方法与优势
围绕同一个转化目标检查文案、信任证据和行动入口,帮助团队区分到底是说服力不足,还是操作流程太费劲。例如表单过早要求过多信息,就需要调整流程,而不只是把按钮文案改得更醒目。
围绕一个明确的购买或留资目标,检查电商页面转化率优化机会。提供页面、流量来源、当前表现和客户顾虑后,这项 Skill 会帮助助手检查卖点是否清楚、证据是否充分、行动入口是否明显,以及表单是否造成阻力,再整理成可以安排测试的修改方案。
访客没有继续行动,可能是没有看懂价值、缺少信任依据,也可能是下一步需要付出的成本太高。这项 Skill 会结合页面目标和访客来源检查这些问题,而不是对所有页面套用同一套修改建议。
当前来源同时覆盖页面与表单优化。团队可以用输出安排文案或设计调整,并明确测试需要观察什么指标。建议属于待验证的假设,Skill 不会直接修改线上页面,也不会替团队运行 A/B 测试平台。
围绕同一个转化目标检查文案、信任证据和行动入口,帮助团队区分到底是说服力不足,还是操作流程太费劲。例如表单过早要求过多信息,就需要调整流程,而不只是把按钮文案改得更醒目。
按页面类型使用相应的实验参考,把观察到的问题转成具体测试方案。结合已有基线数据和客户顾虑,决定先试哪项改动,以及出现什么结果才值得保留,避免一次改动太多后无法解释变化原因。
页面 URL 或截图、转化目标、流量来源、基线数据和客户顾虑。
使用能发现已安装 Skill 并读取辅助文件的兼容 Agent。外部服务或创作运行环境需另行配置。
建议是假设,不是已测得的提升;Skill 不会自行部署改动或运行 A/B 平台。
将指令复制给 Codex 或 Claude Code,让助手从原始仓库下载固定提交,安装完整文件并检查所需依赖。
请在我当前使用的应用中安装 cro,直接执行文件安装,不要只解释步骤。
原始仓库:https://github.com/coreyhaines31/marketingskills.git
固定提交:e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b
Skill 路径:skills/cro
1. 将这个版本下载到新目录。执行随包脚本前,先阅读 SKILL.md 和安装参考文件,不替换成其他作者的包。
2. Codex 安装到 ~/.agents/skills/cro,Claude Code 安装到 ~/.claude/skills/cro,只安装到我正在使用的应用。安装完整 Skill 文件夹,保留 scripts、references、assets 和随包声明;将仓库根目录许可证一并保留。先检查所有目标目录;已有安装时,说明差异后再决定是否替换。
3. 比较来源和安装目录的文件清单、文件哈希,检查文档要求的运行时、依赖及外部连接。只配置此 Skill 所需的本地依赖,适用时使用隔离环境;账号登录由我在本地完成,不把凭据贴进聊天。
4. 返回来源提交、实际安装路径、文件检查结果及尚未完成的运行环境配置,说明如何调用 cro。文件复制与应用发现分别检查,需要时新建会话。不要执行生产任务,也不要把安装完成说成已确认业务效果。以下为已核对版本未经改写的 SKILL.md。安装完整包才能保留引用的脚本、素材和指引。下方启动提示词为 EcomAgentTools 编写的示例。
---
name: cro
description: "When the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages, feature pages, lead capture forms, or contact forms. Also use when the user says 'CRO,' 'conversion rate optimization,' 'this page isn't converting,' 'improve conversions,' 'why isn't this page working,' 'my landing page sucks,' 'form abandonment,' 'nobody's converting,' 'low conversion rate,' or 'this page needs work.' Use this even if the user just shares a URL and asks for feedback. For signup/registration flows, see signup. For post-signup activation, see onboarding. For popups/modals, see popups."
metadata:
version: 2.0.3
---
# Conversion Rate Optimization (CRO)
You are a conversion rate optimization expert. Your goal is to analyze marketing pages and provide actionable recommendations to improve conversion rates.
## Reference Routing
Load the matching reference before recommending changes in these areas. Use the page analysis below for the initial diagnosis; references supply the detailed recommendations.
| User intent | Load | Covers |
|---|---|---|
| Lead, contact, demo, or quote form abandonment; fields, validation, mobile forms | [form.md](references/form.md) | Field decisions, form layouts, errors, trust, measurement, and form-specific experiments |
| Experiment ideas for a homepage, pricing, demo, landing, feature, or resource page | [experiments.md](references/experiments.md) | Hypotheses organized by page type and cross-page tests; use **ab-testing** for test design and measurement |
## Initial Assessment
**Check for product marketing context first:**
If `.agents/product-marketing.md` exists (or `.claude/product-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.
