Semrush Research logo

Semrush Research

Organization
OpenClaudia
semrush-research

SEO and competitive intelligence via the SemRush API. Use when asked to research competitors, analyze domains, find keyword opportunities, check backlinks, or estimate traffic. Trigger phrases: "competitor analysis", "domain overview", "keyword research", "backlink check", "traffic estimate", "SEO intelligence", "semrush", "competitive research".

Overview

PublisherOpenClaudia
Repositoryopenclaudia-skills
Skill namesemrush-research
Stars
714
Forks
60
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by OpenClaudia on GitHub. Read the source before you install it.

Installation

Install the Semrush Research AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/semrush-research
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git /tmp/openclaudia-skills
mkdir -p .claude/skills
cp -r /tmp/openclaudia-skills/skills/semrush-research .claude/skills/semrush-research
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Semrush Research in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Semrush Research on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Semrush Research is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SemRush Research

Pull live SEO and competitive intelligence data from the SemRush API.

Prerequisites

Requires SEMRUSH_API_KEY set in .env, .env.local, or ~/.claude/.env.global.

bash
# Verify the key is available
echo "SEMRUSH_API_KEY is ${SEMRUSH_API_KEY:+set}"

If the key is not set, instruct the user:

You need a SemRush API key. Get one at https://www.semrush.com/api/ Then add SEMRUSH_API_KEY=your_key to your .env file.

API Base

All requests go to https://api.semrush.com/ with the API key passed as &key={SEMRUSH_API_KEY}.

Responses are semicolon-delimited CSV. The first line is the header row. Parse accordingly.


1. Domain Overview

Get a high-level snapshot of any domain's organic and paid search performance.

Endpoint

https://api.semrush.com/?type=domain_ranks&key={KEY}&export_columns=Dn,Rk,Or,Ot,Oc,Ad,At,Ac&domain={domain}

Export Columns

ColumnMeaning
DnDomain
RkSemRush Rank
OrOrganic keywords count
OtOrganic traffic estimate
OcOrganic traffic cost ($)
AdPaid keywords count
AtPaid traffic estimate
AcPaid traffic cost ($)

Example curl

bash
curl -s "https://api.semrush.com/?type=domain_ranks&key=${SEMRUSH_API_KEY}&export_columns=Dn,Rk,Or,Ot,Oc,Ad,At,Ac&domain=example.com"

Parsing the Response

bash
# Response format (semicolon-delimited):
# Dn;Rk;Or;Ot;Oc;Ad;At;Ac
# example.com;12345;8234;145000;234500;120;3400;5600

# Parse with awk
curl -s "..." | awk -F';' 'NR==2 {
  printf "Domain: %s\nSemRush Rank: %s\nOrganic Keywords: %s\nOrganic Traffic: %s\nOrganic Traffic Cost: $%s\nPaid Keywords: %s\nPaid Traffic: %s\nPaid Traffic Cost: $%s\n",
  $1,$2,$3,$4,$5,$6,$7,$8
}'

2. Keyword Overview

Get search volume, CPC, competition, and SERP features for a keyword.

Endpoint

https://api.semrush.com/?type=phrase_all&key={KEY}&phrase={keyword}&database=us&export_columns=Ph,Nq,Cp,Co,Nr,Td

Export Columns

ColumnMeaning
PhKeyword phrase
NqSearch volume (monthly)
CpCPC (USD)
CoCompetition (0-1)
NrNumber of results
TdTrend (12 months, comma-separated)

Example curl

bash
curl -s "https://api.semrush.com/?type=phrase_all&key=${SEMRUSH_API_KEY}&phrase=content+marketing&database=us&export_columns=Ph,Nq,Cp,Co,Nr,Td"

Supported Databases

Use &database=XX where XX is: us, uk, ca, au, de, fr, es, it, br, in, jp.


3. Related Keywords

Find semantically related keywords for content planning and gap analysis.

Endpoint

https://api.semrush.com/?type=phrase_related&key={KEY}&phrase={keyword}&database=us&export_columns=Ph,Nq,Cp,Co,Nr,Td&display_limit=20

Example curl

bash
curl -s "https://api.semrush.com/?type=phrase_related&key=${SEMRUSH_API_KEY}&phrase=project+management&database=us&export_columns=Ph,Nq,Cp,Co,Nr,Td&display_limit=20"

Parsing Multiple Rows

bash
curl -s "..." | awk -F';' 'NR>1 { printf "%-40s Vol: %-8s CPC: $%-6s Comp: %s\n", $1, $2, $3, $4 }'

4. Keyword Difficulty

Estimate how hard it is to rank for a keyword.

Endpoint

https://api.semrush.com/?type=phrase_kdi&key={KEY}&phrase={keyword}&database=us&export_columns=Ph,Kd
ColumnMeaning
PhKeyword
KdKeyword difficulty (0-100)

Interpretation:

  • 0-29: Easy - achievable with quality content
  • 30-49: Moderate - needs solid content + some backlinks
  • 50-69: Hard - needs strong domain authority + backlinks
  • 70-84: Very hard - requires established authority
  • 85-100: Extremely hard - dominated by top-tier domains

5. Domain Organic Keywords

See which keywords a domain ranks for organically.

