Token导航 LogoToken导航

Agent Skill · 研究检索

setup-cms(设置 CMS)

setup-cms 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。

setup-cms 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,权限为接触敏感数据;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 51,212。

总安装 588周安装 25GitHub Stars 1,537下载 206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:setup-cms(设置 CMS)
来源仓库:https://github.com/nowork-studio/toprank
仓库路径:skills/setup-cms
安装命令:
npx skills add https://github.com/nowork-studio/toprank --skill setup-cms
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/nowork-studio/toprank --skill setup-cms

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、检索和筛选相关信息。适合根据关键词或任务场景快速定位候选结果。通过 npx skills add 命令从 nowork-studio/toprank 仓库安装。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。

setup-cms 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/setup-cms

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/nowork-studio/toprank --skill setup-cms;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

    它需要接触敏感数据,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

setup-cms 怎么安装?

在终端执行 npx skills add https://github.com/nowork-studio/toprank --skill setup-cms。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

setup-cms 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。

setup-cms 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

setup-cms 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。

setup-cms 用的人多吗?

公开数据是累计安装 588 次,近一周安装 25 次,下载 206 次,GitHub 1,537 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。

setup-cms 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

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。
  • 来源仓库有 1,537 星,维护活跃度相对可查。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 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。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 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
setup-cms

设置 CMS · 本页

5881,537接触敏感数据未明确未通过

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

/setup-cms

Guide the user through connecting their CMS to toprank's SEO analysis tools.

Once configured, /seo-analysis automatically pulls published content from the CMS and cross-references it against Google Search Console data — finding invisible pages, content gaps, stale articles, and missing SEO fields.


Step 0 — Setup

Read and follow ../shared/preamble.md — it locates the SEO scripts directory. Use $SKILL_SCRIPTS from the preamble for all script calls below.

Step 1 — Detect existing CMS configuration

CMS_TYPE=$(python3 "$SKILL_SCRIPTS/cms_detect.py" 2>/dev/null)
CMS_STATUS=$?
echo "CMS_TYPE=$CMS_TYPE  EXIT=$CMS_STATUS"
  • CMS_STATUS=0 → a CMS is already configured ($CMS_TYPE is the name). Show the user: "You already have [$CMS_TYPE] connected. Would you like to reconfigure it, or switch to a different CMS?" Wait for their reply. If they say reconfigure/switch, continue to Step 2. If they say test or verify, jump to Step 5 (skip to connection test).
  • CMS_STATUS=2 → nothing configured yet. Continue to Step 2.

Step 2 — Choose a CMS

Ask the user:

"Which CMS are you connecting? I support: 1. WordPress — self-hosted or WordPress.com (uses REST API + Application Password) 2. Strapi — v4 or v5, self-hosted (uses API Token) 3. Contentful — cloud headless CMS (uses Delivery API key) 4. Ghost — Ghost.org or self-hosted (uses Content API key) Reply with the name or number."

Wait for their answer. Map to: wordpress, strapi, contentful, ghost.


Step 3 — Credential setup by CMS

Jump to the sub-section for the chosen CMS.


3A — WordPress

WordPress uses the built-in Application Passwords feature (introduced in WP 5.6). This is the safest way to grant API access — it never exposes your main password and can be revoked at any time.

Tell the user:

"I need three things to connect WordPress: 1. Your WordPress URL (e.g. https://myblog.com) 2. Your WordPress username (the one you log in with) 3. An Application Password — create one in: WordPress Admin → Users → Profile → scroll to Application Passwords → enter a name like "toprank" → click Add New → copy the generated password Paste each value when ready."

Collect values one at a time:

  1. Ask for WP_URL → validate it starts with http:// or https://
  2. Ask for WP_USERNAME
  3. Ask for WP_APP_PASSWORD
  4. Ask for WP_CONTENT_TYPE: "What content type should I analyze? Common values: posts, pages. Press Enter to use posts (default), or enter a custom post type slug."

Once all four are collected, continue to Step 4 (test connection).

Write to .env.local:

WP_URL=<value>
WP_USERNAME=<value>
WP_APP_PASSWORD=<value>
WP_CONTENT_TYPE=<value or posts>

3B — Strapi

Tell the user:

"I need two things to connect Strapi: 1. Your Strapi URL (e.g. https://cms.example.com) 2. A Full-access API Token — create one in: Strapi Admin → Settings → Global settings → API Tokens → Create new API Token → Type: Full access → copy the token Optionally: - Content type — the plural API ID of your content collection (default: articles). Find it in: Content-Type Builder → [your type] → API ID (plural) - Strapi version — 4 or 5 (auto-detected if omitted) Paste each value when ready."

Collect:

  1. STRAPI_URL
  2. STRAPI_API_KEY
  3. STRAPI_CONTENT_TYPE (optional, default: articles)
  4. STRAPI_VERSION (optional)

Write to .env.local:

STRAPI_URL=<value>
STRAPI_API_KEY=<value>
STRAPI_CONTENT_TYPE=<value or articles>

Include STRAPI_VERSION=<value> only if the user specified it.


