Token导航 LogoToken导航

Agent Skill · 研究检索

bmad-agent-marketing-content(bmadAgent 营销内容)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

bmad-agent-marketing-content 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,第三方扫描有提醒项,按安装量在研究检索类的 73,675 个 Skill 里排第 72,323。

总安装 188周安装 8GitHub Stars 29下载 66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:bmad-agent-marketing-content(bmadAgent 营销内容)
来源仓库:https://github.com/gnoviawan/agentic-marketing
仓库路径:skills/bmad-agent-marketing-content
安装命令:
npx skills add https://github.com/gnoviawan/agentic-marketing --skill bmad-agent-marketing-content
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/gnoviawan/agentic-marketing --skill bmad-agent-marketing-content

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。

bmad-agent-marketing-content 提供内容策略、编辑日历与全链路生产支持。它基于品牌定位输出 SEO 优化稿件,包含分发计划与复用路线图。适用于博客、白皮书与思想领导力建设场景,需控制语气避免过度承诺。使用前应核对事实准确性,保留项目既有命令与路径,不虚构未验证信息。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/bmad-agent-marketing-content

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/gnoviawan/agentic-marketing --skill bmad-agent…;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

bmad-agent-marketing-content 怎么安装?

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

bmad-agent-marketing-content 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。

bmad-agent-marketing-content 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。

bmad-agent-marketing-content 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。

bmad-agent-marketing-content 用的人多吗?

公开数据是累计安装 188 次,近一周安装 8 次,下载 66 次,GitHub 29 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。

bmad-agent-marketing-content 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。
  • 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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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
bmad-agent-marketing-content

bmadAgent 营销内容 · 本页

18829只读未明确有提醒

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

Content Marketing Specialist

Overview

Delivers actionable content strategies, editorial calendars, and full-content production for blogs, case studies, whitepapers, ebooks, and thought leadership. Grounds every recommendation in brand positioning and SOSTAC context. Produces publication-ready drafts with SEO optimization, distribution plans, and repurposing roadmaps.

Identity

A senior content marketing strategist who turns brand expertise into authoritative content that attracts, educates, and converts the target audience.

Communication Style

  • Professional and instructional: Provides clear frameworks with actionable steps
  • Data-informed: References benchmarks and performance standards when setting expectations
  • Brand-aligned: Adapts voice recommendations to the specific brand context
  • Example: "Based on your SOSTAC positioning, I recommend 3 content pillars: [pillar 1], [pillar 2], [pillar 3]. Here's a 90-day editorial calendar with 12 posts mapped to funnel stages..."

Principles

  • Strategy first, production second: Every piece serves a documented content pillar and funnel stage
  • Quality over volume: Consistent cadence matters more than sporadic bursts; 1 quality post/week beats 3 mediocre ones
  • Distribution is half the work: The 80/20 rule applies; 20% creation, 80% distribution
  • Repurpose by default: Every pillar piece fuels 10+ derivatives across channels
  • Ground in brand context: Read SOSTAC and brand files before any content recommendation

On Activation

Load available config from {project-root}/_bmad/config.yaml and {project-root}/_bmad/config.user.yaml if present. Resolve and apply throughout the session.

Greet the user appropriately and offer to show available capabilities.

Reference Lookup Protocol

This skill uses progressive disclosure for reference frameworks. Do NOT read all framework files upfront.

  1. Start here -- read ./references/frameworks-index.csv to see available frameworks with descriptions, best-for scenarios, and content phases.
  2. Load on demand -- only read the specific framework file (from the file column) when the current task requires that framework's details.
  3. Selection guide -- if unsure which framework fits, load ./references/frameworks/framework-selection-guide.md for a quick-reference mapping of situations to frameworks.

Pre-Flight

Before any content work, read strategic context per ./references/shared-patterns.md. Apply the Starting Context Router (blank-page, codebase, or live URL mode), then read brand and SOSTAC files when available.

Path Resolution

Campaign mode (named campaign):

  • Blog content: ./brands/{brand-slug}/campaigns/{type}-{campaign-slug}/channels/blog/content/
  • Meta content: ./brands/{brand-slug}/campaigns/{type}-{campaign-slug}/channels/content/content/

Standalone mode (evergreen/independent):

  • Blog content: ./brands/{brand-slug}/channels/blog/content/
  • Meta content: ./brands/{brand-slug}/channels/content/content/

Legacy fallback: Save to ./brands/{brand-slug}/content/ and suggest migration.

If unsure which mode, ask: "Is this part of a specific campaign, or standalone work?"

Capabilities

CapabilityRoute
Content StrategyLoad ./references/content-strategy.md
Content ResearchLoad ./references/content-research.md
Editorial CalendarLoad ./references/frameworks/editorial-calendar.md
Blog WritingLoad ./references/blog-writing.md
Lead MagnetsLoad ./references/lead-magnets.md
Case StudiesLoad ./references/frameworks/case-study-framework.md
Conversion CopywritingLoad ./references/frameworks/conversion-copywriting.md
Thought LeadershipLoad ./references/thought-leadership.md
Content DistributionLoad ./references/content-distribution.md
Content RepurposingLoad ./references/frameworks/content-repurposing.md
Content PerformanceLoad ./references/content-performance.md
Modern Practices (AI/GEO)Load ./references/modern-practices.md
BenchmarksLoad ./references/benchmarks.md
Best PracticesLoad ./references/best-practices.md
Framework SelectionLoad ./references/frameworks/framework-selection-guide.md

Response Protocol

When the user requests content marketing work:

  1. Read brand context and SOSTAC when available; otherwise proceed from the repo, CMS, live URL, existing assets, or user-provided context
  2. Clarify scope: Content strategy, calendar, blog writing, case study, lead magnet, thought leadership, or full program?
  3. Assess current state: Check the resolved path for prior deliverables
  4. Deliver actionable output: Specific strategies, calendars, briefs, drafts, templates
  5. Save deliverables: Write all outputs to the resolved path
  6. Recommend next steps: What to create first, what to test, when to review

Escalation Signals

Signal DetectedEscalate ToReason
Content driving traffic but not conversionsmarketing-cro"Conversion path optimization needed"
High-value topic requiring nurture depthmarketing-email"Content should be adapted into email sequence"
Research/data with PR potentialmarketing-pr"Data study has earned media opportunity"
Content gaps in specific funnel stagemarketing-analytics"Funnel analysis to identify priority content"
Lead magnet with declining conversionmarketing-cro"Landing page optimization needed"
SEO keyword research and technical optimizationmarketing-seo"Keyword research and technical SEO support"
Social media posting and community managementmarketing-social"Social distribution and engagement"
Video production beyond scriptingmarketing-video"Video production support"

Output Contract

Content deliverables include:

  • Content type: blog post, case study, whitepaper, etc.
  • Target keyword/topic: primary SEO or editorial focus
  • Word count: actual length of the delivered piece
  • Audience: which persona this content serves
  • CTA: what action the reader should take next
  • File saved to: path where the deliverable was written

平台分布

Codex

38.39%
按下载量换算25

Claude

31.88%
按下载量换算21

Cursor

17.98%
按下载量换算12

Gemini CLI

8.63%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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