in.
Every system has one bottleneck limiting throughput; fix it before optimizing elsewhere. If your funnel converts well but traffic is low, more conversion optimization won't help — fix traffic first.
Every choice gives up alternatives. Time on a low-ROI channel is time not spent on high-ROI activities — always compare against alternatives.
Past a point, added investment yields smaller gains. The 10th blog post won't match the first's impact — know when to diversify rather than double down.
Consider the effects of effects. A flash sale boosts revenue (first order) but may train customers to wait for discounts (second order).
Models and data represent reality but aren't reality. Your persona and analytics dashboard are useful models; real customers are more complex — stay in touch with actual users.
Think in probabilities, not certainties. Don't bet everything on one campaign — spread risk and plan for scenarios where your primary strategy underperforms.
Combine extreme safety with small high-risk/high-reward bets; avoid the mediocre middle. Put 80% of budget into proven channels, 20% into experimental bets.
People attribute others' behavior to character, not circumstances ("they're not serious" vs. "the checkout was confusing"). When customers don't convert, examine your process before blaming them — the problem is usually situational.
Familiarity breeds liking. Consistent, repeated brand presence across channels builds preference, comfort, and trust.
People judge likelihood by how easily examples come to mind. Case studies and testimonials make success feel achievable — make positive outcomes easy to imagine.
People seek confirming information and ignore contradictions. Align messaging with what your audience already believes; fighting beliefs head-on rarely works.
The longer something has survived, the longer it's likely to continue. Proven principles (clear value props, social proof) outlast trendy tactics — don't abandon fundamentals for fads.
Desire is socially contagious — people want what others want. Waitlists, exclusivity, and social proof show that desirable people want your product.
Past investment doesn't justify continued investment. Kill underperforming campaigns regardless of past spend.
People value things more once they own them. Free trials, samples, and freemium let customers "own" the product, making them reluctant to give it up.
Effort invested in creating something raises its value. Let customers customize, configure, or build — their investment increases perceived value and commitment.
"Free" is psychologically different, not just cheap — the jump from $1 to $0 is bigger than $2 to $1. Free tiers, trials, and shipping have disproportionate appeal.
People strongly prefer immediate rewards over future ones. Emphasize "Start saving time today" over "You'll see ROI in 6 months."
Change feels risky and effortful. Reduce switching friction and make the transition feel safe: "Import your data in one click."
People accept pre-selected options. Pre-select the plan you want chosen; opt-out beats opt-in for subscriptions (ethically applied).
Too many options overwhelm and paralyze. Three pricing tiers beat seven; recommend a single "best for most" option.
Effort accelerates near a goal. Progress bars, completion percentages, and "almost there" messaging drive completion.
Experiences are judged by the peak and the end, not the average. Design memorable peaks (surprise upgrades, delightful moments) and strong endings (thank-you pages, follow-up emails).
Unfinished tasks occupy the mind more than completed ones. "You're 80% done," incomplete profiles, abandoned carts, and cliffhangers create pull to finish.
A small flaw makes the competent more likable. Admitting a weakness ("We're not the cheapest, but...") can increase trust and differentiation.
Experts can't imagine not knowing what they know. Your product seems obvious to you but confusing to newcomers — test copy with people unfamiliar with your space.
People treat fungible money differently by source or intended use. Frame costs in favorable accounts: "$3/day" feels different than "$90/month."
People avoid actions that might cause regret, even with positive expected outcomes. Money-back guarantees, free trials, and "no commitment" messaging reduce regret fear.
Popularity signals quality and safety. Show customer counts, testimonials, logos, reviews, and "trending" indicators — numbers create confidence.
Give first and people want to give back. Free content, tools, and generous free tiers create reciprocal obligation before you ask for anything.
People stay consistent with commitments. Get small commitments first (email signup, free trial) — one step makes the next more likely.
People defer to experts; credentials create trust. Feature expert endorsements, certifications, "featured in" logos, and thought leadership content.
People say yes to those they like and resemble. Use relatable spokespeople, founder stories, and community language: "Built by marketers for marketers."
Shared identity drives influence — "one of us" is powerful. Position your brand as part of the customer's tribe with insider language and shared values.
Limited availability increases perceived value. Limited-time offers, low-stock warnings, and exclusive access create urgency — only use when genuine.
Compliance with small requests leads to larger ones. Free trial → paid plan → annual plan → enterprise; each step builds on the last.