Before providing recommendations, identify:
1. **Page Type**: Homepage, landing page, pricing, feature, blog, about, other
2. **Primary Conversion Goal**: Sign up, request demo, purchase, subscribe, download, contact sales
3. **Traffic Context**: Where are visitors coming from? (organic, paid, email, social)
---
## CRO Analysis Framework
Analyze the page across these dimensions, in order of impact:
### 1. Value Proposition Clarity (Highest Impact)
**Check for:**
- Can a visitor understand what this is and why they should care within 5 seconds?
- Is the primary benefit clear, specific, and differentiated?
- Is it written in the customer's language (not company jargon)?
**Common issues:**
- Feature-focused instead of benefit-focused
- Too vague or too clever (sacrificing clarity)
- Trying to say everything instead of the most important thing
### 2. Headline Effectiveness
**Evaluate:**
- Does it communicate the core value proposition?
- Is it specific enough to be meaningful?
- Does it match the traffic source's messaging?
**Strong headline patterns:**
- Outcome-focused: "Get [desired outcome] without [pain point]"
- Specificity: Include numbers, timeframes, or concrete details
- Social proof: "Join 10,000+ teams who..."
### 3. CTA Placement, Copy, and Hierarchy
**Primary CTA assessment:**
- Is there one clear primary action?
- Is it visible without scrolling?
- Does the button copy communicate value, not just action?
- Weak: "Submit," "Sign Up," "Learn More"
- Strong: "Start Free Trial," "Get My Report," "See Pricing"
**CTA hierarchy:**
- Is there a logical primary vs. secondary CTA structure?
- Are CTAs repeated at key decision points?
### 4. Visual Hierarchy and Scannability
**Check:**
- Can someone scanning get the main message?
- Are the most important elements visually prominent?
- Is there enough white space?
- Do images support or distract from the message?
### 5. Trust Signals and Social Proof
**Types to look for:**
- Customer logos (especially recognizable ones)
- Testimonials (specific, attributed, with photos)
- Case study snippets with real numbers
- Review scores and counts
- Security badges (where relevant)
**Placement:** Near CTAs and after benefit claims
### 6. Objection Handling
**Common objections to address:**
- Price/value concerns
- "Will this work for my situation?"
- Implementation difficulty
- "What if it doesn't work?"
**Address through:** FAQ sections, guarantees, comparison content, process transparency
### 7. Friction Points
**Look for:**
- Too many form fields
- Unclear next steps
- Confusing navigation
- Required information that shouldn't be required
- Mobile experience issues
- Long load times
---
## Output Format
Structure your recommendations as:
### Quick Wins (Implement Now)
Easy changes with likely immediate impact.
### High-Impact Changes (Prioritize)
Bigger changes that require more effort but will significantly improve conversions.
### Test Ideas
Hypotheses worth A/B testing rather than assuming.
### Copy Alternatives
For key elements (headlines, CTAs), provide 2-3 alternatives with rationale.
---
## Page-Specific Frameworks
### Homepage CRO
- Clear positioning for cold visitors
- Quick path to most common conversion
- Handle both "ready to buy" and "still researching"
### Landing Page CRO
- Message match with traffic source
- Single CTA (remove navigation if possible)
- Complete argument on one page
### Pricing Page CRO
- Clear plan comparison
- Recommended plan indication
- Address "which plan is right for me?" anxiety
### Feature Page CRO
- Connect feature to benefit
- Use cases and examples
- Clear path to try/buy
### Blog Post CRO
- Contextual CTAs matching content topic
- Inline CTAs at natural stopping points
---
## Experiment Ideas
When recommending experiments, consider tests for:
- Hero section (headline, visual, CTA)
- Trust signals and social proof placement
- Pricing presentation
- Form optimization
- Navigation and UX
**For comprehensive experiment ideas by page type**: See [references/experiments.md](references/experiments.md)
---
## Task-Specific Questions
1. What's your current conversion rate and goal?
2. Where is traffic coming from?
3. What does your signup/purchase flow look like after this page?
4. Do you have user research, heatmaps, or session recordings?
5. What have you already tried?
---
## Related Skills
- **signup**: If the issue is in the signup process itself
- **popups**: If considering popups as part of the strategy
- **copywriting**: If the page needs a complete copy rewrite
- **ab-testing**: To properly test recommended changes
---
## Form Optimization
When enrichment controls the next step after a lead form, use the [revops inbound-routing playbook](https://github.com/coreyhaines31/marketingskills/blob/main/skills/revops/references/inbound-routing.md): preserve valid submissions, bound the lookup wait, and provide a useful fallback when qualification is unknown.
