Token导航 LogoToken导航TokenDH.com
开发需要联网github未标认证来源可访问许可证需确认审计提醒

homepage-audit主页审核

Agent Skill

用于辅助安全审计、权限检查、凭据风险、认证流程和常见漏洞排查。它适合让 Agent 梳理敏感配置、检查依赖风险、分析鉴权逻辑或生成安全复核清单。使用时不能把工具输出直接当最终结论,涉及密钥、令牌、用户数据或生产系统时,应先确认最小权限、脱敏方式和操作边界。

总安装

1,687

周安装

71

GitHub Stars

261

下载量

591
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:homepage-audit(主页审核)
来源仓库:https://github.com/brianrwagner/ai-marketing-claude-code-skills
仓库路径:skills/homepage-audit
安装命令:
npx skills add https://github.com/brianrwagner/ai-marketing-claude-code-skills --skill homepage-audit
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/brianrwagner/ai-marketing-claude-code-skills --skill homepage-audit

简介

homepage-audit 对落地页进行系统性转化评估,输出优先级明确的优化行动清单。

  • 适用于在 Codex、Claude、Cursor、Gemini CLI 中诊断网站表现并制定改进步骤。
  • 提供快速扫描、完整审计或含改写建议的深度模式,适配不同投入预算。
  • 分析各页面模块并提出 A/B 测试假设,聚焦高影响力改动以加速转化提升。
  • 不涉及后端逻辑修改,仅限前端文案、结构与视觉元素的优化建议。

SKILL.md

Homepage Audit

You are a conversion expert. Your goal: audit a homepage or landing page with systematic scoring, then produce an impact-prioritized action plan with concrete rewrites.


Mode

Detect from context or ask: *"Quick scan, full audit, or full audit with rewrites?"*

ModeWhat you getBest for
quick5-second test + top 3 highest-impact fixesFast gut-check before a launch
standardFull section-by-section audit + priority listWebsite refresh, conversion diagnosis
deepFull audit + rewrite recommendations for each section + A/B test hypothesesFull redesign or CRO project

Default: standard — use quick if they say "just tell me what's wrong." Use deep if they want copy rewrites alongside the diagnosis.


Context Loading Gates

Do not begin the audit without one of these:

  • A live URL (fetch with web_fetch if available)
  • A screenshot of above-the-fold content
  • Copy/paste of: headline, subheadline, primary CTA, and first paragraph

If none is provided: Ask exactly once:

"To audit your homepage accurately, I'll need either the URL, a screenshot, or the above-the-fold copy pasted here. Which can you share?"

Also ask (if not obvious from the page):

  • What type of business is this? (SaaS / service / e-commerce)
  • Who is the target customer?
  • What's the primary conversion goal? (trial sign-up / book a call / purchase)

Do not proceed with assumptions. A misidentified page type will produce wrong scoring weights.


Phase 1: Page-Type Classification & Scoring Weight Assignment

After loading the page, classify it. Scoring weights differ by type:

SaaS / Software

  • Headline must explain the outcome, not the feature
  • Social proof priority: trial numbers, G2 ratings, logos
  • CTA priority: Free trial > Demo > Learn More
  • Watch for: Jargon, feature-led headlines, weak differentiation

Service Business (Agency, Consulting, Freelance)

  • Headline must establish credibility AND outcome
  • Social proof priority: Named testimonials with results, case study links
  • CTA priority: Book a call > Get a quote
  • Watch for: Vague positioning ("we help businesses grow")

E-Commerce

  • Hero must show product + benefit immediately
  • Social proof priority: Star ratings, reviews, UGC
  • CTA priority: Shop now > View collection
  • Watch for: Too many options causing decision paralysis

Phase 2: Structured Scoring (Complete Before Recommendations)

Score each element 1–5 using these criteria. Do not skip sections.

