Token导航 LogoToken导航

Agent Skill · 研究检索

programmatic-seo(程序化 SEO)

programmatic-seo 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。

programmatic-seo 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;许可证为 MIT,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 61,129。

总安装 356周安装 15GitHub Stars 1下载 125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
MIT

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:programmatic-seo(程序化 SEO)
来源仓库:https://github.com/younesbenallal/seo-skills
仓库路径:skills/programmatic-seo
安装命令:
npx skills add https://github.com/younesbenallal/seo-skills --skill programmatic-seo
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/younesbenallal/seo-skills --skill programmatic-seo

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。可结合来源仓库和 README 核验具体用法。安装命令:npx skills add https://github.com/younesbenallal/seo-skills --skill programmatic-seo。

安装前建议确认权限范围和维护状态。

来源仓库内路径:skills/programmatic-seo

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/younesbenallal/seo-skills --skill programmatic…;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

programmatic-seo 怎么安装?

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

programmatic-seo 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。

programmatic-seo 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。

programmatic-seo 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

programmatic-seo 用的人多吗?

公开数据是累计安装 356 次,近一周安装 15 次,下载 125 次,GitHub 1 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。

programmatic-seo 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。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

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。
  • 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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

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
programmatic-seo

程序化 SEO · 本页

3561接触敏感数据MIT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

pSEO

You help the user ship pSEO that avoids thin content and actually ranks.

Shared context first

Before asking repeated discovery questions, check whether .agents/seo-context.md exists.

If it does:

  • read it first
  • reuse the saved site, market, competitor, and tooling context
  • ask only for pSEO-specific gaps that are still missing

Context Gathering First

Before asking the user for inputs, proactively gather context:

  • Search the codebase for existing pSEO implementations, templates, or similar patterns
  • Check for product documentation, ICP info, or business context files
  • Look for existing data sources, APIs, or databases mentioned in the codebase
  • Review any existing SEO documentation or strategies
  • Only ask the user for information you cannot find through exploration

Tooling & credentials

  • Auth mode: none
  • Requires: no external credential
  • Optional tools: Browser MCP or agent-browser, SERP API MCP, Ahrefs/Semrush MCP
  • Fallback: continue with repo context, manual URLs, and user-provided data if external tools are unavailable

Follow the shared setup and missing-access rules in docs/credentials-and-tooling.md.

Core Principles

  1. Unique Value Per Page: Every page must provide value specific to that page—not just swapped variables. Maximize unique content and avoid thin content penalties.
  2. Proprietary Data Wins: Best pSEO uses data competitors can't easily replicate. Hierarchy: proprietary > product-derived > user-generated > licensed > public.
  3. Subfolders, Not Subdomains: Always use subfolders (yoursite.com/templates/resume/), never subdomains. They make tracking easier and pass authority.
  4. Genuine Search Intent Match: Pages must actually answer what people are searching for—don't over-optimize keywords at the expense of usefulness.

pSEO Patterns

1. Templates

Pattern: [type] template or free [type] template Examples: "resume template", "invoice template", "pitch deck template" URL: /templates/[type]/ Value: Actually usable templates, multiple variations, quality comparable to paid options

2. Curation

Pattern: best [category] or top [number] [things] Examples: "best website builders", "top 10 crm software", "best free design tools" URL: /best/[category]/ Value: Genuine evaluation criteria, real testing, regular updates

3. Conversions

Pattern: [X] to [Y] or [amount] [unit] in [unit] Examples: "$10 USD to GBP", "100 kg to lbs", "pdf to word" URL: /convert/[from]-to-[to]/ Value: Accurate, real-time data, fast functional tool

4. Comparisons

Pattern: [X] vs [Y] or [X] alternative Examples: "webflow vs wordpress", "notion vs coda", "figma alternatives" URL: /compare/[x]-vs-[y]/ Value: Honest analysis, feature comparison data, clear recommendations

5. Examples

Pattern: [type] examples or [category] inspiration Examples: "saas landing page examples", "email subject line examples", "portfolio website examples" URL: /examples/[type]/ Value: Real, high-quality examples with screenshots and analysis

6. Locations

Pattern: [service/thing] in [location] Examples: "coworking spaces in san diego", "dentists in austin", "best restaurants in brooklyn" URL: /[service]/[city]/ Value: Actual local data, local providers listed, location-specific insights

7. Personas

Pattern: [product] for [audience] or [solution] for [role/industry] Examples: "payroll software for agencies", "crm for real estate", "project management for freelancers" URL: /for/[persona]/ Value: Persona-specific content, relevant features, testimonials from that segment

8. Integrations

Pattern: [your product] [other product] integration or [product] + [product] Examples: "slack asana integration", "zapier airtable", "hubspot salesforce sync" URL: /integrations/[product]/ Value: Real integration details, setup instructions, use cases

9. Glossary

Pattern: what is [term] or [term] definition Examples: "what is pSEO", "api definition", "what does crm stand for" URL: /glossary/[term]/ Value: Clear definitions with examples, related terms linked

10. Translations

Pattern: Same content in multiple languages Examples: "qué es pSEO", "was ist SEO" URL: /[lang]/[page]/ Value: Quality translation (not just Google Translate), cultural localization

11. Directory

Pattern: [category] tools or [type] software Examples: "ai copywriting tools", "email marketing software", "crm companies" URL: /directory/[category]/ Value: Comprehensive coverage, useful filtering, details per listing

12. Profiles

Pattern: [person/company name] or [entity] + [attribute] Examples: "stripe ceo", "airbnb founding story", "elon musk companies" URL: /people/[name]/ Value: Accurate, sourced information, unique insights

You can combine patterns: "Marketing agencies for startups in Austin" (Locations + Personas), "Best coworking spaces in San Diego" (Curation + Locations)

Workflow

  1. Pattern Selection: Pick ONE scalable pattern with real search demand.
  2. Unique Value Rules: Define what makes each page unique—what changes per page that matters. Avoid thin content by ensuring genuine differentiation.
  3. Template Design:

- Intent-matching core content - Data-driven block (unique per page) - Comparison/alternatives (if relevant) - FAQ/definitions (AEO/GEO friendly)

  1. URL Structure: Use subfolders, clean slugs, consistent pattern. Example: /templates/[type]/ or /[service]/[city]/
  2. Thin Content Gate: Checklist that every page must pass:

- Provides unique value (not just variable substitution) - Answers search intent - Has sufficient unique content - Includes data/insights specific to this page

  1. Production Plan:

- Data generation/acquisition - Page rendering (template + data) - Internal linking (hub + spokes model) - Sitemap + indexation strategy

  1. Measurement: Track indexing rate, impressions, CTR, position buckets by pattern

Output

  • Template spec: Sections + data fields required
  • Unique value rules: Checklist for what makes each page unique
  • First 10 pages: Prioritized list to build first
  • Internal linking plan: Hub page + spoke pages structure
  • Quality checklist: Pre-launch validation criteria

平台分布

Claude Code

27.95%
按下载量换算35

Antigravity

25.99%
按下载量换算32

OpenCode

16.53%
按下载量换算21

Codex

12.47%
按下载量换算16

Gemini CLI

8.76%
按下载量换算11

Cursor

3.47%
按下载量换算4

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

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。

继续浏览同类 Skills