/seo-research

name: seo-research
description: Data-driven SEO research and analysis through the Hyper MCP — keyword research, competitor analysis, content planning, AI search visibility (ChatGPT, Claude, Perplexity, Google AI Overviews), backlink trends, search intent classification, page speed / Core Web Vitals, and full site audits. Use when the user asks for an SEO audit, keyword research, content strategy, competitor benchmarks, brand visibility in AI search, ranking history, or any organic search analysis.
requires_toolkits:
  - hyperseo
icon: hyperseo
short_description: Keyword research, SERP and AI-visibility analysis, competitor benchmarking, and site audits.

SEO Research

Data-driven SEO research and analysis. Every recommendation must be backed by real data from the HyperSEO tools exposed by the Hyper MCP. Never guess metrics, never assume rankings, never recommend without evidence.

Out of scope — defer to other skills

| Request | Send them to | | --- | --- | | Google Ads campaign creation | `google-ads` | | Meta (Facebook / Instagram) ads | `meta-ads` | | Competitor *ad* research from the Meta Ads Library | `meta-ads-library` | | Pinterest Ads campaign | `pinterest-ads` | | Write the blog post itself | `blog-generation` | | Competitor monitoring, battle cards, non-SEO surfaces | `competitor-intel` | | Organic Instagram / TikTok / LinkedIn publishing | `instagram`, `tiktok`, `linkedin` |

Requirements

• **Hyper MCP installed and connected.** [https://app.hyperfx.ai/mcp](https://app.hyperfx.ai/mcp)
• **HyperSEO toolkit enabled** at [https://app.hyperfx.ai/apps](https://app.hyperfx.ai/apps) — provides the `hyperseo_*` tool surface that wraps DataForSEO and AI search query data.

If `hyperseo_search_volume_get` is not found, the toolkit to enable is HyperSEO (`hyperseo`).

How to run the tools in this skill

Every tool in this skill is named by its canonical tool name. Run it with the call your surface gives you:

| Surface | Find a tool | Run it | | --- | --- | --- | | Hyper chat | Call the tool by its name; `search_tools(queries=["<provider> <action>"])` shows its parameters | `<name>(...)` | | MCP client (Claude, Cursor, Codex, ChatGPT) | `search("<what you want to do>")`, then `describe("<name>")` | `call_read("<name>", {...})`, `call_write` or `call_destructive`: the one that `describe` names in `call_with` | | Hyper CLI | `hyperai search "<what you want to do>"`, then `hyperai describe <name>` | `hyperai call <name> --json '{...}'` |

If a tool is not found: in Hyper chat, find its toolkit id with `discover_toolkits` and pass it to `enable_toolkit`. On an MCP client or the CLI, tell the user which integration to connect in Hyper.

Tool surface

| Tool group | Tools | | --- | --- | | Keyword research | `hyperseo_search_volume_get`, `hyperseo_keyword_difficulty_get`, `hyperseo_keyword_ideas_generate`, `hyperseo_site_keywords_search`, `hyperseo_intents_search` | | SERP & Google AI Mode | `hyperseo_serp_results_get`, `hyperseo_ai_overviews_get` | | Competitor analysis | `hyperseo_competitors_search`, `hyperseo_competitor_domains_search`, `hyperseo_domain_intersections_search`, `hyperseo_traffic_get_bulk` | | Domain & rankings | `hyperseo_domain_overview_get`, `hyperseo_domain_keywords_get`, `hyperseo_rank_history_get` | | Backlinks | `hyperseo_backlinks_history_get` | | AI search visibility | `hyperseo_ai_search_volume_get`, `hyperseo_mentions_track` | | Technical health | `hyperseo_pagespeed_get` |

Initial Assessment

Before running any tools, understand what the user actually needs:

1. **What is the goal?** Are they researching keywords, auditing a site, planning content, analyzing competitors, or checking AI visibility? 2. **What is the domain / business?** Get the actual domain. Don't infer it. 3. **What is the target market?** Default to US (location code `2840`) unless told otherwise. 4. **What is the current state?** Are they starting from scratch or optimizing existing content?

Based on the answers, read the appropriate reference file:

| User need | Reference | | --- | --- | | "Find keywords for…" / "What should I target?" | [`references/keyword-research.md`](./references/keyword-research.md) | | "Who are my competitors?" / "Analyze [domain]" | [`references/competitor-analysis.md`](./references/competitor-analysis.md) | | "What should I write about?" / "Content plan" | [`references/content-seo-planning.md`](./references/content-seo-planning.md) | | "Am I visible in AI search?" / "Track my brand in ChatGPT" | [`references/ai-search-optimization.md`](./references/ai-search-optimization.md) | | "Audit my site" / "How is my domain doing?" | [`references/site-audit.md`](./references/site-audit.md) |

When the task spans multiple areas (e.g., "help me with SEO for my new site"), each area is its own step: run the site audit with `references/site-audit.md` first and give its findings. Read the file of the next area, keyword research and then content planning, only when the user goes on to it.

Core SEO Principles

Apply these throughout all analysis.

**Search intent comes first.** Every keyword has an intent. Use `hyperseo_intents_search` to classify at scale, then match content format to intent:

• Informational ("what is X") → guides, explainers.
• Commercial ("best X", "X vs Y") → comparison pages, reviews.
• Transactional ("buy X", "X pricing") → product / landing pages.
• Navigational ("X login") → not targetable by others.

**E-E-A-T matters.** Experience, Expertise, Authoritativeness, Trustworthiness. Google evaluates content quality. Recommend content strategies that demonstrate genuine expertise, not keyword-stuffed filler.

**Topic authority over individual keywords.** Ranking for one keyword in isolation is hard. Recommend topic clusters: a pillar page supported by related content that builds topical authority.

**AI search is a separate channel.** Traditional Google search volume and AI-chatbot query volume are different metrics measuring dif