Token导航 LogoToken导航

Agent Skill · 研究检索

researching-seo-keywords(researching SEO keywords 搜索)

researching-seo-keywords 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。

researching-seo-keywords 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 72,863。

总安装 186周安装 8GitHub Stars 4下载 65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:researching-seo-keywords(researching SEO keywords 搜索)
来源仓库:https://github.com/wesleysmits/agent-skills
仓库路径:skills/researching-seo-keywords
安装命令:
npx skills add https://github.com/wesleysmits/agent-skills --skill researching-seo-keywords
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/wesleysmits/agent-skills --skill researching-seo-keywords

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 SEO 关键词相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中根据关键词或任务场景快速定位候选结果。通过 npx skills add 命令从指定 GitHub 仓库安装,需确认权限与联网能力。建议结合原始 README 核验具体用法,注意维护状态和功能边界。

使用前请检查是否会触发文件读写或命令执行,确保环境安全。

来源仓库内路径:skills/researching-seo-keywords

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/wesleysmits/agent-skills --skill researching-s…;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

researching-seo-keywords 怎么安装?

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

researching-seo-keywords 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。

researching-seo-keywords 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。

researching-seo-keywords 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。

researching-seo-keywords 用的人多吗?

公开数据是累计安装 186 次,近一周安装 8 次,下载 65 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。

researching-seo-keywords 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
researching-seo-keywords

researching SEO keywords 搜索 · 本页

1864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

SEO Keyword Research Assistant

When to use this skill

  • User asks for keyword research
  • User needs keyword variations
  • User wants to analyze search intent
  • User mentions finding content gaps
  • User needs low-competition keywords

Workflow

  • Identify seed keywords
  • Generate variations and long-tails
  • Classify search intent
  • Identify opportunities
  • Group by topic clusters
  • Prioritize for content

Instructions

Step 1: Gather Seed Keywords

Required inputs:

FieldPurpose
Main topic/productCore focus area
Target audienceWho you're reaching
Business goalTraffic, leads, sales
CompetitorsFor gap analysis
Current rankingsWhat you already rank for

Seed keyword sources:

SourceHow to Use
Product/service namesDirect terms
Customer questionsSupport tickets, FAQs
Competitor contentWhat they rank for
Industry termsJargon, acronyms
Problem statementsPain points

Step 2: Generate Keyword Variations

Variation types:

TypeFormulaExample (seed: "email marketing")
Long-tail[seed] + [modifier]"email marketing for small business"
Question[question word] + [seed]"how to start email marketing"
Comparison[seed] vs [alternative]"email marketing vs social media"
Best/topbest [seed] + [qualifier]"best email marketing software 2026"
How-tohow to [action] + [seed]"how to improve email marketing"
Guide[seed] + guide/tutorial"email marketing guide for beginners"
Tool[seed] + tool/software"email marketing automation tools"
Cost[seed] + cost/pricing"email marketing software pricing"

Modifier categories:

CategoryModifiers
Intentbuy, compare, review, learn, find
Time2026, today, now, quick, fast
Qualitybest, top, free, cheap, premium
Audiencefor beginners, for developers, for small business
Locationnear me, in [city], [country]
Formattemplate, checklist, guide, examples

Step 3: Search Intent Classification

Intent types:

IntentSignal WordsContent TypeFunnel Stage
Informationalhow, what, why, guide, learnBlog, guide, tutorialTop (awareness)
Navigational[brand name], login, websiteLanding page, homepageMiddle
Commercialbest, review, compare, vs, topComparison, reviewMiddle (consideration)
Transactionalbuy, price, discount, orderProduct page, pricingBottom (decision)

Intent identification patterns:

## Informational Intent

- "how to [action]"
- "what is [topic]"
- "why does [thing happen]"
- "[topic] explained"
- "[topic] tutorial"

## Commercial Investigation

- "best [product category]"
- "[product A] vs [product B]"
- "[product] review"
- "[product] alternatives"
- "top 10 [products]"

## Transactional Intent

- "buy [product]"
- "[product] price"
- "[product] discount code"
- "[product] free trial"
- "order [product] online"

## Navigational Intent

- "[brand] login"
- "[brand] website"
- "[brand] support"

Step 4: Keyword Opportunity Analysis

Opportunity scoring:

FactorLow Competition Signal
Search volume100-1,000/month (sweet spot for new sites)
Keyword difficultyUnder 30 (tool-dependent)
SERP featuresFew featured snippets, no ads
Top resultsForums, outdated content, thin pages
Domain authorityLow DA sites ranking

Opportunity matrix:

VolumeDifficultyPriority
HighLow🔥 Top priority
MediumLow✅ Quick wins
HighMedium📈 Long-term targets
LowLow⚡ Easy content
HighHigh🎯 Authority builders
LowHigh❌ Skip

Step 5: Question-Based Keywords

Question patterns to generate:

Question WordFocus
HowProcess, tutorial
WhatDefinition, explanation
WhyReasoning, benefits
WhenTiming, triggers
WhereLocation, source
WhichComparison, selection
Can/CouldPossibility, capability
ShouldRecommendation, advice
Is/AreVerification, validation

Question generation template:

## Questions for: [Seed Keyword]

### How questions

- How to [action with keyword]?
- How does [keyword] work?
- How much does [keyword] cost?
- How long does [keyword] take?

