mcpbeat Sign in

Algo SEO Content Agent Skill

Execute content SEO strategy from keyword research through content planning, writing, and on-page optimization. Use this skill when the user needs to create SEO-optimized content, perform keyword research, identify content gaps, or improve existing content rankings — even if they say 'content strategy', 'keyword research', or 'how to rank for this topic'.

7k tokens
context cost
the whole folder, loaded on every use
4
files
instructions only
0
copies elsewhere
how many repositories repackaged it
223
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/asgard-ai-platform/skills --skill algo-seo-content

What comes with it

24 051 bytes besides the instruction
examples/sample_scenario.md
references/content-brief-template.md
references/keyword-clustering.md

The instruction itself

14 sections, as written by the author

Content SEO Strategy

Overview

Content SEO is the systematic process of creating and optimizing content to match search intent and rank organically. The pipeline: keyword research → intent mapping → content creation → on-page optimization → performance monitoring. Success depends on intent match, not keyword density.

When to Use

Trigger conditions:

  • Planning new content to capture organic search traffic
  • Optimizing existing underperforming content
  • Conducting keyword research and content gap analysis

When NOT to use:

  • When the issue is technical (page speed, crawlability) — use technical SEO
  • When the issue is off-page (backlinks, authority) — use backlink analysis

Algorithm

IRON LAW: Content Must Match SEARCH INTENT
A perfectly optimized page targeting the wrong intent will NOT rank.
Four intent types:
1. Informational — wants to learn ("how to", "what is")
2. Navigational — wants a specific site ("github login")
3. Commercial — comparing options ("best CRM 2025")
4. Transactional — wants to buy/do ("buy iPhone 16 case")
Check SERP results to determine actual intent before writing.

Phase 1: Input Validation

Define target topic/niche. Gather seed keywords from brainstorming, competitor analysis, and tools (Ahrefs, SEMrush, Google Keyword Planner).

Gate: Seed keyword list with search volume and difficulty estimates.

Phase 2: Core Algorithm

  • Keyword clustering: Group related keywords by intent and topic
  • SERP analysis: Check top 10 results for each cluster — identify intent, content format, and depth
  • Content gap analysis: Find keywords competitors rank for that you don't
  • Content brief: Define: target keyword, intent, format (guide/list/comparison), word count benchmark, required subtopics from SERP analysis
  • On-page optimization: Title tag (keyword front-loaded), meta description, H1/H2 structure, internal links, image alt text

Phase 3: Verification

Check: title contains primary keyword, intent matches SERP, all key subtopics covered, internal links to related content.

Gate: Content matches identified intent and covers SERP-derived subtopics.

Phase 4: Output

Return content brief and optimization checklist.

Output Format

{
  "content_brief": {"primary_keyword": "...", "intent": "informational", "format": "how-to guide", "target_word_count": 2000, "subtopics": ["...", "..."]},
  "optimization": {"title": "...", "meta_description": "...", "h2_structure": ["...", "..."], "internal_links": 5},
  "metadata": {"search_volume": 2400, "keyword_difficulty": 35}
}

Examples

Sample I/O

Input: Topic "email marketing automation", target market: Taiwan SMBs

Expected: Primary KW: "email行銷自動化", intent: commercial investigation, format: comparison guide, 2500 words

Edge Cases

| Input | Expected | Why |

|-------|----------|-----|

| Zero search volume keyword | Consider if it's emerging or nonexistent | May be worth targeting if topically relevant |

| KD > 80 for new site | Target long-tail variants first | New sites can't compete on high-KD terms |

| Mixed intent SERP | Create content matching dominant intent | Don't try to serve all intents in one page |

Gotchas

  • Keyword density is dead: There's no optimal keyword density. Write naturally. Forced keyword insertion hurts readability and may trigger spam signals.
  • Search volume ≠ traffic: A #1 ranking for a 10K volume keyword won't bring 10K visits. Click-through rates vary by SERP features (ads, featured snippets, PAA).
  • Content freshness: Some queries demand fresh content (e.g., "best laptop 2025"). Outdated content drops rankings even if it once ranked #1.
  • Cannibalization: Multiple pages targeting the same keyword compete with each other. One strong page outperforms three mediocre ones.
  • E-E-A-T: For YMYL topics (health, finance), Google requires demonstrated Experience, Expertise, Authority, and Trust. Anonymous content won't rank.

References

  • For keyword clustering methodology, see references/keyword-clustering.md
  • For content brief templates, see references/content-brief-template.md

Other skills for the same job

different authors, same section of the catalogue
Internal Comms
by anthropics
vendor ×13

A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).

6k tokens
Competitive Ads Extractor
by frostant
×10

Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.

2k tokens
Lead Research Assistant
by frostant
×8

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

2k tokens
Developer Growth Analysis
by frostant
×6

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

4k tokens
App Store Optimization
by alirezarezvani
×3

Complete App Store Optimization (ASO) toolkit for researching, optimizing, and tracking mobile app performance on Apple App Store and Google Play Store

55k tokens scripts
Deeptools
by christophacham
×3

NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.

21k tokens scripts
Pymatgen
by christophacham
×3

Materials science toolkit. Crystal structures (CIF, POSCAR), phase diagrams, band structure, DOS, Materials Project integration, format conversion, for computational materials science.

26k tokens scripts
Enhance Prompt
by google-labs-code
vendor ×2

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

3k tokens

How to use it

Copy the folder

Take asgard-ai-platform/algo-seo-content from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.