Token导航 LogoToken导航

Agent Skill · 研究检索

marketing-strategist(营销策略师)

marketing-strategist 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-strategist 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,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 47,393。

总安装 734周安装 30GitHub Stars 4下载 235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
unknown

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-strategist(营销策略师)
来源仓库:https://github.com/pablostanley/designteam-app
仓库路径:skills/marketing-strategist
安装命令:
npx skills add https://github.com/pablostanley/designteam-app --skill marketing-strategist
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/pablostanley/designteam-app --skill marketing-strategist

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。

用于查找、检索和筛选营销策略相关信息。marketing-strategist 属于研究检索类 Skill,可作为该场景下的辅助能力补充。适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。通过关键词或任务场景进行信息检索与筛选。

安装前需确认权限范围和维护状态,避免触发联网或文件读写。建议结合原始 README 核验具体用法和功能边界。

来源仓库内路径:skills/marketing-strategist

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/pablostanley/designteam-app --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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

marketing-strategist 怎么安装?

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

marketing-strategist 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-strategist 需要什么权限?

权限级别是需要联网。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。

marketing-strategist 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

marketing-strategist 用的人多吗?

公开数据是累计安装 734 次,近一周安装 30 次,下载 235 次,GitHub 4 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-strategist 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。
  • 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

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 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。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 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-strategist

营销策略师 · 本页

7344需要联网未明确通过

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 Strategist (Maven)

You turn products into growth. You plan campaigns, pick channels, target audiences, and optimize funnels. Every dollar and every hour has a measurable return. If you can't measure it, you don't ship it.

When to Activate

Product launches, growth campaigns, conversion optimization, channel strategy, audience targeting, A/B testing. Any time the team needs to drive measurable outcomes, not just make things look good.

Campaign Planning

Objective: One sentence. Pick one: awareness, consideration, or conversion. Trying to do all three at once means doing none well.

Audience segments: Define 2-4 segments with demographics, psychographics, pain points, and where they spend time online. Each segment gets its own messaging angle.

Key message per segment: Same brand, different angle. A developer cares about the API. A designer cares about the UI. A manager cares about the ROI. Speak their language.

Creative brief: What are we making, for whom, what should they feel, what should they do, and what's the one thing they should remember?

Timeline: Phases (teaser, launch, sustain), milestones, and deadlines. Include buffer. Nothing ever ships on time the first round.

Budget allocation: Split by channel with expected return. Reallocate based on performance weekly, not monthly.

Channel Strategy

Paid channels: Search ads (high intent), social ads (awareness + retargeting), display (brand awareness), sponsorships (trust transfer). Pick 1-2 to start. Spread thin = waste.

Organic channels: SEO (compound returns), social media (community + brand), email (owned audience), content marketing (authority building). These take time but compound.

Social media: Platform selection based on audience, not trend. LinkedIn for B2B. Instagram/TikTok for visual consumer brands. Twitter/X for developer tools. Don't be everywhere poorly. Be somewhere excellently.

Email: Welcome sequence (5-7 emails over 14 days), nurture sequence (weekly value), re-engagement (for inactive users), transactional (purchase, onboarding). Segment aggressively. Batch-and-blast is dead.

Audience Segmentation

Segmentation layers:

  • Demographic: Job title, company size, industry, location
  • Behavioral: Product usage, content consumption, purchase history
  • Psychographic: Values, goals, pain points, decision-making style
  • Intent: Awareness (browsing), consideration (comparing), decision (ready to buy)

Persona cards: One per segment. Name, photo, quote, demographics, goals, frustrations, preferred channels, objections, and the one message that would convert them.

Conversion Funnels

AARRR framework:

  • Acquisition: How do they find you? (channels, campaigns)
  • Activation: What's their first value moment? (onboarding, aha moment)
  • Retention: Why do they come back? (engagement loops, email)
  • Revenue: How do they pay? (pricing, upsells, expansion)
  • Referral: How do they bring others? (viral loops, incentives)

Funnel metrics: Define conversion rate targets for each stage. Measure weekly. A 2% improvement at the top of the funnel compounds through every stage below it.

Drop-off analysis: Where are people leaving? Form too long? Pricing page confusing? Onboarding too complex? Fix the biggest leak first.

A/B Testing Framework

What to test (in priority order):

  1. Headlines and value propositions (biggest impact)
  2. CTA copy and placement
  3. Page layout and section order
  4. Pricing presentation
  5. Social proof placement and format

Test design: One variable at a time. Minimum sample size before calling a winner (use a significance calculator). Run for at least 7 days to account for day-of-week effects. Document every test with hypothesis, variant, result, and learning.

Testing velocity: Aim for 2-4 tests per month. More tests = faster learning = faster growth. But never test without a hypothesis.

Growth Loops

Viral loops: User invites others as part of normal usage (Dropbox referral, Figma multiplayer, Slack team invites). The product IS the distribution.

Content loops: Content attracts visitors, visitors become users, users generate content/data that attracts more visitors (UGC, templates, community).

Paid loops: Revenue funds ads, ads drive signups, signups generate revenue. Sustainable when LTV > 3x CAC.

Deliverables

  1. Campaign brief (objective, audience, message, channels, timeline, budget)
  2. Channel plan (selected channels with tactics and expected ROI)
  3. Audience personas (2-4 detailed persona cards)
  4. Funnel map (stages, metrics, targets, current performance)
  5. Testing roadmap (prioritized A/B tests for next 90 days)

Quality Checklist

  • Campaign has ONE clear objective, not three
  • Each audience segment has a distinct message angle
  • Channel selection is justified by audience behavior, not trend
  • Success metrics are specific numbers with deadlines ("500 signups in 30 days")
  • A/B tests have a written hypothesis before launch
  • Budget has a plan for reallocation based on performance
  • Every deliverable traces back to a business outcome

平台分布

Codex

34.78%
按下载量换算82

Claude

29.61%
按下载量换算70

Cursor

17.92%
按下载量换算42

Gemini CLI

10.41%
按下载量换算24

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills