How to Install Any Claude Skill From GitHub [Step-by-step] - Beginner Tutorial

Ever get tired of typing the same giant prompt into Claude every time you need an SEO audit, a code review, or some other detailed task? Yeah, same. That’s exactly the problem Claude Skills were built to solve - and the best part is, you don’t have to build your own. Thousands of ready-made skills are sitting on GitHub, free for the taking.

Here’s a quick, no-fluff walkthrough on how to grab them.

What Are Claude Skills, Anyway?

Think of a Skill as a saved “instruction manual” for Claude. Instead of re-explaining what you want every single time (on-page SEO checks, meta descriptions, schema markup, the whole technical checklist), you upload a Skill once - and Claude just knows how to do that task consistently, every time you use it.

Anthropic puts it simply on their skills page: skills turn your expertise and best practices into reusable capabilities. One and done.

Step 1: Understand the Skill File

Every Skill is basically a SKILL.md file - a document containing the skill’s name, description, and detailed instructions. Once you open one up, you’ll see exactly how it’s structured: name at the top, description below, then the full set of instructions Claude will follow.

Step 2: Manually Upload a Skill to Claude

Got a single Skill file you want to try? Here’s the manual route:

1. Open Claude and click Customize.
2. Go to the Skills section.
3. Click Add, then Upload Skill.
4. Select your SKILL.md file and hit Open.

That’s it - your new skill now shows up whenever you click the + icon and hover over “Skill” in a chat.

Step 3: Find Trending Skills on GitHub

Want to browse what’s popular instead of building your own? Head to github.com/trending. This page shows the hottest repositories on GitHub right now - and skill repositories show up here often, packed with dozens of ready-to-use .md files organized by category (engineering, marketing, SEO, you name it).

Click into any repo, navigate to the skill you want, open its SKILL.md file, and download it. Then just follow Step 2 to install it.

Step 4: Bulk-Install an Entire Repository at Once

Downloading skills one by one gets old fast - especially when a repo has 30+ of them. Good news: you can install the whole repository in one shot using Claude’s Marketplace feature.

1. On the repository’s GitHub page, click the green Code button and copy the repository URL.
2. In Claude, go to Customize > Plugins.
3. Click Add > Add Marketplace.
4. Choose Add from a Repository.
5. Paste the GitHub URL and click Sync.
6. All the skills in that repo will populate - click Install to add them all at once.

Just like that, dozens of skills are ready to use without a single manual download.

Step 5: Discover More Skills on skills.sh

Beyond GitHub, there’s a dedicated marketplace called skills.sh where you can browse trending AI agent skills - some with millions of installs - built for Claude and other AI agents alike. It’s a great place to see what the community is actually using and find hidden gems for your workflow.

Why Bother With Skills At All?

• No more repetitive prompting - write the instructions once, reuse forever
• Consistent, high-quality output every time
• Save tokens since you’re not re-typing lengthy prompts
• Learn from the best - many popular skills are built by experienced engineers and creators

Once you’ve got a handful of skills installed, Claude starts feeling less like a chatbot and more like a set of trained specialists on standby.

Want to level up further? Try pairing your skills with Claude Design for building visuals and prototypes right alongside your workflow.

Want to add seo-skill, just add the following:

---
name: seo-audit
description: "Full website SEO audit with parallel subagent delegation. Crawls up to 500 pages, detects business type, delegates to up to 15 specialists (8 always + 7 conditional), generates health score. Use when user says audit, full SEO check, analyze my site, or website health check."
user-invocable: true
argument-hint: "[url]"
license: MIT
metadata:
  author: WebSensePro
  version: "1.0"
  category: seo
---

# Full Website SEO Audit

## Process

1. **Render homepage**: use `claude-seo run render_page.py <url> --mode auto --json` to capture raw HTML, rendered HTML, extracted text, SPA status, and accessibility data when needed
2. **Detect business type**: analyze homepage signals per seo orchestrator
3. **Crawl site**: follow internal links up to 500 pages, respect robots.txt
4. **Delegate to subagents** (if available, otherwise run inline sequentially):
   - `seo-technical` -- robots.txt, sitemaps, canonicals, Core Web Vitals, security headers
   - `seo-content` -- E-E-A-T, readability, thin content, AI citation readiness
   - `seo-schema` -- detection, validation, generation recommendations
   - `seo-sitemap` -- structure analysis, quality gates, missing pages
   - `seo-performance` -- LCP, INP, CLS measurements
   - `seo-visual` -- screenshots, mobile testing, above-fold analysis
   - `seo-geo` -- AI crawler access, llms.txt, citability, brand mention signals
   - `seo-local` -- GBP signals, NAP consistency, reviews, local schema, industry-specific local factors (spawn when Local Service industry detected: brick-and-mortar, SAB, or hybrid business type)
   - `seo-maps` -- Geo-grid rank tracking, GBP audit, review intelligence, competitor radius mapping (spawn when Local Service detected AND DataForSEO MCP available)
   - `seo-google` -- CWV field data (CrUX), URL indexation (GSC), organic traffic (GA4) (spawn when Google API credentials detected via `claude-seo run google_auth.py --check`)
   - `seo-backlinks` -- Backlink profile data: DA/PA, referring domains, anchor text, toxic links (spawn when Moz or Bing API credentials detected via `claude-seo run backlinks_auth.py --check`, or always include Common Crawl domain-level metrics)
   - `seo-cluster` -- Semantic clustering analysis (spawn when content strategy signals detected: blog, pillar pages, topic clusters)
   - `seo-sxo` -- Search experience analysis: page-type mismatch, user stories, persona scoring (always include in full audits)
   - `seo-drift` -- Drift analysis: compare against stored baseline (spawn when drift baseline exists for the URL via `claude-seo run drift_history.py <url>`)
   - `seo-ecommerce` -- Product schema, marketplace intelligence (spawn when E-commerce industry detected)
5. **Score** -- aggregate into SEO Health Score (0-100)
6. **Persist audit artifacts** -- write all outputs under `{domain}-audit/`
7. **Report** -- generate prioritized action plan and optional PDF/HTML report

