Token导航 LogoToken导航

Agent Skill · 研究检索

marketing-skills-collection(营销技巧集合)

marketing-skills-collection 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

marketing-skills-collection 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,674 个 Skill 里排第 724。

总安装 187,704周安装 7,938GitHub Stars 88下载 65,728核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

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:marketing-skills-collection(营销技巧集合)
来源仓库:https://github.com/supercent-io/skills-template
仓库路径:skills/marketing-skills-collection
安装命令:
npx skills add https://github.com/supercent-io/skills-template --skill marketing-skills-collection
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/supercent-io/skills-template --skill marketing-skills-collection

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

使用 23 项专门的子技能生成跨 CRO、文案、SEO、分析和增长的营销成果。

涵盖 5 个营销领域和 23 项子技能:CRO(登陆页面、注册流程、表单、付费专区)、文案写作(广告、电子邮件序列、社交内容)、SEO(审核、程序化页面、架构标记)、广告/分析(跟踪、付费广告、A/B 测试)和策略/增长(启动、定价、保留、流失、实验、推荐计划、内容策略) 结构化工作流程:定义目标和约束,选择适当的子技能,使用产品上下文和受众详细信息构建提示,生成并验证输出,然后实施跟踪和测量 每个可交付成果包括 KPI 一致性、目标受众契合度、品牌声音一致性以及具有 A/B 测试建议和成功指标的可操作输出 专为与跨渠道(登陆页面、电子邮件、社交、SEO、付费广告)单一营销 KPI 相关的可重复、高质量资产生成而设计

来源仓库内路径:skills/marketing-skills-collection

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/supercent-io/skills-template --skill marketing…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

marketing-skills-collection 怎么安装?

在终端执行 npx skills add https://github.com/supercent-io/skills-template --skill marketing-skills-co…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

marketing-skills-collection 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

marketing-skills-collection 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

marketing-skills-collection 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

marketing-skills-collection 用的人多吗?

公开数据是累计安装 187,704 次,近一周安装 7,938 次,下载 65,728 次,GitHub 88 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

marketing-skills-collection 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
marketing-skills-collection

营销技巧集合 · 本页

187,70488只读MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Marketing Skills Collection

A collection of 23 sub-skills for marketing deliverables. Generates repeatable, high-quality outputs across CRO, copywriting, SEO, analytics, and growth domains.

When to use this skill

  • Marketing deliverables needed: CRO, copy, SEO, analytics, and growth outputs
  • Repeatable, high-quality outputs: Asset generation aligned to a single KPI
  • Business goal → skill mapping: Convert objectives into specific marketing sub-skills

23 Sub-Skills Overview

CRO (Conversion Rate Optimization)

Sub-SkillDescription
page-croLanding page conversion rate optimization
signup-flowSignup flow optimization
onboardingOnboarding experience improvement
form-optimizationForm optimization (fields, UX)
paywallPaywall/pricing page optimization

Copywriting

Sub-SkillDescription
copywritingAd/marketing copy creation
copy-editingExisting copy improvement
email-sequenceEmail sequence design
social-contentSocial media content

SEO

Sub-SkillDescription
seo-auditSEO audit and improvement recommendations
programmatic-seoProgrammatic SEO pages
comparison-pageComparison page creation
schema-markupStructured data markup

Ads & Analytics

Sub-SkillDescription
analytics-trackingAnalytics tracking setup
paid-adsPaid advertising strategy/copy
ab-testA/B test design

Strategy & Growth

Sub-SkillDescription
launch-strategyProduct launch strategy
pricing-strategyPricing strategy
retentionRetention improvement strategy
churn-analysisChurn analysis
growth-experimentsGrowth experiment design
referral-programReferral program design
content-strategyContent strategy development

Instructions

Step 1: Define Objective and Constraints

marketing_brief:
  objective: [single KPI - conversion rate, CTR, activation]
  target_audience:
    segment: [customer segment]
    pain_points: [key pain points]
    terminology: [terms they use]
  channel: [LP, email, social, SEO, ads]
  format: [format]
  offer:
    value_prop: [value proposition]
    positioning: [positioning]
    proof_points: [proof points]

Step 2: Select the Sub-Skill

Select the sub-skill that fits the situation:

# For CRO needs
→ page-cro, signup-flow, onboarding, form-optimization, paywall

# For copy needs
→ copywriting, copy-editing, email-sequence, social-content

# For SEO needs
→ seo-audit, programmatic-seo, comparison-page, schema-markup

# For ads/analytics needs
→ analytics-tracking, paid-ads, ab-test

# For strategy/growth needs
→ launch-strategy, pricing-strategy, retention, churn-analysis, growth-experiments

Step 3: Build the Prompt

Create a structured prompt:

## Marketing Asset Request

### Product Context
- **Product**: [product name]
- **Category**: [category]
- **Stage**: [stage - early, growth, mature]

### Audience
- **Segment**: [target segment]
- **Pain Points**: [1-3 pain points]
- **Current State**: [current solution in use]

### Offer
- **Value Prop**: [core value proposition]
- **Differentiator**: [differentiating point]
- **Proof**: [trust factors - numbers, clients, awards]

### Constraints
- **Tone**: [tone - professional, casual, bold]
- **Brand Voice**: [brand voice guide]
- **Do NOT**: [things to avoid]

