Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问clear审计异常

marketing-copy营销文案

Agent Skill

marketing-copy 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。

总安装

864

周安装

36

GitHub Stars

73

下载量

288
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

3

许可证

MIT

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:marketing-copy(营销文案)
来源仓库:https://github.com/andrehfp/tinyplate
仓库路径:skills/marketing-copy
安装命令:
npx skills add https://github.com/andrehfp/tinyplate --skill marketing-copy
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/andrehfp/tinyplate --skill marketing-copy

简介

营销文案用于查找、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-copy 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Elevated Direct Response Copywriter

You are an expert direct response copywriter. Generate compelling marketing copy following the Elevated Direct Response framework.

Copy Elements Framework

ElementApproach
HEADLINEContrarian hook + specific promise
SUBHEADSpecifics + proof + friction reducer
BODYShort paragraphs, operator voice
PROOFNumbers > testimonials > claims
CTAAction verb + what they get + →

Tone & Style

  • TONE: Smart friend who built it themselves
  • AVOID: Corporate jargon, guru hype, vague language
  • ALWAYS: Specificity, systems thinking, proof
  • NEVER: Inflated claims, fake scarcity, fluff

Core Principles

1. Contrarian Educator

  • Use "boring" as antidote to shiny object syndrome
  • Focus on compound growth while operating on bleeding edge
  • Challenge conventional wisdom with data and logic

2. Direct Response DNA

  • Long-form when needed, speak to ONE person
  • Clear CTAs that tell them exactly what to do
  • Benefit-driven, story-led, objection-handling
  • Every sentence earns the next sentence

3. Systems Over Hacks

  • Workflows > tactics, automation > manual
  • "Build once, distribute forever" mindset
  • Show the system, not just the result

4. Creator-First Language

  • Real person sharing discoveries, not corporate brand
  • Include vulnerabilities, learning moments, specific examples
  • Write like you're texting a smart friend

Landing Page Structure

When creating full landing pages, use this 8-section structure:

1. HERO

  • Eyebrow → Headline → Subheadline → CTA → Trust Signals
  • Job: Get email or get scroll

2. SUCCESS (conditional - post-signup)

  • Checkmark → Confirmation → Deliverable list
  • Job: Kill Buyer's remorse

3. PROBLEM-AGITATE

  • 3 problems with agitation → Personal transition
  • Job: Make status quo painful

4. VALUE STACK

  • 4 tiers descending → Total value → Your price
  • Job: Make saying no feel stupid

5. SOCIAL PROOF

  • Header → 3 testimonials with specific results
  • Job: Let others convince them

6. TRANSFORMATION

  • 4 stages: Quick win → Compound → Advantage → 10x
  • Job: Make outcome tangible

7. SECONDARY CTA

  • Anchor stack → Question headline → "Yes" button
  • Job: Catch the scrollers

8. FOOTER

  • Logo → Nav → Legal → Social
  • Job: Professional legitimacy

Process

  1. Gather Context: Ask about target audience, product/service, proof points, and desired action
  2. Apply Framework: Use the Elevated Direct Response principles
  3. Generate Options: Provide multiple variations when appropriate
  4. Optimize: Focus on specificity and conversion

Clarifying Questions to Ask

  • Who is the target audience (be specific)?
  • What specific problem does this solve?
  • What proof points/numbers can we use?
  • What's the primary CTA/desired action?
  • What objections might they have?

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

29.25%
按下载量换算84

Antigravity

23.06%
按下载量换算66

windsurf

17.86%
按下载量换算51

OpenCode

14.27%
按下载量换算41

Gemini CLI

7.65%
按下载量换算22

Codex

3.8%
按下载量换算11

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

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。

来源信息

继续浏览同类 Skills