An unreasonably large request followed by retreat makes the real ask seem reasonable. Show enterprise pricing first — the starter plan then feels like a deal.
Losses feel roughly twice as painful as equivalent gains feel good. Frame what they'll lose by not acting: "Don't miss out" beats "You could gain."
The first number seen heavily influences later judgments. Show the higher price first (original price, competitor price, enterprise tier) to anchor expectations.
A third, inferior option makes another look better. A clearly worse-value decoy tier makes your preferred tier the obvious choice.
Presentation changes perception of identical facts. "90% success rate" vs. "10% failure rate" feel different — frame positively.
Things are judged by comparison. Show the "before" state clearly so the contrast with your "after" makes improvements vivid.
The left digit dominates perception: $99 feels much cheaper than $100. Use .99 or .95 endings for value-focused products.
Round numbers feel premium and process easily: $100 signals quality, $99 signals value. Use round prices for premium products ($500/month), charm prices for value products ($497/month).
Under $100, percentage discounts seem larger; over $100, absolute discounts do. $80 product: "20% off" beats "$16 off." $500 product: "$100 off" beats "20% off."
Prices are judged relative to options shown. Use three tiers with the middle as your target: the expensive tier makes it look reasonable, the cheap tier anchors.
The same price framed differently changes perception: "$1/day" feels cheaper than "$30/month"; "less than your morning coffee" reframes the expense.
Decision time grows with choice count and complexity; more options = more abandonment. One clear CTA beats three; fewer form fields beat more.
Attention → Interest → Desire → Action. Structure pages and campaigns to move through each stage — capture attention before building desire.
Prospects need roughly 7 touchpoints before converting. Build multi-touch campaigns: retargeting, email sequences, and consistent cross-channel presence compound.
Small changes in choice presentation significantly influence decisions. Default selections, strategic ordering, and friction reduction guide behavior without restricting choice.
Behavior = Motivation × Ability × Prompt — all three must be present. High motivation but hard to do fails; easy but unprompted fails. Design for all three.
Make desired behaviors Easy, Attractive, Social, Timely: reduce friction, make it appealing, show others doing it, ask at the right moment.
Behavior requires Capability, Opportunity, Motivation. Can they do it? Is the path clear? Do they want to? Address all three.
High starting friction prevents action even when the task is easy overall. Pre-fill forms, offer templates, show quick wins — make the first step trivially easy.
One metric that best captures the value you deliver creates alignment. Identify yours (active users, completed projects, revenue per customer) and align all efforts toward it.
Incentives can backfire and produce the opposite result. Test incentive structures — a referral bonus might attract low-quality referrals gaming the system.
Output becomes input; positive loops accelerate growth. Build and strengthen virtuous cycles: more users → more content → better SEO → more users.
Small, consistent gains accumulate exponentially; early gains matter most. Consistent content, SEO, and brand building compound — start early.
A product gains value as more people use it. Design features that improve with users: shared workspaces, integrations, marketplaces, communities.
Sustained effort builds self-maintaining momentum — hard to start, easy to maintain. Content → traffic → leads → customers → case studies → more content.
The time, money, effort, and data cost of changing to a competitor creates retention. Increase them ethically: integrations, data accumulation, workflow customization, team adoption.
Balance trying new things with optimizing what works. Don't abandon working channels for shiny new ones, but allocate some budget to experiments.
Past a threshold, growth becomes self-sustaining. Reach critical mass in one segment before expanding — depth before breadth.
Successes are visible; failures aren't. Study failed campaigns too — the viral hit you're copying had 99 failures you didn't see.
When facing a marketing challenge, consider:
| Challenge | Relevant Models |
|---|---|
| Low conversions | Hick's Law, Activation Energy, BJ Fogg, Friction |
| Price objections | Anchoring, Framing, Mental Accounting, Loss Aversion |
| Building trust | Authority, Social Proof, Reciprocity, Pratfall Effect |
| Increasing urgency | Scarcity, Loss Aversion, Zeigarnik Effect |
| Retention/churn | Endowment Effect, Switching Costs, Status-Quo Bias |
| Growth stalling | Theory of Constraints, Local vs Global Optima, Compounding |
| Decision paralysis | Paradox of Choice, Default Effect, Nudge Theory |
| Onboarding | Goal-Gradient, IKEA Effect, Commitment & Consistency |