3C — Contentful

Tell the user:

"I need three things to connect Contentful: 1. Space ID — find it in: Contentful → Settings → General Settings → Space ID 2. Content Delivery API token — find it in: Settings → API Keys → [your key] → Content Delivery API - access token (If no key exists, create one under Settings → API Keys → Add API Key) 3. Content type ID — the API identifier for your content type. Find it in: Content model → [your type] → API Identifier Optionally: - Environment (default: master) Paste each value when ready."

Collect:

  1. CONTENTFUL_SPACE_ID
  2. CONTENTFUL_DELIVERY_TOKEN
  3. CONTENTFUL_CONTENT_TYPE
  4. CONTENTFUL_ENVIRONMENT (optional, default: master)

Write to .env.local:

CONTENTFUL_SPACE_ID=<value>
CONTENTFUL_DELIVERY_TOKEN=<value>
CONTENTFUL_CONTENT_TYPE=<value>
CONTENTFUL_ENVIRONMENT=<value or master>

3D — Ghost

Tell the user:

"I need two things to connect Ghost: 1. Your Ghost URL (e.g. https://myblog.ghost.io) 2. Content API key — create one in: Ghost Admin → Settings → Integrations → Add custom integration → copy the Content API Key Optionally: - Content type: posts (default) or pages Paste each value when ready."

Collect:

  1. GHOST_URL
  2. GHOST_CONTENT_KEY
  3. GHOST_CONTENT_TYPE (optional, default: posts)

Write to .env.local:

GHOST_URL=<value>
GHOST_CONTENT_KEY=<value>
GHOST_CONTENT_TYPE=<value or posts>

Step 4 — Write.env.local

Find the project's .env.local file. Search for it:

ENV_FILE=""
for candidate in ".env.local" "$HOME/.env.local"; do
  [ -f "$candidate" ] && ENV_FILE="$candidate" && break
done
[ -z "$ENV_FILE" ] && ENV_FILE=".env.local"
echo "Writing to: $ENV_FILE"

Merge strategy — do not overwrite the entire file. For each env var:

  1. If the key already exists in the file, replace that line.
  2. If it does not exist, append it to the end.

Read the file first (if it exists), then update key by key, then write back.

If the file doesn't exist yet, create it.

After writing, confirm:

"Credentials written to [path]. Testing connection now..."

Step 5 — Test connection

Run the appropriate preflight script and capture the exit code:

# WordPress
python3 "$SKILL_SCRIPTS/preflight_wordpress.py" 2>&1; PREFLIGHT_EXIT=$?

# Strapi
python3 "$SKILL_SCRIPTS/preflight_strapi.py" 2>&1; PREFLIGHT_EXIT=$?

# Contentful
python3 "$SKILL_SCRIPTS/preflight_contentful.py" 2>&1; PREFLIGHT_EXIT=$?

# Ghost
python3 "$SKILL_SCRIPTS/preflight_ghost.py" 2>&1; PREFLIGHT_EXIT=$?

The 2>&1 redirect surfaces error messages in the output so you can show them.

PREFLIGHT_EXIT=0 — connection successful. Show the "OK: …" line to the user, then continue to Step 6.

PREFLIGHT_EXIT=1 — connection failed. Show the full error output verbatim. Help the user diagnose:

  • 401 Unauthorized → wrong token/password — suggest regenerating
  • 403 Forbidden → token lacks permission — suggest a Full Access / unrestricted token
  • 404 Not Found → wrong URL or wrong content type slug
  • Network error → URL unreachable — check the URL in a browser first

Ask: "Want to fix the credentials and try again (I'll go back to Step 3), or skip CMS setup for now?"

PREFLIGHT_EXIT=2 → credentials were removed from .env.local between steps. Restart from Step 3.


Step 6 — Confirm and summarize

Once the connection succeeds, show a summary:

CMS connected successfully!

  CMS:          [WordPress/Strapi/Contentful/Ghost]
  URL:          [cms_url]
  Content type: [content_type]
  Published:    [N] entries found

What this enables in /seo-analysis:
  • Cross-reference [N] published articles against Google Search Console data
  • Find published content with zero GSC impressions (unindexed or invisible)
  • Identify content gaps: queries ranking 11-30 with no matching article
  • Flag stale content: articles >6 months old with declining clicks
  • Audit SEO fields: missing meta titles/descriptions, length violations

Then offer:

"Run /seo-analysis to see a full audit with your CMS content included, or type /setup-cms again to connect a different CMS."

平台分布

Codex

33.93%
按下载量换算70

Claude

30.8%
按下载量换算63

Cursor

18.55%
按下载量换算38

Gemini CLI

8.87%
按下载量换算18

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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