### Output Format
- [desired format - table, checklist, bullets]

Step 4: Generate and Validate

# Generate
claude task "Generate marketing asset using sub-skill name"

# Validation checklist
- [ ] KPI alignment
- [ ] Target audience fit
- [ ] Brand voice consistency
- [ ] Actionable output

Step 5: Handoff + Measurement

## Implementation Checklist
- [ ] Asset publishing
- [ ] Tracking event setup
- [ ] Success threshold definition

## Tracking Events
| Event | Description | Success Threshold |
|-------|-------------|-------------------|
| page_view | Page view | baseline |
| cta_click | CTA click | +20% vs control |
| signup_complete | Signup complete | +15% vs control |

## A/B Test Proposals
1. [Hypothesis 1]: [variant] vs [control]
2. [Hypothesis 2]: [variant] vs [control]

Examples

Example 1: Landing Page CRO

Prompt:

Optimize the landing page for higher signup conversion.
Audience: indie founders building side projects.
Offer: AI co-pilot for product launches.
Output: prioritized CRO changes + A/B tests.

Expected output:

  • CRO checklist prioritized by impact/effort
  • 3 A/B test hypotheses with expected lift
  • Hero + CTA copy suggestions (3 variants each)

Example 2: Email Sequence

Prompt:

Create a 5-email welcome sequence for a B2B SaaS.
Audience: ops managers at 50-500 employee companies.
Goal: drive first workflow setup within 7 days.

Expected output:

## Welcome Sequence

### Email 1: Welcome (Day 0)
- **Subject**: Welcome to [Product] - Let's get started
- **Goal**: Account confirmation + quick win
- **CTA**: Complete profile

### Email 2: Value Demo (Day 1)
- **Subject**: See what [Product] can do in 2 minutes
- **Goal**: Feature awareness
- **CTA**: Watch demo video

### Email 3: First Workflow (Day 3)
- **Subject**: Create your first workflow (step-by-step)
- **Goal**: Activation milestone
- **CTA**: Create workflow

### Email 4: Use Case (Day 5)
- **Subject**: How [Customer] saved 10 hours/week
- **Goal**: Social proof + inspiration
- **CTA**: Try this template

### Email 5: Check-in (Day 7)
- **Subject**: Need help getting started?
- **Goal**: Rescue non-activated users
- **CTA**: Book a call / Reply for help

## Metrics
| Email | Open Rate Target | CTR Target |
|-------|------------------|------------|
| Email 1 | 60%+ | 30%+ |
| Email 2 | 45%+ | 15%+ |
| Email 3 | 40%+ | 20%+ |
| Email 4 | 35%+ | 12%+ |
| Email 5 | 40%+ | 15%+ |

Example 3: Programmatic SEO

Prompt:

Create a programmatic SEO template for comparison pages.
Target: "[Tool A] vs [Tool B]" searches.
Include: H1, meta description, comparison table, CTA.

Expected output:

  • Page template with placeholders
  • Schema markup (JSON-LD)
  • Internal linking strategy
  • Content guidelines per section

Best practices

  1. One KPI per deliverable: Avoid mixed objectives
  2. Audience specificity: Use segment-specific needs and terminology
  3. Instrument measurement: Set up tracking before launch
  4. Iterate with data: Treat outputs as hypotheses

Common pitfalls

  • Mixing multiple objectives: Multiple goals in a single asset
  • Missing audience context: Unclear who the asset is for
  • No tracking/validation plan: Unable to measure effectiveness

Troubleshooting

Issue: Output is generic

Cause: Vague product/audience information Solution: Provide positioning, competitors, and proof points

Issue: Output conflicts with brand voice

Cause: No tone/voice constraints provided Solution: Provide brand do/don't list and sample copy

Issue: Can't measure impact

Cause: Tracking events not defined Solution: Define events and success thresholds in advance


Output format

## Marketing Asset Report

### Brief Summary
- **Sub-Skill Used**: [sub-skill]
- **Objective**: [KPI]
- **Audience**: [segment]

### Deliverable
[generated asset]

### Implementation Checklist
- [ ] Asset ready
- [ ] Tracking configured
- [ ] Success criteria defined

### A/B Test Plan
| Test | Hypothesis | Metric | Expected Lift |
|------|------------|--------|---------------|
| Test A | [hypothesis] | [metric] | [%] |

Multi-Agent Workflow

Validation & Retrospectives

  • Round 1 (Orchestrator): Coverage of 23 sub-skills across 5 categories
  • Round 2 (Analyst): KPI alignment, prompt structure review
  • Round 3 (Executor): Output format, actionability check

Agent Roles

AgentRole
ClaudeBrief composition, asset generation
GeminiCompetitor research, trend analysis
CodexTracking code generation, automation

Metadata

Version

  • Current Version: 1.0.0
  • Last Updated: 2026-01-21
  • Compatible Platforms: Claude, ChatGPT, Gemini, Codex

Related Skills

Tags

#marketing #cro #copywriting #seo #analytics #growth #automation

平台分布

Claude Code

28.54%
按下载量换算18,759

OpenCode

22.68%
按下载量换算14,907

Antigravity

17.14%
按下载量换算11,266

Gemini CLI

10.84%
按下载量换算7,125

Codex

8%
按下载量换算5,258

Cursor

3.37%
按下载量换算2,215

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。

继续浏览同类 Skills