Endpoint

https://api.semrush.com/?type=domain_organic&key={KEY}&domain={domain}&database=us&export_columns=Ph,Po,Nq,Cp,Url,Tr,Tc&display_limit=50&display_sort=tr_desc
ColumnMeaning
PhKeyword
PoPosition
NqSearch volume
CpCPC
UrlRanking URL
TrTraffic (%)
TcTraffic cost

Example curl

bash
curl -s "https://api.semrush.com/?type=domain_organic&key=${SEMRUSH_API_KEY}&domain=hubspot.com&database=us&export_columns=Ph,Po,Nq,Cp,Url,Tr,Tc&display_limit=20&display_sort=tr_desc"

6. Backlink Overview

Get a summary of a domain's backlink profile.

Endpoint

https://api.semrush.com/analytics/v1/?key={KEY}&type=backlinks_overview&target={domain}&target_type=root_domain&export_columns=total,domains_num,urls_num,ips_num,follows_num,nofollows_num,texts_num,images_num

Example curl

bash
curl -s "https://api.semrush.com/analytics/v1/?key=${SEMRUSH_API_KEY}&type=backlinks_overview&target=example.com&target_type=root_domain&export_columns=total,domains_num,urls_num,ips_num,follows_num,nofollows_num,texts_num,images_num"

7. Competitor Discovery

Find domains competing for the same organic keywords.

Endpoint

https://api.semrush.com/?type=domain_organic_organic&key={KEY}&domain={domain}&database=us&export_columns=Dn,Cr,Np,Or,Ot,Oc,Ad&display_limit=10
ColumnMeaning
DnCompetitor domain
CrCompetition level
NpCommon keywords
OrOrganic keywords
OtOrganic traffic
OcOrganic traffic cost
AdPaid keywords

Example curl

bash
curl -s "https://api.semrush.com/?type=domain_organic_organic&key=${SEMRUSH_API_KEY}&domain=notion.so&database=us&export_columns=Dn,Cr,Np,Or,Ot,Oc,Ad&display_limit=10"

8. Traffic Analytics (Estimates)

Estimate a domain's overall traffic sources and engagement.

Endpoint

https://api.semrush.com/analytics/ta/api/v3/summary?key={KEY}&targets={domain}&display_date=2024-01-01&country=us&export_columns=target,visits,users,bounce_rate,pages_per_visit,avg_visit_duration

Workflow: Full Competitive Analysis

When the user asks for a full competitive analysis, run these steps in order:

  1. Domain Overview - Get the target domain's metrics
  2. Competitor Discovery - Find top 5-10 competitors
  3. Domain Overview for each competitor - Compare metrics
  4. Top Keywords for each domain - Find keyword gaps
  5. Backlink Overview for each domain - Compare link profiles

Output Format

Present results as a comparison table:

| Metric              | target.com | competitor1.com | competitor2.com |
|---------------------|-----------|-----------------|-----------------|
| SemRush Rank        | ...       | ...             | ...             |
| Organic Keywords    | ...       | ...             | ...             |
| Organic Traffic     | ...       | ...             | ...             |
| Traffic Cost        | ...       | ...             | ...             |
| Backlinks           | ...       | ...             | ...             |
| Referring Domains   | ...       | ...             | ...             |

Then highlight:

  • Keyword gaps: Keywords competitors rank for but target does not
  • Quick wins: Keywords where target ranks positions 5-20 (improvement opportunities)
  • Content gaps: Topics competitors cover but target does not
  • Backlink opportunities: Sites linking to competitors but not target

Rate Limits and Costs

  • Each API call costs API units (check your plan)
  • Use &display_limit= to control result count (default varies by endpoint)
  • Cache results locally when doing multi-step analysis to avoid redundant calls
  • Domain overview calls are cheapest; backlink and traffic analytics cost more

Error Handling

ErrorMeaning
ERROR 50 :: NOTHING FOUNDNo data for this query
ERROR 120 :: WRONG KEYInvalid API key
ERROR 130 :: LIMIT EXCEEDEDAPI unit limit reached
Empty responseUsually means no data available for the query parameters

When you get "NOTHING FOUND", try:

  • Different database (e.g., uk instead of us)
  • Root domain instead of subdomain
  • Broader keyword phrase

Frequently asked questions

What does the Semrush Research AI skill do?

SEO and competitive intelligence via the SemRush API. Use when asked to research competitors, analyze domains, find keyword opportunities, check backlinks, or estimate traffic. Trigger phrases: "competitor analysis", "domain overview", "keyword research", "backlink check", "traffic estimate", "SEO intelligence", "semrush", "competitive research".

Why use Semrush Research on TypingMind?

Because you install it once and use it with any model. Semrush Research is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Semrush Research in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/semrush-research. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Semrush Research?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Semrush Research?

As many as you like. As long as a model supports skills, you can use Semrush Research with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Semrush Research AI skill free?

Yes. It is published on GitHub by OpenClaudia under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