Agent skill

Backlink Audit via DataForSEO

by zubair-trabzada in zubair-trabzada/dataforseo-claude

Audits a domain's backlink profile with the DataForSEO Backlinks API and reports referring domains, anchor text, dofollow ratio and a toxicity assessment.

MITAuto-check: notesMarketing & SEO

Install Backlink Audit via DataForSEO

skills CLI
$ npx skills add zubair-trabzada/dataforseo-claude --skill seo-backlinks -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zubair-trabzada/dataforseo-claude seo-backlinks --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zubair-trabzada/dataforseo-claude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/seo-backlinks .claude/skills/seo-backlinks && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
seo-backlinks
GitHub stars
165
Token cost
~1k tokens
SKILL.md length
373 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

Audits a domain's backlink profile with the DataForSEO Backlinks API and reports referring domains, anchor text, dofollow ratio and a toxicity assessment.

  • Works in 7 steps: Parse login: and password: from their… → Write them to ~/.claude/skills/seo/.env → chmod 600 ~/.claude/skills/seo/.env → …
  • Auditing a site's backlink profile before an SEO campaign
  • SKILL.md covers Phase 0: Credential Preflight…, Run, What to evaluate and Authority Score (0-100), plus 1 more section
  • Needs DATAFORSEO_PASSWORD

What it does

The skill makes three calls through helper scripts in `~/.claude/skills/seo/scripts/`: a summary, referring domains and anchors. The report covers total backlinks and referring domains, top referring domains by authority, top anchors with over-optimization flags, and a toxicity assessment with an Authority Score from 0 to 100. According to the skill, one run costs about 3 to 5 cents of DataForSEO credit.

A credential preflight runs first. If DataForSEO login details are missing, the agent shows a setup wizard, asks you to paste your API login and API password, stores them in a local `.env` file with restricted permissions, and checks them with a test call. It is told never to echo or commit them. The evaluation then looks at volume and freshness (new and lost links over 30 and 90 days), quality (dofollow ratio, domain rank mix, TLD spread, IP diversity as a private-network warning sign) and anchor text. The excerpt ends within the anchor section.

When your agent uses it

  • Auditing a site's backlink profile before an SEO campaign
  • Spotting over-optimized anchor text or a suspicious link mix
  • Checking whether new and lost backlinks are trending up or down

Example prompts

  • “Run a backlink audit on example.com.”
  • “How healthy is the anchor text profile for mystore.com? Flag any over-optimization.”
  • “Which referring domains carry the most authority for acme.io, and are there toxic links?”

Requirements

  • A DataForSEO account with an API login and password
  • The shared seo skill scripts installed in `~/.claude/skills/seo/`
  • Network access to the DataForSEO API
  • Pre-approved tools (allowed-tools): Bash, Write

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. Parse login: and password: from their message.
  2. Write them to ~/.claude/skills/seo/.env
  3. chmod 600 ~/.claude/skills/seo/.env
  4. Run a verification call: ~/.claude/skills/seo/scripts/keyword_research.py volume "test"
  5. If verification succeeds (real JSON returned): tell the user "✅ Credentials verified. Running your command now..." and proceed with the…
  6. If status 40104 — Please verify your account: tell the user to verify their account at https://app.dataforseo.com/, then say "continue" to…
  7. If any other auth error: ask them to double-check the API password (the long alphanumeric string from…

What it can do on your machine

Read from SKILL.md and the folder at commit 67ac4f0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash
    • Write

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • dataforseo.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • DATAFORSEO_PASSWORD

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Backlink Audit via DataForSEO loads about 1k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 373 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~67
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:29
    2. Write them to `~/.claude/skills/seo/.env`:
  • NoteMentions a .env fileSKILL.md:34
    3. `chmod 600 ~/.claude/skills/seo/.env`
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Write

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zubair-trabzada/dataforseo-claude at commit 67ac4f0, republished under its MIT licence (© zubair-trabzada). 373 words, ~1,018 tokens.

