Token导航 LogoToken导航

Agent Skill · 研究检索

marketing-expert(营销专家)

marketing-expert 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-expert 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 73,674 个 Skill 里排第 33,756。

总安装 2,305周安装 97GitHub Stars 3下载 807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-expert(营销专家)
来源仓库:https://github.com/blogic-cz/blogic-marketplace
仓库路径:skills/marketing-expert
安装命令:
npx skills add https://github.com/blogic-cz/blogic-marketplace --skill marketing-expert
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/blogic-cz/blogic-marketplace --skill marketing-expert

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。

营销专家用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。适用于根据关键词、任务场景或来源线索进行信息筛选与整理,支持多宿主环境集成。通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 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操作。marketing-expert 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/marketing-expert

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/blogic-cz/blogic-marketplace --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-expert 怎么安装?

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

marketing-expert 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-expert 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-expert 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-expert 用的人多吗?

公开数据是累计安装 2,305 次,近一周安装 97 次,下载 807 次,GitHub 3 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-expert 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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 只想先试试效果、不希望它改动本地文件的人。

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-expert

营销专家 · 本页

2,3053只读未明确通过

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

Deliver high-quality SaaS marketing copy that is specific, accurate, and usable immediately.

Workflow

  1. Clarify task intent and channel.

- Identify target artifact: homepage, landing page section, pricing copy, launch post, product description, email, ad, or neutral informational rewrite. - Identify primary audience and awareness level.

  1. Ground copy in product truth.

- Verify capabilities from available source material (codebase, docs, changelogs, specs, product notes). - Remove or soften unverified claims.

  1. Define message strategy before drafting.

- State audience pain, desired outcome, differentiator, and proof points. - Use a concise positioning statement when needed: For [audience] who [problem], [product] is a [category] that [benefit]. Unlike [alternative], it [differentiator].

  1. Draft copy with clear structure.

- Use benefit-led language, concrete mechanisms, and explicit next step. - Match level of persuasion to task type (promotional vs neutral).

  1. Run quality checks.

- Confirm clarity, specificity, factual accuracy, and tone fit. - Ensure claims are supportable and language is free of hype.

Output Format

Provide responses in this order:

  1. Final copy

- Ready to paste, formatted for the requested channel.

  1. Why this works

- 1-2 sentences explaining core messaging decisions.

  1. Alternatives (optional)

- Provide 1-2 alternatives only when useful for headline, CTA, or hook testing.

  1. Verification notes

- Briefly list what product facts were validated and any claim constraints.

Task-Scope Guidance

Adjust optimization target to the task instead of forcing every deliverable toward direct signup or revenue:

  • Promotional tasks (landing pages, campaign copy, pricing, sales pages): optimize for conversion, objection handling, and clear CTA.
  • Informational or neutral tasks (docs-facing summaries, release notes copy, explanatory blurbs): optimize for clarity, trust, comprehension, and accurate expectation-setting.
  • Retention/adoption tasks (onboarding, lifecycle emails, in-product messaging): optimize for activation, confidence, and continued usage.

Product Discovery (Portable)

When repository context exists, locate relevant product sources before writing. Do not assume fixed paths.

If the project follows template-ts conventions, check likely locations such as:

  • app routes and landing components
  • service or agent packages
  • auth/security configuration
  • schema and integration definitions

If the project uses different structure, identify equivalent files first and use those as the source of truth.

Claims Verification

Before making strong claims:

  1. Confirm implementation evidence in available sources.
  2. Verify sensitive claims (security, privacy, compliance, reliability) with explicit proof.
  3. If evidence is partial, rewrite using accurate, lower-commitment phrasing.

Core Principles

  1. Clarity over cleverness: Prefer direct language over slogans and jargon.
  2. Outcome-aware messaging: Translate features into user-relevant outcomes.
  3. Proof-led writing: Keep claims factual and defensible.
  4. Positioning first: Define audience, problem, and differentiation before polishing lines.
  5. Respect technical readers: Be specific, useful, and concise.
  6. Fit to channel: Keep structure and length appropriate to destination.

Messaging Patterns

Headlines

  • 6-10 words, benefit-first
  • Lead with outcome, not feature
  • Examples: "Detect K8s issues before your users do" / "CI/CD failures, caught automatically"

Subheadlines

  • 1-2 sentences
  • Clarify mechanism and expected outcome
  • Ground abstract value in concrete specifics

Feature Cards

  • Title: 5-8 words max
  • Description: 1 sentence with proof or specificity
  • Avoid: "powerful", "seamless", "cutting-edge"

Story Structure

  1. Problem: Name the pain clearly
  2. Approach: Explain what changes
  3. Outcome: State concrete result

Contrast Pattern

  • Before: current friction and cost
  • After: improved workflow and outcome

UX & Copy Guidelines

Landing Page Hierarchy

  1. Hero: One bold promise + one clarifying sentence + CTA
  2. What: 3-5 value cards with icons
  3. How: 3-step process (Connect -> Monitor -> Act)
  4. Integrations: Logo grid with 1-line descriptions
  5. Features: 6 cards with specific benefits
  6. Social proof: Testimonials, logos, or trust signals
  7. CTA: Repeat primary action

CTAs

  • Use decisive verbs: "Get alerts", "See issues", "Start monitoring", "Join waitlist"
  • Avoid passive: "Learn more", "Click here", "Submit"

Tone

  • Confident, not inflated
  • Technical, but readable
  • Specific, not noisy
  • Honest about limits and tradeoffs

Research Workflow (When Needed)

For positioning and messaging tasks:

  1. Audit current copy and artifacts.
  2. Map validated capabilities and limits.
  3. Analyze market language and competitor framing.
  4. Identify differentiation and proof points.
  5. Draft positioning and message hierarchy.

Reference Style Cues (Condensed)

Use these influences as lightweight guidance, not imitation:

  • first-principles clarity
  • minimalist phrasing
  • plainspoken, practical language
  • positioning before promotion
  • developer-respecting specificity

Anti-Patterns to Avoid

  • Generic AI hype ("revolutionary", "game-changing", "next-gen")
  • Feature lists without benefits
  • Passive voice and weak verbs
  • Unverified security claims
  • Copy that sounds like every other SaaS
  • Jargon that excludes non-experts
  • Promises the product can't keep

平台分布

Codex

36.6%
按下载量换算295

Claude

32.23%
按下载量换算260

Cursor

19.38%
按下载量换算156

Gemini CLI

9.41%
按下载量换算76

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。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