Ahrefs Python logo

Ahrefs Python

Organization
OpenClaudia
ahrefs-python

Manages Ahrefs API usage in Python using `ahrefs-python` library. Use when working with SEO / marketing related tasks or with data including backlinks, keywords, domain ratings, organic traffic, site audits, rank tracking, and brand monitoring. Covers `ahrefs-python` usage including AhrefsClient / AsyncAhrefsClient, typed request/response models, error handling, and all API sections.

Overview

PublisherOpenClaudia
Repositoryopenclaudia-skills
Skill nameahrefs-python
Stars
714
Forks
60
Bundled files
2
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.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Ahrefs Python 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/ahrefs-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/ahrefs-research .claude/skills/ahrefs-python
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ahrefs Python 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 Ahrefs Python 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 Ahrefs Python 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.

Ahrefs Python SDK Skill

Overview

The Ahrefs API provides programmatic access to Ahrefs SEO data. The official Python SDK (ahrefs-python) provides typed request and response models for all endpoints, auto-generated from the OpenAPI spec.

Key capabilities:

  • Site Explorer - Backlinks, organic keywords, domain rating, traffic, referring domains
  • Keywords Explorer - Keyword research, volumes, difficulty, related terms
  • Rank Tracker - SERP monitoring, competitor tracking
  • Site Audit - Technical SEO issues, page content, page explorer
  • Brand Radar - AI brand mentions, share of voice, impressions
  • SERP Overview - Search result analysis
  • Batch Analysis - Bulk domain/URL metrics via POST

Installation

sh
pip3 install git+https://github.com/ahrefs/ahrefs-python.git

Requires Python 3.11+. Dependencies: httpx, pydantic.

API Method Discovery

The SDK has 52 methods across 7 API sections. The built-in search tool is the fastest way to find the right method — it returns matching method signatures, parameters, and return types directly, so there's no need to scan through a large reference.

Python (preferred when already in a Python context):

python
from ahrefs.search import search_api_methods

# Returns formatted text with method signatures, parameters, and return types
print(search_api_methods("domain rating"))

# Filter by API section and limit results
print(search_api_methods("backlinks", section="site-explorer", limit=3))

CLI (preferred when exploring from the terminal):

sh
# Ensure python3 points to the interpreter where ahrefs-python is installed:
#   which python3
#   python3 -c "import ahrefs"
python3 -m ahrefs.api_search "domain rating"
python3 -m ahrefs.api_search "backlinks" --section site-explorer --limit 3
python3 -m ahrefs.api_search "batch" --json
python3 -m ahrefs.api_search --sections  # list all API sections

IMPORTANT RULES

  • ALWAYS use the ahrefs-python SDK. DO NOT make raw httpx/requests calls to the Ahrefs API.
  • ALWAYS pass dates as strings in YYYY-MM-DD format (e.g. "2025-01-15").
  • ALWAYS use select on list endpoints to request only the columns you need. List endpoints return all columns by default, which wastes API units and increases response size.
  • USE context managers (with / async with) for client lifecycle management.
  • NEVER hardcode API keys in source code. Use the AHREFS_API_KEY environment variable or your preferred secrets mechanism.
  • The client handles retries (429, 5xx, connection errors) automatically. DO NOT implement your own retry logic on top of the SDK.

Quick Start

python
import os
from ahrefs import AhrefsClient

with AhrefsClient(api_key=os.environ["AHREFS_API_KEY"]) as client:
    data = client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15")
    print(data.domain_rating)  # 91.0
    print(data.ahrefs_rank)    # 3

SDK Patterns

Client Setup

python
import os
import ahrefs

with ahrefs.AhrefsClient(
    api_key=os.environ["AHREFS_API_KEY"],  # or any secrets source
    base_url="...",          # override API base URL (default: https://api.ahrefs.com/v3)
    timeout=30.0,            # request timeout in seconds (default: 60)
    max_retries=3,           # retries on transient errors (default: 2)
) as client:
    ...