For detailed form CRO guidance — including field optimization, multi-step forms, error handling, and form-specific experiments — see [references/form.md](references/form.md).
以下是主要功能的用例提示词,可以直接复制使用。
审查落地页价值说明与 CTA 适用于:审查落地页价值说明与 CTA。请准备:页面 URL 或截图、转化目标、流量来源、基线数据和客户顾虑。
请使用已安装的 cro Skill。任务:审查落地页价值说明与 CTA。输入:[INPUT]。限制:[CONSTRAINTS]。先检查缺失信息,再输出可审查的结果、依据、假设和下一步。建议是假设,不是已测得的提升;Skill 不会自行部署改动或运行 A/B 平台。[INPUT][CONSTRAINTS]减少线索或联系表单的填写阻力 适用于:减少线索或联系表单的填写阻力。请准备:页面 URL 或截图、转化目标、流量来源、基线数据和客户顾虑。
请使用已安装的 cro Skill。任务:减少线索或联系表单的填写阻力。输入:[INPUT]。限制:[CONSTRAINTS]。先检查缺失信息,再输出可审查的结果、依据、假设和下一步。建议是假设,不是已测得的提升;Skill 不会自行部署改动或运行 A/B 平台。[INPUT][CONSTRAINTS]准备附依据的页面实验优先级 适用于:准备附依据的页面实验优先级。请准备:页面 URL 或截图、转化目标、流量来源、基线数据和客户顾虑。
请使用已安装的 cro Skill。任务:准备附依据的页面实验优先级。输入:[INPUT]。限制:[CONSTRAINTS]。先检查缺失信息,再输出可审查的结果、依据、假设和下一步。建议是假设,不是已测得的提升;Skill 不会自行部署改动或运行 A/B 平台。[INPUT][CONSTRAINTS]输入付费社交落地页线框和一个有 8 个必填字段的咨询表单,购买率基线 2.5%、移动端占 70%。目标是让顾客更快看懂商品并完成必要操作。
案例输入资料:business-inputs.zip
Use the page-cro Skill.
Review our paid-social landing-page and inquiry-form brief. Identify the biggest obstacles to understanding the offer and completing a purchase or inquiry. Provide revised headline, CTA, shipping explanation, form fields, validation messages and success state. Separate necessary fixes from experiments and explain what to measure after implementation.
The attached business materials are:
- inputs/brief.md
- inputs/merchant.json
Deliver a complete result.md report that the operations team can read, plus any finished files needed for this task. Keep supporting calculations and evidence with the deliverables. Write the report in English; use the requested target language for customer-facing copy. The business datasets are fictional examples unless the brief explicitly names a live public website.下方直接展示本次 Prompt 产生的主要文件,保留实际输出语言。
The brief describes a paid-social landing page for a $24 mug. Its headline hides the product, the first CTA sends shoppers to a form, and the information needed to judge fit sits in the footer. Correct those three issues first. This assessment uses the supplied text wireframe; it does not claim a browser inspection or observed customer interviews.
| Measure | Prior | Current |
|---|---|---|
| Orders / sessions | 100 / 4,000 | 120 / 4,800 |
| Order-to-session ratio | 2.50% | 2.50% |
Sales and traffic grew together; purchase conversion did not improve. The 3% goal is a target, not a forecast.
| Device | Page sessions | Form starts | Accepted submissions | Start rate | Completion per start |
|---|---|---|---|---|---|
| Mobile | 3,360 | 168 | 42 | 5.00% | 25.00% |
| Desktop | 1,440 | 72 | 36 | 5.00% | 50.00% |
| Total | 4,800 | 240 | 78 | 5.00% | 32.50% |
Mobile has more lost starts (126) than desktop (36). This prioritizes mobile investigation but does not prove which field caused abandonment. Page-to-accepted-submission rates are 1.25% mobile, 2.50% desktop and 1.625% overall.
Headline: A 500 ml stainless steel mug for your desk
Supporting copy: HarborMug holds your everyday cup in a blue insulated stainless steel mug. Check its 9 × 9 × 19 cm dimensions and care requirements before choosing it.
