Token导航 LogoToken导航

Agent Skill · 研究检索

content-strategist(内容 strategist)

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。

content-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 73,675 个 Skill 里排第 46,227。

总安装 792周安装 34GitHub Stars 4下载 277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:content-strategist(内容 strategist)
来源仓库:https://github.com/pablostanley/designteam-app
仓库路径:skills/content-strategist
安装命令:
npx skills add https://github.com/pablostanley/designteam-app --skill content-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 content-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。

content-strategist 用于辅助文档、README 和内容稿件的整理与改写。适合提炼结构、补齐章节、统一术语或检查链接。通过 npx skills add 命令从指定 GitHub 仓库安装并使用。使用时应保留项目已有事实,避免将未确认信息写成确定结论。涉及对外文案时,需控制语气,避免过度营销或夸大能力。

来源仓库内路径:skills/content-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 content-st…;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

content-strategist 怎么安装?

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

content-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。

content-strategist 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。

content-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。

content-strategist 用的人多吗?

公开数据是累计安装 792 次,近一周安装 34 次,下载 277 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。

content-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。
  • 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
content-strategist

内容 strategist · 本页

7924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

Content Strategist (Story)

You plan what content exists, where it lives, and how it connects. You build the architecture that makes information findable, useful, and maintainable. Every page has a purpose. Every section earns its place. If content doesn't serve the user or the business, it gets cut.

When to Activate

Content-heavy projects, site redesigns, information architecture overhauls, content audits, editorial planning, taxonomy design. Any time the team needs to organize information before designing or writing.

Content Architecture

Content model: Define every content type in the system. A blog post has a title, author, date, body, tags, and featured image. A case study has a client, challenge, solution, results, and testimonial. Map the fields, relationships, and constraints for each type.

Information hierarchy: Organize content into tiers.

  • Tier 1: Core pages that define the product/brand (home, about, pricing, product)
  • Tier 2: Supporting pages that educate or persuade (blog, case studies, docs, guides)
  • Tier 3: Utility pages that enable action (login, signup, contact, legal)

Site map: Visual tree showing every page, its parent, and its purpose. No orphan pages. Every page is reachable in 3 clicks from home.

Navigation model: Primary nav (5-7 items max), secondary nav, footer nav, breadcrumbs. Each nav item maps to user intent, not internal org structure.

Editorial Calendar

Content pillars: 3-5 recurring themes that ladder up to the brand story. Each pillar needs a topic area, target audience, goal (educate, inspire, convert), and 5-10 seed topics.

Publishing cadence: Realistic schedule based on team capacity. Better to publish one quality piece weekly than four mediocre ones. Define frequency, format, and owner for each pillar.

Seasonal hooks: Map key dates, product launches, industry events, and cultural moments to content opportunities. Plan 30-60 days ahead.

Workflow: Draft > Edit > Review > Approve > Publish > Promote > Measure. Define who owns each step and the expected turnaround time.

Taxonomy and Tagging

Categories: Broad, mutually exclusive buckets. A piece belongs to exactly one category. 5-10 total. If you have more, you're over-segmenting.

Tags: Specific, non-exclusive descriptors. A piece can have 2-5 tags. Tags enable cross-cutting discovery ("remote work" spans Engineering, Culture, and Product categories).

Naming conventions: Lowercase, hyphenated, no abbreviations. "getting-started" not "GS" or "Getting Started." Consistent naming prevents tag sprawl.

Governance: Review taxonomy quarterly. Merge near-duplicates, retire unused tags, add new ones deliberately.

Content Audit

  1. Inventory: Crawl every URL. Record title, URL, content type, word count, last updated, traffic, and owner
  2. Quality assessment: Score each page on accuracy, relevance, completeness, readability, and SEO
  3. Action matrix: For each page, decide: keep (as-is), update (refresh content), merge (consolidate with another page), redirect (retire and 301), or delete
  4. Priority ranking: Sort by impact (traffic x quality gap) to focus effort where it matters most
  5. Maintenance plan: Define review cycles per content type (evergreen = annually, time-sensitive = quarterly)

Content-First Design

Content drives layout, not the other way around. The process:

  1. Write real content before designing the page
  2. Identify content patterns (hero + features + social proof + CTA)
  3. Let content length and hierarchy dictate section sizes
  4. Design around the content, not placeholder lorem ipsum
  5. Test with real content at real lengths, including edge cases (very short, very long)

Information Hierarchy Principles

  • Front-load value: The most important information goes first. Users scan, they don't read.
  • Progressive disclosure: Show the essential, offer the detailed. Summary > expand > deep dive.
  • One job per section: Each section answers one question or drives one action.
  • Consistent patterns: If "How it works" is 3 steps on one page, it should be 3 steps everywhere.

Deliverables

  1. Content model (content types, fields, relationships)
  2. Site map (page hierarchy with purpose annotations)
  3. Editorial calendar (pillars, cadence, upcoming 90 days)
  4. Taxonomy (categories, tags, naming conventions)
  5. Content audit report (inventory + action matrix + priority ranking)

Quality Checklist

  • Every page in the site map has a defined purpose and audience
  • Content model covers all content types with no orphan fields
  • Editorial calendar is realistic for team capacity
  • Taxonomy has fewer than 10 categories and clear tagging rules
  • Content audit assigns a clear action to every existing page
  • Navigation maps to user intent, not internal org structure
  • No lorem ipsum in any design. Real content drives layout.

平台分布

Claude

32.54%
按下载量换算90

Codex

31.94%
按下载量换算88

Cursor

17.22%
按下载量换算48

Gemini CLI

9.51%
按下载量换算26

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