agentleFS
Sign inStart free
UXMagicaiUXMagicai/seosorted-skills/skills/link-building-playbooks/SKILL.md

link-building-playbooks

Skill0 starsChanged 40 days agoMITView on GitHub

Run white-hat link-building playbooks end to end — broken link replacement, link reclamation, unlinked brand mentions, outdated statistics, resource pages, competitor link intersect and AI-citation listicle outreach — from prospecting with SEOsorted's backlink data to ready-to-send drafts. Use when the user asks for link building strategies, how to get backlinks, outreach campaigns, broken link building, or unlinked mentions.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Search the web for the brand name excluding the user's own domain.

    line 17
  2. Very specific:

    Search "<topic>" inurl:resources and "<topic>" "helpful links".

    line 23
  3. Very specific:

    Check prospect strength with analyze_any_domain operation: "authority" (domains, up to 50.

    line 33

≈ “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

Link-building playbooks

Pick one playbook per campaign. Each ends with a short prospect list and a drafted email per prospect, written with build_backlinks operation: "draft_pitch" (free; it only drafts, nothing is sent).

1. Link reclamation (start here)

build_backlinks operation: "reclaim" — links already pointing at dead pages on the user's site, with a suggested live page to redirect to. Fixing these needs no outreach. See link-reclamation.

2. Broken link replacement

Find a niche resource page, then audit_any_page operation: "links" with its url to flag broken outbound links (free). Where a dead link covers a topic the user has a page for, draft with pitch_type: "broken_link" and put the dead URL in notes.

3. Unlinked mentions

Search the web for the brand name excluding the user's own domain; track_ai_search_visibility operation: "citations" also lists cited pages that name the brand and whether they link. For pages that mention without linking, draft with pitch_type: "unlinked_mention". Highest reply rate of any playbook.

4. Outdated statistics

Find well-linked articles quoting old numbers in the niche. Create or point to a page with current, sourced figures (statistics-page) and draft with pitch_type: "citation_update".

5. Resource pages

Search "<topic>" inurl:resources and "<topic>" "helpful links". Pitch the single best page for that list (our_page_url), not the homepage, with pitch_type: "resource".

6. Competitor link intersect

build_backlinks operation: "intersect" with 2–5 competitors — sites linking to several competitors but not the user. See backlink-outreach.

7. AI-citation listicles

find_backlink_prospects (see ai-citation-outreach) — pages AI engines cite are the most valuable links to earn now.

For every playbook

  • Check prospect strength with analyze_any_domain operation: "authority" (domains, up to 50; 1 keyword lookup credit per 10 domains) and drop weak or spammy sites.
  • Prospect table: page, Domain Rating, why it fits, contact (from public pages only).
  • One specific email per prospect: draft_pitch with prospect, pitch_type, contact_name if known, our_page_url and notes. Edit it so it references the exact page and fix. Under 120 words.
  • The user sends the emails. Never send outreach or claim it was sent.

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