Download SKILL.mdSave it as .claude/skills/seo-backlinks/SKILL.md (or your agent's skills folder).
name
seo-backlinks
description
Backlink profile audit via the DataForSEO Backlinks API. Returns total backlinks, referring domains, dofollow ratio, top anchors with over-optimization flags, top referring domains by authority, and a toxicity assessment with an Authority Score (0-100).
allowed-tools
Bash, Write

Phase 0: Credential Preflight (REQUIRED — run BEFORE anything else)

Before running any of the steps below, always invoke the shared preflight check:

bash
~/.claude/skills/seo/scripts/preflight.sh

If exit code is 0: credentials are configured — proceed with the rest of this skill silently.

If exit code is 2: the script prints the DataForSEO setup wizard to stdout. STOP, display that wizard to the user verbatim, and wait for them to paste credentials in this format:

login: their_email@example.com
password: their_api_password_here

When they reply:

  1. Parse login: and password: from their message.
  2. Write them to ~/.claude/skills/seo/.env:
    DATAFORSEO_LOGIN=<login>
    DATAFORSEO_PASSWORD=<password>
  3. chmod 600 ~/.claude/skills/seo/.env
  4. Run a verification call: ~/.claude/skills/seo/scripts/keyword_research.py volume "test"
  5. If verification succeeds (real JSON returned): tell the user "✅ Credentials verified. Running your command now..." and proceed with the original request.
  6. If status 40104 — Please verify your account: tell the user to verify their account at https://app.dataforseo.com/, then say "continue" to retry.
  7. If any other auth error: ask them to double-check the API password (the long alphanumeric string from https://app.dataforseo.com/api-access — not their account login password).

Never echo credentials back to the user, never include them in tool output, and never commit them.


Powered by: DataForSEO API — Backlinks summary + referring_domains + anchors + domain_intersection. Cost: ~$0.03-0.05 per run.

Run

Three calls, parallel:

bash
~/.claude/skills/seo/scripts/backlinks.py summary --target <domain>
~/.claude/skills/seo/scripts/backlinks.py refdomains --target <domain> --limit 100
~/.claude/skills/seo/scripts/backlinks.py anchors --target <domain> --limit 50

What to evaluate

Volume & freshness
  • Total backlinks, total referring domains
  • New backlinks in last 30/90 days
  • Lost backlinks in last 30/90 days
  • Trend: growing, stable, declining
Show full SKILL.md (144 more words)Show less
Quality
  • Dofollow ratio (50-80% is healthy; >95% looks artificial)
  • Domain rank distribution of referring sites (mostly low-rank domains = weak profile)
  • TLD distribution (.edu / .gov / .org weight more)
  • IP / subnet diversity (PBN red flag if all same C-class)
Anchor text
  • Top 10 anchors by frequency
  • Branded anchor share — should be 40-60% for a healthy profile
    • <30% looks unnatural
    • 80% means few topical links

  • Exact-match anchor share — should be < 10%
    • 20% = over-optimization, manual penalty risk

Toxicity flags
  • High share of links from low-rank domains (rank < 50)
  • Sudden spike in backlinks (possible negative SEO)
  • Anchor text patterns suggesting paid links
  • Adult / gambling / pharma TLDs in referring domains

Authority Score (0-100)

SignalWeight
log10(referring_domains) scaled to 0-3030%
Domain rank percentile25%
Anchor naturalness (penalty for >20% exact-match)15%
Dofollow ratio in healthy band (50-80%)10%
TLD/IP diversity10%
Toxicity penalty (negative)up to -10%

Return JSON shape

json
{
  "authority_score": 68,
  "backlink_summary": {
    "backlinks": 12345, "referring_domains": 432,
    "dofollow_pct": 67, "broken_backlinks": 12,
    "new_30d": 18, "lost_30d": 5
  },
  "top_referrers": [{"domain": "...", "rank": 612, "backlinks": 24, "dofollow": true}],
  "anchor_distribution": {
    "branded": 0.51, "exact_match": 0.08, "partial_match": 0.18,
    "naked_url": 0.12, "generic": 0.11
  },
  "toxicity_flags": ["..."]
}

© zubair-trabzada, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/seo-backlinks of zubair-trabzada/dataforseo-claude.

