agentleFS
Sign inStart free
UXMagicaiUXMagicai/seosorted-skills/skills/backlinks/SKILL.md

backlinks

Skill0 starsChanged 39 days agoMITView on GitHub

Analyse a site's backlink profile and find link opportunities with SEOsorted — live backlinks, anchor-text distribution, links gained and lost, Domain Rating, the backlink gap versus competitors and managed backlink package progress. Use when the user asks about backlinks, link building targets, domain authority, who links to competitors, lost links, anchor text, or their backlink package progress.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No paid links, link farms or PBNs — they put the site at risk.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Backlinks

Link data comes from DataForSEO's backlink index. build_backlinks defaults to the workspace's own site; pass domain for any other.

1. Where the site stands

  1. manage_competitors operation: "backlinks" — stored profile: backlinks, referring domains, spam score, domain rank with 30-day change, and the directory-package progress (live, in review, to do) if the workspace has one. Free.
  2. analyze_any_domain operation: "authority" with domains: [the site, its competitors] — Domain Rating, Domain Rank and referring domains side by side (1 keyword lookup credit per 10 domains).
  3. build_backlinks operation: "links" with dofollow_only: true, one_per_domain: true — the strongest live links (1 keyword lookup credit).
  4. build_backlinks operation: "anchors", with keyword set to the money keyword — anchor distribution; exact match above 10% is flagged as over-optimised (1 credit).
  5. build_backlinks operation: "new_lost" with days: 30 (or 7 / 90) — links gained and lost with dates (1 credit). Lost links from strong domains are worth a polite follow-up.

2. Where the gaps are

  1. manage_competitors operation: "list"; pick the competitor ranking for the user's most valuable keywords.
  2. manage_competitors operation: "backlink_gap" with url set to that competitor's domain — domains linking to them but not to the user. Paid plans only; pass on any upgrade link as is.
  3. For several competitors at once, build_backlinks operation: "intersect" with competitors (2–5 domains) and min_competitors: 2 — domains linking to at least two of them but not to the user (1 credit per competitor domain). These are the warmest prospects.
  4. Group the gap by type: industry publications, directories and listings, resource pages, blogs and podcasts, partners and integrations. Drop high spam scores.

3. Turn it into work

  • Dead pages on the site that still have links → link-reclamation.
  • Intersect and gap domains → backlink-outreach (drafts a pitch per prospect).
  • Editorial links need a linkable asset → statistics-page; other tactics → link-building-playbooks.

Quote credits before running several operations: the user's keyword lookup allowance is shared with keyword research.

Guardrails

No paid links, link farms or PBNs — they put the site at risk. Recommend links a real editor would give. Numbers come from the tools; never estimate DR or link counts.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free