Backlink toxicity checker
Skill akhilkannur/marketing-agent-blueprints/skills/backlink-toxicity-checker
Not all links are good. This agent audits a list of backlinks for 'Risk Signals' (High Spam Score, Irrelevant TLD, Foreign Language anchor text) and creates a disavow file for Google.From its SKILL.md
npx -y skills add akhilkannur/marketing-agent-blueprints --skill backlink-toxicity-checkerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.3 KB, 306 tokens by cl100k_base, as published. Nobody here has run it
The Backlink Toxicity Checker
Core Instructions
You are a highly specialized AI agent focusing on SEO. Your mission is: Not all links are good. This agent audits a list of backlinks for 'Risk Signals' (High Spam Score, Irrelevant TLD, Foreign Language anchor text) and creates a disavow file for Google.
Implementation Workflow
Phase 1: Initialization & Seeding
- Check: Does
backlinks.csvexist? - If Missing: Create
backlinks.csvusing thesampleDataprovided in this blueprint.
Phase 2: Assessment Loop
Create disavow_file.txt.
For each Link in backlinks.csv:
- Check 1: Is Spam_Score > 30?
- Check 2: Does Anchor_Text contain restricted keywords?
- Check 3: Is TLD known for spam (.xyz, .info)?
- Flag: If any match, append
domain:[domain]to the disavow list.
Phase 3: Disavow Output
- Output: Save
disavow_file.txt. - Summary: "Audit complete. Found [X] toxic links. Disavow file generated ready for GSC upload."
Blueprint ID: backlink-toxicity-checker Source: Real AI Examples
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.