Open the folder on GitHubat commit 67ac4f0

Compare with similar skills

Backlink Audit via DataForSEO next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Backlink Audit via DataForSEO compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Backlink Audit via DataForSEO this skillzubair-trabzada/dataforseo-claude165—~1kAutomated safety check: NotesMIT
FLOW SEO FrameworkAgriciDaniel/claude-seo19k2 repos~1.4kAutomated safety check: PassMIT
Roblox Homepage Ranking Auditorkennyzir/7deer_skills322—~3.8kAutomated safety check: PassMIT
E2E SEO Assistantirinabuht12-oss/marketing-skills4.1k—~1.9kAutomated safety check: PassNone
Global SEO Growthminhnv0807/ai-business-skills609—~5kAutomated safety check: PassMIT
Ahrefs PythonOpenClaudia/openclaudia-skills713—~1.9kAutomated safety check: PassMIT

Similar skills

  • FLOW SEO Framework

    AgriciDaniel/claude-seo

    Brings the FLOW framework's stage-specific SEO prompts into the agent, from keyword discovery through backlinks, on-page work and conversion to local SEO, loaded on demand.

    19k GitHub starsUsed in 2 repos~1.4k tokens
    Marketing & SEOAuto-check passed
  • Roblox Homepage Ranking Auditor

    kennyzir/7deer_skills

    Audit a Roblox or game-site homepage against the RB Auto Golden Homepage model.

    322 GitHub stars~3.8k tokensUpdated 12 days ago
    Marketing & SEOAuto-check passed
  • E2E SEO Assistant

    irinabuht12-oss/marketing-skills

    Full SEO workflow covering technical audits, content gaps, backlink opportunities, on-page fixes, and content briefs.

    4.1k GitHub stars~1.9k tokensUpdated 17 days ago
    Marketing & SEOAuto-check passed
  • Global SEO Growth

    minhnv0807/ai-business-skills

    Covers six SEO layers for a website: crawl and index audit, local SEO, search-intent content, AI search visibility, schema markup and backlink or directory distribution.

    609 GitHub stars~5k tokensUpdated 29 days ago
    Marketing & SEOAuto-check passed
  • Ahrefs Python

    OpenClaudia/openclaudia-skills

    Manages Ahrefs API usage in Python using ahrefs-python library.

    713 GitHub stars~1.9k tokensUpdated today
    Marketing & SEOAuto-check passed
  • Backlink Profile Analysis

    AgriciDaniel/claude-seo

    Analyzes a site's backlink profile, anchor text, toxic links, competitor gaps and disavow candidates, using whichever link data sources are configured.

    19k GitHub stars~3.8k tokensUpdated 6 days ago
    Marketing & SEOAuto-check passed

More from zubair-trabzada/dataforseo-claude

All 16 skills in this repo
  • DataForSEO SEO Toolkit

    zubair-trabzada/dataforseo-claude

    Runs keyword research, rank checks, backlink and competitor analysis, site audits and PDF reports from live Google data through the DataForSEO API.

    165 GitHub stars~3.2k tokensUpdated 4 mo ago
    Auto-check: notes
  • DataForSEO Site Audit

    zubair-trabzada/dataforseo-claude

    Runs a full SEO audit through the DataForSEO API with five parallel subagents and produces a composite 0 to 100 SEO score, an action plan and an audit JSON for PDF export.

    165 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check: notes
  • SEO Domain Comparison

    zubair-trabzada/dataforseo-claude

    Compares two domains side by side with DataForSEO data on traffic, keywords, backlinks, referring domains and keyword overlap, then states which has the stronger position.