## Crawl Configuration

```
Max pages: 500
Respect robots.txt: Yes
Follow redirects: Yes (max 3 hops)
Timeout per page: 30 seconds
Concurrent requests: 5
Delay between requests: 1 second
```

## Output Files

- `{domain}-audit/FULL-AUDIT-REPORT.md`: Comprehensive findings
- `{domain}-audit/ACTION-PLAN.md`: Prioritized recommendations (Critical > High > Medium > Low)
- `{domain}-audit/audit-data.json`: Structured audit envelope for report generation
- `{domain}-audit/findings/*.md`: Per-category specialist findings (`technical.md`, `content.md`, `schema.md`, `performance.md`, `visual.md`, etc.)
- `{domain}-audit/screenshots/`: Desktop + mobile captures (if Playwright available)
- **PDF Report** (recommended): Generate a professional A4 PDF using `claude-seo run google_report.py --type full --data {domain}-audit/audit-data.json --domain <domain> --output-dir {domain}-audit/`. This produces a white-cover enterprise report with TOC, executive summary, charts (Lighthouse gauges, query bars, index donut), metric cards, threshold tables, prioritized recommendations with effort estimates, and implementation roadmap. Always offer PDF generation after completing an audit.

## Structured Audit Data Envelope

Write `{domain}-audit/audit-data.json` with this shape so `claude-seo run google_report.py --type full --data {domain}-audit/audit-data.json --domain <domain> --output-dir {domain}-audit/` can generate a report even when Google API data is unavailable:

```json
{
  "summary": {
    "health_score": 0,
    "business_type": "detected type",
    "top_findings": [],
    "quick_wins": []
  },
  "categories": [
    {
      "name": "Technical SEO",
      "score": 0,
      "what_works": [],
      "findings": [
        {
          "title": "Finding title",
          "severity": "Critical|High|Medium|Low|Info",
          "description": "Evidence-backed detail",
          "recommendation": "Specific fix"
        }
      ]
    }
  ],
  "action_plan": {
    "phases": [
      {"name": "Phase 1: Critical Fixes", "timeframe": "Week 1", "items": []},
      {"name": "Phase 2: High-Impact Improvements", "timeframe": "Weeks 2-3", "items": []},
      {"name": "Phase 3: Content & Authority", "timeframe": "Month 2", "items": []},
      {"name": "Phase 4: Monitoring & Iteration", "timeframe": "Ongoing", "items": []}
    ]
  },
  "artifacts": {
    "findings_dir": "findings/",
    "screenshots_dir": "screenshots/"
  }
}
```

## Scoring Weights

| Category | Weight |
|----------|--------|
| Technical SEO | 22% |
| Content Quality | 23% |
| On-Page SEO | 20% |
| Schema / Structured Data | 10% |
| Performance (CWV) | 10% |
| AI Search Readiness | 10% |
| Images | 5% |

## Report Structure

### Executive Summary
- Overall SEO Health Score (0-100)
- Business type detected
- Top 5 critical issues
- Top 5 quick wins

### Technical SEO
- Crawlability issues
- Indexability problems
- Security concerns
- Core Web Vitals status

### Content Quality
- E-E-A-T assessment
- Thin content pages
- Duplicate content issues
- Readability scores

### On-Page SEO
- Title tag issues
- Meta description problems
- Heading structure
- Internal linking gaps

### Schema & Structured Data
- Current implementation
- Validation errors
- Missing opportunities

### Performance
- LCP, INP, CLS scores
- Resource optimization needs
- Third-party script impact

### Images
- Missing alt text
- Oversized images
- Format recommendations

### AI Search Readiness
- Citability score
- Structural improvements
- Authority signals

## Priority Definitions

- **Critical**: Blocks indexing or causes penalties (fix immediately)
- **High**: Significantly impacts rankings (fix within 1 week)
- **Medium**: Optimization opportunity (fix within 1 month)
- **Low**: Nice to have (backlog)

## DataForSEO Integration (Optional)

If DataForSEO MCP tools are available, spawn the `seo-dataforseo` agent alongside existing subagents to enrich the audit with live data: real SERP positions, backlink profiles with spam scores, on-page analysis (Lighthouse), business listings, and AI visibility checks (ChatGPT scraper, LLM mentions).

## Google API Integration (Optional)

If Google API credentials are configured (`claude-seo run google_auth.py --check`), spawn the `seo-google` agent to enrich the audit with real Google field data: CrUX Core Web Vitals (replaces lab-only estimates), GSC URL indexation status, search performance (clicks, impressions, CTR), and GA4 organic traffic trends. The Performance (CWV) category score benefits most from field data.

## Error Handling

| Scenario | Action |
|----------|--------|
| URL unreachable (DNS failure, connection refused) | Report the error clearly. Do not guess site content. Suggest the user verify the URL and try again. |
| robots.txt blocks crawling | Report which paths are blocked. Analyze only accessible pages and note the limitation in the report. |
| Rate limiting (429 responses) | Back off and reduce concurrent requests. Report partial results with a note on which sections could not be completed. |
| Timeout on large sites (500+ pages) | Cap the crawl at the timeout limit. Report findings for pages crawled and estimate total site scope. |