Price: $24 USD + $5 US shipping for one mug. $29 before applicable tax.
Primary CTA: Add to cart
Care line: Hand-wash only. Not microwave safe.
Delivery: Dispatch in 2 business days, followed by 3–5 business days in transit. US delivery only. Shipping is free on orders of $50 or more.
Returns: Unused returns within 30 days of delivery; final refunds require merchant approval.
Keep a quieter “Ask about this mug” link below the decision information. Buying remains possible without submitting a question or registering. Use a genuine product image when available; the supplied abstract illustration does not verify the product's appearance.
Alternative headline: “Meet HarborMug: 500 ml, $24.” It matches the ad's factual offer. A second alternative, “Check the fit before your next cup,” suits the dimensions section but is less clear as a cold-traffic headline. Do not replace facts with an untested superiority claim.
Title: Have a question before ordering?
Description: “Tell us what you need to know about HarborMug. Our support team will reply to the email address you provide.” No reply-time SLA has been approved.
Order: Email (required, type=email, autocomplete=email); Your question (required textarea); Name (optional, autocomplete=name). The message remains required because support needs the actual question. Remove phone, company, role and order number from this pre-purchase flow. Keep persistent visible labels and a single column; use a comfortably tappable button of at least 44 px height.
CTA: Send my question. Pending: Sending…. Disable repeated submissions while a request is pending and use a request identifier to avoid duplicate tickets.
| State | Message and behaviour |
|---|---|
| Missing email | “Enter the email address where we should reply.” Focus Email |
| Malformed email | “Check your email address, for example shopper@example.com.” Keep entered values |
| Empty question | “Tell us what you would like to know about the mug.” Focus question |
| Server/network failure | “Your question was not sent. Your text is still here; please try again.” Preserve fields |
| Server accepted | “Your question has been sent to our support team. We will reply by email.” Show Continue shopping |
Show success only after server acceptance. Do not auto-subscribe to marketing. Route ordinary questions to the support owner; policy exceptions go to the escalation owner. Do not add an unapproved privacy or response-time promise.
The merchandiser owns factual headline, cost, care and shipping changes. The developer owns the direct purchase CTA, persistent labels, field reduction, accessible errors and reliable submission state. The analyst verifies one start and one accepted submission per session and separates attempt, failure and acceptance events without recording message text or email in analytics.
After those fixes, test a dimension image beside the purchase decision against the existing factual image. Hypothesis: shoppers can judge fit sooner. Another test can compare the two factual headlines. Define one primary purchase measure with a consistent attribution window before enrollment; track add-to-cart, accepted questions, technical errors and returns as secondary or guardrail measures. Do not bundle unrelated tests or claim field-count benchmarks predict this store's uplift.
Review mobile versus desktop completion, error category and time to accepted submission. Conduct five task-based sessions asking shoppers to find total cost, care restrictions and how to ask a question. Use observed failures to revise the page; five sessions diagnose usability and do not estimate a population conversion lift.
案例中的商家经营资料为模拟数据;涉及网站检查时,报告中的页面观察来自所列公开网址。
建议是假设,不是已测得的提升;Skill 不会自行部署改动或运行 A/B 平台。
核对源码及随包文件:GitHub e85f3cbc2e4a。 当前包标识为 cro。本次为静态审查,不代表已完成安装运行或业务效果测试。
使用获授权输入,不把密钥贴入提示词。采用前检查面向客户的声明、计算、代码改动及任何拟议的外部操作。
检查营销页与表单的转化阻力,并提出可测试改动。当前 cro Skill 合并了原 page-cro 与 form-cro,并提供按页面类型分类的实验参考。
按实际 Agent 选择方式,安装完整包,不要只复制页面中的 SKILL.md。 页面 URL 或截图、转化目标、流量来源、基线数据和客户顾虑。 开启新 Agent 会话,明确要求使用 cro。先用小型样本尝试下方一个场景,并检查输出。
审查落地页价值说明与 CTA;减少线索或联系表单的填写阻力;准备附依据的页面实验优先级
建议是假设,不是已测得的提升;Skill 不会自行部署改动或运行 A/B 平台。
核对源码及随包文件:GitHub e85f3cbc2e4a。 当前包标识为 cro。本次为静态审查,不代表已完成安装运行或业务效果测试。
核对源码及随包文件:GitHub e85f3cbc2e4a。 当前包标识为 cro。本次为静态审查,不代表已完成安装运行或业务效果测试。
暂无评论。