    165 GitHub stars~892 tokensUpdated 4 mo ago
    Auto-check: notes
  • SEO Competitor Analysis with DataForSEO

    zubair-trabzada/dataforseo-claude

    Finds a domain's real SEO competitors through DataForSEO Labs, ranked by SERP overlap, with shared keywords, traffic estimates and a 0-100 competitive score.

    165 GitHub stars~957 tokensUpdated 4 mo ago
    Auto-check: notes
  • SEO Content Authority

    zubair-trabzada/dataforseo-claude

    Clusters the keywords a domain ranks for into topics, compares coverage with competitors and returns a content score using DataForSEO data.

    165 GitHub stars~1k tokensUpdated 4 mo ago
    Auto-check: notes
  • SEO Content Gap

    zubair-trabzada/dataforseo-claude

    Find keywords competitors rank for that you don't, via the DataForSEO Labs domainintersection endpoint.

    165 GitHub stars~823 tokensUpdated 4 mo ago
    Auto-check: notes

Categories

Questions about Backlink Audit via DataForSEO

What does Backlink Audit via DataForSEO do?

Audits a domain's backlink profile with the DataForSEO Backlinks API and reports referring domains, anchor text, dofollow ratio and a toxicity assessment. claude/skills/seo/scripts/`: a summary, referring domains and anchors. The report covers total backlinks and referring domains, top referring domains by authority, top anchors with over-optimization flags, and a toxicity assessment with an Authority Score from 0 to 100.

When should I use Backlink Audit via DataForSEO?

Backlink Audit via DataForSEO fits situations like: auditing a site's backlink profile before an SEO campaign; spotting over-optimized anchor text or a suspicious link mix; checking whether new and lost backlinks are trending up or down.

How do I install Backlink Audit via DataForSEO in Claude Code?

Run `npx skills add zubair-trabzada/dataforseo-claude --skill seo-backlinks -a claude-code`. Or copy the skill folder (skills/seo-backlinks in zubair-trabzada/dataforseo-claude) into .claude/skills/seo-backlinks in your project. Claude Code loads it when a task matches its description.

How do I install Backlink Audit via DataForSEO in Codex?

Run `npx skills add zubair-trabzada/dataforseo-claude --skill seo-backlinks -a codex`. Or copy the skill folder (skills/seo-backlinks in zubair-trabzada/dataforseo-claude) into .agents/skills/seo-backlinks in your project. Codex loads it when a task matches its description.

Can I use Backlink Audit via DataForSEO in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zubair-trabzada/dataforseo-claude --skill seo-backlinks -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/seo-backlinks, .gemini/skills/seo-backlinks, .github/skills/seo-backlinks and .opencode/skills/seo-backlinks in your project.

What does Backlink Audit via DataForSEO need to run?

Going by SKILL.md and its folder, Backlink Audit via DataForSEO needs credentials named DATAFORSEO_PASSWORD. Our summary lists: A DataForSEO account with an API login and password; The shared seo skill scripts installed in `~/.claude/skills/seo/`; Network access to the DataForSEO API. Its frontmatter pre-approves these tools: Bash, Write.

Does Backlink Audit via DataForSEO access the network?

SKILL.md names 1 domain. As links in the text: dataforseo.com. This is read from the text; nothing was executed.

Is Backlink Audit via DataForSEO safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file; pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Backlink Audit via DataForSEO use?

Backlink Audit via DataForSEO is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Backlink Audit via DataForSEO use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Backlink Audit via DataForSEO?

Skills that share tags, products or a category with Backlink Audit via DataForSEO: FLOW SEO Framework (AgriciDaniel/claude-seo, 19k stars), Roblox Homepage Ranking Auditor (kennyzir/7deer_skills, 322 stars), E2E SEO Assistant (irinabuht12-oss/marketing-skills, 4.1k stars) and Global SEO Growth (minhnv0807/ai-business-skills, 609 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Backlink Audit via DataForSEO?

zubair-trabzada (a GitHub user) maintains it in zubair-trabzada/dataforseo-claude, which has 165 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on May 20, 2026.

Source: zubair-trabzada/dataforseo-claude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.