mikefutia/seo-consultant/backlinks

Claude Code and agent skill by mikefutia/seo-consultant

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Flag toxic backlinks for review and rank outreach targets by DR × relevance, from Ahrefs MCP or CSV exports. Trigger on "backlinks", "toxic links", "link cleanup", "outreach targets", or /seo-os:backlinks.

Install

npx vskill@latest install mikefutia/seo-consultant/backlinks

SKILL.md

Backlink Cleanup + Outreach

Ahrefs data → action list. Three outputs: FLAG, PROTECT, PURSUE.

Data source (in order of preference)

  1. Ahrefs MCP if connected (every Ahrefs plan from Lite up includes it)
  2. CSVs in data/ahrefs/: backlinks, referring-domains, and optionally competitors' referring domains
  3. Neither → stop and tell the user exactly which Ahrefs export screens to use. Never analyze imaginary backlinks.

Process

  1. FLAG — links matching toxic patterns: DR < 5 sitewide footers, exact-match commercial anchors at unnatural rates, link-network footprints (same subnet/IP clusters), irrelevant foreign-language directories. Each flag shows the evidence.
  2. PROTECT — the 20 most valuable links by DR × topical relevance. These define what outreach should replicate.
  3. PURSUE — domains linking to competitors (from CLAUDE.md or user input) but not this site, ranked by DR × relevance, each with a one-line "why they'd link" angle.
  4. Save to runs/backlinks-[date].md.

Rules (non-negotiable)

  • Flagging ≠ disavowing. Never produce a ready-to-upload disavow file. Google ignores most spam links on its own; a trigger-happy disavow does more damage than the spam. Disavow is only worth discussing after a manual action or a genuinely radioactive profile — and even then, the user decides.
  • DR is Ahrefs' metric, not Google's — say so when leaning on it.
  • Outreach targets are candidates with reasoning, not a guaranteed list.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/mikefutia/seo-consultant/backlinks/badge)](https://verified-skill.com/skills/mikefutia/seo-consultant/backlinks)

Something wrong with this skill or its page? Tell us.