Async client:

python
import os
from ahrefs import AsyncAhrefsClient

async with AsyncAhrefsClient(api_key=os.environ["AHREFS_API_KEY"]) as client:
    data = await client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15")

For parallel calls, use asyncio.gather:

python
import asyncio

async with AsyncAhrefsClient(api_key=os.environ["AHREFS_API_KEY"]) as client:
    dr_ahrefs, dr_moz = await asyncio.gather(
        client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15"),
        client.site_explorer_domain_rating(target="moz.com", date="2025-01-15"),
    )

Calling Methods

Two calling styles -- both are equivalent:

python
# Keyword arguments (recommended)
data = client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15")

# Request objects (full type safety)
from ahrefs.types import SiteExplorerDomainRatingRequest
request = SiteExplorerDomainRatingRequest(target="ahrefs.com", date="2025-01-15")
data = client.site_explorer_domain_rating(request)

Method names follow {api_section}_{endpoint}, e.g. site_explorer_organic_keywords, keywords_explorer_overview.

Responses

Methods return typed Data objects directly.

Scalar endpoints return a single data object (or None):

python
data = client.site_explorer_domain_rating(target="ahrefs.com", date="2025-01-15")
print(data.domain_rating)

List endpoints return a list of data objects. There is no pagination — set limit to the number of results you need. Use select to request only the columns you need:

python
items = client.site_explorer_organic_keywords(
    target="ahrefs.com",
    date="2025-01-15",
    select="keyword,volume,best_position",
    order_by="volume:desc",
    limit=10,
)
for item in items:
    print(item.keyword, item.volume, item.best_position)

Error Handling

python
import ahrefs

try:
    data = client.site_explorer_domain_rating(target="example.com", date="2025-01-15")
except ahrefs.AuthenticationError:    # 401
    ...
except ahrefs.RateLimitError as e:    # 429 -- e.retry_after has the delay
    ...
except ahrefs.NotFoundError:          # 404
    ...
except ahrefs.APIError as e:          # other 4xx/5xx -- e.status_code, e.response_body
    ...
except ahrefs.APIConnectionError:     # network / timeout
    ...

All exceptions inherit from ahrefs.AhrefsError.

Common Parameters

Most list endpoints share these parameters:

ParameterTypeDescription
targetstrDomain, URL, or path to analyze
datestrDate in YYYY-MM-DD format
date_from / date_tostrDate range for history endpoints
countrystrTwo-letter country code (ISO 3166-1 alpha-2)
selectstrComma-separated columns to return
wherestrFilter expression
order_bystrColumn and direction, e.g. "volume:desc"
limitintMax results to return

Parameters typed as enums in the API reference (CountryEnum, VolumeModeEnum, etc.) accept plain strings — pass country="us" not CountryEnum("us").

The where parameter takes a JSON string. Use json.dumps() to build it:

python
import json
where = json.dumps({"field": "volume", "is": ["gte", 1000]})
items = client.site_explorer_organic_keywords(
    target="ahrefs.com", date="2025-01-15",
    select="keyword,volume", where=where,
)

For full filter syntax (boolean combinators, operators, nested fields), see references/filter-syntax.md.

API Methods

Use search_api_methods("query") or python3 -m ahrefs.api_search "query" to find methods by keyword. Search covers all 52 methods across 7 API sections and returns complete signatures, parameters, and response fields.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Ahrefs Python AI skill do?

Manages Ahrefs API usage in Python using `ahrefs-python` library. Use when working with SEO / marketing related tasks or with data including backlinks, keywords, domain ratings, organic traffic, site audits, rank tracking, and brand monitoring. Covers `ahrefs-python` usage including AhrefsClient / AsyncAhrefsClient, typed request/response models, error handling, and all API sections.

Why use Ahrefs Python on TypingMind?

Because you install it once and use it with any model. Ahrefs Python 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 Ahrefs Python in TypingMind?

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

Which AI models can use Ahrefs Python?

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 Ahrefs Python?

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

Is the Ahrefs Python 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 👇