### What questions

- What is [keyword]?
- What are the benefits of [keyword]?
- What is the best [keyword]?
- What [keyword] should I use?

### Why questions

- Why is [keyword] important?
- Why use [keyword]?
- Why does [keyword] fail?

### Comparison questions

- [Keyword A] vs [Keyword B]?
- Is [keyword] better than [alternative]?
- What's the difference between [A] and [B]?

Step 6: Topic Cluster Organization

Cluster structure:

## Topic Cluster: [Pillar Topic]

### Pillar Page (main keyword)

- Target: [High-volume keyword]
- Intent: [Informational/Commercial]
- Content: Comprehensive guide (3,000+ words)

### Cluster Content (supporting pages)

| Topic        | Keyword   | Intent   | Internal Link |
| ------------ | --------- | -------- | ------------- |
| [Subtopic 1] | [keyword] | [intent] | → Pillar      |
| [Subtopic 2] | [keyword] | [intent] | → Pillar      |
| [Subtopic 3] | [keyword] | [intent] | → Pillar      |
| [Subtopic 4] | [keyword] | [intent] | → Pillar      |

Cluster example:

## Topic Cluster: Email Marketing

### Pillar Page

- Target: "email marketing guide"
- Intent: Informational
- Content: Ultimate Guide to Email Marketing

### Cluster Content

| Topic           | Keyword                         | Intent        |
| --------------- | ------------------------------- | ------------- |
| Getting started | "how to start email marketing"  | Informational |
| Tools           | "best email marketing software" | Commercial    |
| Templates       | "email marketing templates"     | Informational |
| Automation      | "email marketing automation"    | Commercial    |
| Metrics         | "email marketing KPIs"          | Informational |
| B2B focus       | "b2b email marketing"           | Commercial    |
| List building   | "how to build email list"       | Informational |

Step 7: Competitor Gap Analysis

Gap analysis template:

## Competitor Keyword Gap Analysis

### Competitors Analyzed

1. [Competitor 1 URL]
2. [Competitor 2 URL]
3. [Competitor 3 URL]

### Keywords They Rank For (You Don't)

| Keyword   | Volume | Difficulty | Competitor  | Priority   |
| --------- | ------ | ---------- | ----------- | ---------- |
| [keyword] | [vol]  | [KD]       | [who ranks] | [priority] |

### Content Gaps Identified

| Topic   | Competitor Coverage | Your Coverage | Action        |
| ------- | ------------------- | ------------- | ------------- |
| [topic] | 3 articles          | 0 articles    | Create pillar |
| [topic] | 1 article           | Outdated      | Update        |
| [topic] | None                | None          | First mover   |

Step 8: Keyword Prioritization

Prioritization framework:

CriteriaWeightScore (1-5)
Search volume20%
Keyword difficulty25%
Business relevance25%
Conversion potential20%
Content gap10%

Priority tiers:

## Keyword Priorities

### Tier 1: Immediate (This Month)

- Low difficulty + high relevance
- Quick wins for traffic
  | Keyword | Volume | KD | Intent |
  |---------|--------|----|----|

### Tier 2: Short-term (1-3 Months)

- Medium difficulty + commercial intent
- Revenue-driving content
  | Keyword | Volume | KD | Intent |
  |---------|--------|----|----|

### Tier 3: Long-term (3-6 Months)

- High difficulty + high volume
- Authority-building pillar content
  | Keyword | Volume | KD | Intent |
  |---------|--------|----|----|

Output Format

## Keyword Research: [Topic/Niche]

**Seed keywords:** [List of seeds]
**Target audience:** [Who you're reaching]
**Business goal:** [Traffic/Leads/Sales]

---

### Keyword List

| Keyword | Volume | KD  | Intent | Priority |
| ------- | ------ | --- | ------ | -------- |
|         |        |     |        |          |

### By Search Intent

**Informational:**

- [keywords]

**Commercial:**

- [keywords]

**Transactional:**

- [keywords]

---

### Topic Clusters

[Cluster organization]

---

### Question Keywords

[Question-based keywords for FAQ/content]

---

### Quick Wins (Low KD, Decent Volume)

| Keyword | Volume | KD  | Content Type |
| ------- | ------ | --- | ------------ |
|         |        |     |              |

---

### Content Recommendations

1. [Recommendation 1]
2. [Recommendation 2]
3. [Recommendation 3]

Validation

Before completing:

  • Keywords classified by intent
  • Volume and difficulty included
  • Question keywords generated
  • Topic clusters organized
  • Priority tiers assigned
  • Quick wins identified
  • Content recommendations provided
  • Competitor gaps noted

Error Handling

  • No seed keywords: Ask for main product/service or topic area.
  • Too broad: Narrow with audience, location, or specific use case.
  • No volume data: Note as "volume unknown" and prioritize by relevance.
  • All high difficulty: Focus on long-tail variations or question keywords.
  • No competitors identified: Search top 3 ranking for seed keywords.

Resources

平台分布

Codex

38.44%
按下载量换算25

Claude

27.04%
按下载量换算18

Cursor

17.48%
按下载量换算11

Gemini CLI

9.57%
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