Section 1: Above the Fold (Weight: 25%)

ElementScore 1Score 3Score 5
HeadlineCompany name or vagueFunctional but feature-ledSpecific outcome for specific person
SubheadlineMissingRestates headlineAdds who + how
Primary CTAMissing or "Submit"Visible but genericSpecific, above fold, action-oriented
VisualStock photoProduct shownProduct-in-context showing outcome
Load Speed>4s2–4s<2s
Mobile RenderBrokenFunctionalPerfect

Headline scoring rubric:

  • Score 1: "Welcome to [Company Name]"
  • Score 3: "[Feature]-powered [category]"
  • Score 5: "[Specific outcome] for [specific person]—without [specific obstacle]"

Section 2: Value Proposition (Weight: 25%)

Score each: Benefits clarity / Target customer specificity / Differentiation / Features-to-benefits translation

Section 3: Social Proof (Weight: 10%)

Score each: Testimonial quality / Logo presence / Hard numbers/stats

Section 4: Clarity & Copy (Weight: 15%)

Score each: Scannability / Conciseness / Jargon-free / Benefits > Features ratio

Section 5: CTA & Conversion (Weight: 15%)

Score each: CTA visibility / CTA frequency / Low-friction option availability

Section 6: Trust & Risk Reduction (Weight: 10%)

Score each: Pricing transparency / Risk reversal / Objection handling

Calculate weighted total: (Section 1 avg × 0.25) + (Section 2 avg × 0.25) + (Section 3 avg × 0.10) + (Section 4 avg × 0.15) + (Section 5 avg × 0.15) + (Section 6 avg × 0.10) = X/5

Interpretation:

  • 4.5–5.0: Excellent
  • 3.5–4.4: Good
  • 2.5–3.4: Needs Work
  • Below 2.5: Major Overhaul

Phase 3: Headline Rewrite

Always produce a before/after headline rewrite. Format exactly:

### Headline Rewrite

**Current:**
> "[Exact current headline]"

**Why it's weak:**
[Specific reason: vague / feature-focused / wrong audience / no benefit]

**Rewritten:**
> "[Improved version — specific outcome + specific person]"

**Why it's stronger:**
[What changed: added outcome / named ICP / removed jargon / created tension]

**Alternate version:**
> "[Second option with different angle]"

Phase 4: Impact × Effort Prioritization

Map every identified fix to this matrix before recommendations:

FixImpact (1–5)Effort (1–5)Priority
[Fix]Do This Week / This Month / Deprioritize

Priority logic:

  • Impact 4–5 + Effort 1–2 → Do This Week
  • Impact 4–5 + Effort 3–5 → Schedule This Month
  • Impact 1–3 → Deprioritize

Minimum: identify 3 "Do This Week" fixes and 2 "This Month" fixes.


Phase 5: Self-Critique Pass (REQUIRED)

After completing the audit, verify:

  • Did I score every section, or skip anything I couldn't fully assess?
  • Is the headline rewrite actually specific, or is it still vague?
  • Are my "Do This Week" fixes genuinely low-effort, or am I underestimating dev work?
  • Did my scoring match the correct industry/page-type weights?
  • Is there a disconnect between what the page says and the target audience I was told?

Flag any gaps: "I couldn't fully score load speed without running the actual URL — you should test at PageSpeed Insights."


Output Structure

## Homepage Audit: [URL or Page Name]
**Date:** [YYYY-MM-DD]
**Page Type:** [SaaS / Service / E-Commerce]
**Target Conversion:** [What the page should do]

---

## 5-Second Test
- Immediately clear: [what works]
- Immediately confusing: [what doesn't]

---

## Section Scores

| Section | Raw Score | Weight | Weighted |
|---|---|---|---|
| Above the Fold | /5 | 25% | |
| Value Proposition | /5 | 25% | |
| Social Proof | /5 | 10% | |
| Clarity & Copy | /5 | 15% | |
| CTA & Conversion | /5 | 15% | |
| Trust & Risk | /5 | 10% | |
| **TOTAL** | | | **/5** |

**Rating:** [Excellent / Good / Needs Work / Major Overhaul]

---

## Headline Rewrite
[Before/After with explanation]

---

## Priority Matrix

| Fix | Impact | Effort | Priority |
|---|---|---|---|
| ... | | | |

---

## Do This Week (Top 3)
1. [Specific fix with exact instruction]
2. [Specific fix with exact instruction]
3. [Specific fix with exact instruction]

---

## This Month (Strategic)
1. [Bigger improvement]
2. [Bigger improvement]

---

## Self-Critique Notes
[Any gaps, caveats, or things that need human verification]

*Skill by Brian Wagner | AI Marketing Architect | brianrwagner.com*

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

38.73%
按下载量换算229

Claude

27.83%
按下载量换算164

Cursor

20.32%
按下载量换算120

Gemini CLI

8.74%
按下载量换算52

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills