seo-backlink-gap
Skill201 starsChanged 5 months agoMITView on GitHub
Find referring domains that link to multiple competitors but not to your site, then enrich with authority, anchor samples, and outreach angle per row. Produces a prospect list an outreach team can start emailing tomorrow. Use when the user asks for backlink gap analysis, link building opportunities, competitor backlink intersection, link prospecting, or wants referring domains they are missing.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- amirjahfar1/automate-seo-with-claudeedited, first seen Jun 9, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- amirjahfar1/automate-seo-with-claude★ 276% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository31 other files it gives its agents.
- ai-search-gaps-to-social-campaignSkill
- client-onboarding-proposalSkill
- local-gmb-visibilitySkill
- seo-adsSkill
- seo-agency-landing-pageSkill
- seo-ai-search-share-of-voiceSkill
- seo-ai-social-reportSkill
- seo-apiSkill
- seo-backlinks-profileSkill
- seo-competitor-gap-analysisSkill
- seo-competitor-pagesSkill
- seo-content-auditSkill
- seo-content-briefSkill
- seo-driftSkill
- seo-firecrawlSkill
- seo-gaps-to-social-campaignSkill
- seo-geoSkill
- seo-googleSkill
- seo-hreflangSkill
- seo-imagesSkill
- seo-keyword-clusterSkill
- seo-keyword-nicheSkill
- seo-localSkill
- seo-pageSkill
- seo-planSkill
- seo-schemaSkill
- seo-sitemapSkill
- seo-subdomainSkill
- seo-sxoSkill
- seo-technical-auditSkill
- site-audit-to-social-distributionSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 44
Create a folder seo-backlink-gap-{target-slug}-{YYYYMMDD}/ with:
- Distinctive: line 96
Do not include subdomains of already-linked domains in the prospect list.
- Distinctive: line 99
If the target already outranks all competitors for branded terms, prioritise non-branded editorial placements over parity directories.
≈ “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.
Files
Example output: examples/seo-backlink-gap-linear-app-20260514/REPORT.md
Backlink Gap
Produce an actionable link-prospecting list: domains linking to your top competitors but not to you, filtered by authority and relevance, enriched with anchor samples and a suggested outreach angle.
Prerequisites
- SE Ranking MCP server connected.
- Claude's
WebFetchtool available (used for prospect scoring and topical relevance checks). - User provides: (a) target domain, (b) 3 to 5 competitor domains, and optionally (c) minimum Domain Trust (default: 25), (d) dofollow-only filter (default: true), (e) minimum intersection count (default: linked by at least 2 of the N competitors).
Process
- Baseline target backlinks
DATA_getBacklinksRefDomains,DATA_getBacklinksSummary- Pull the target domain's existing referring domains to build an exclusion set.
- Save count and summary metrics for the report.
- Per-competitor referring domains
DATA_getBacklinksRefDomains- For each competitor, pull referring domains with
dofollow_only=trueandmin_domain_trust={threshold}. - Collect as a dict keyed by referring domain with the list of competitors linking to it.
- For each competitor, pull referring domains with
- Intersection
- Retain referring domains that link to at least the minimum number of competitors.
- Exclude any domain already in the target's backlink set.
- Enrichment
DATA_getBacklinksAuthority,DATA_getBacklinksAnchors- For each candidate, pull: Domain Trust, Page Trust of the linking page, linking-to-competitor anchor samples (top 3 anchors), and country if available.
- Classify by link type: editorial, resource list, directory, forum/UGC.
- Relevance scoring
- Score each candidate on: (a) topical overlap (use domain homepage title/meta via WebFetch), (b) DT, (c) intersection count, (d) link-type preference.
- Suggest an outreach angle per row: local fit, topical fit, competitive parity, resource-list inclusion, broken link, etc.
- Produce the prospect list (see Output Format).
Output format
Create a folder seo-backlink-gap-{target-slug}-{YYYYMMDD}/ with:
seo-backlink-gap-{target-slug}-{YYYYMMDD}/
├── 01-target-baseline.md
├── 02-competitor-{domain}-refs.md # one per competitor
├── 03-intersection-raw.md
├── prospects.csv # machine-readable output
└── REPORT.mdREPORT.md follows this shape:
# Backlink Gap: {target} vs {competitors}
## Filters applied
- Dofollow only: yes
- Min Domain Trust: {n}
- Min intersection: links to at least {n} of {total} competitors
## Top 25 prospects
| # | Referring domain | DT | Links to | Sample anchor | Link type | Angle | Score |
|---|---|---|---|---|---|---|---|
| 1 | example.com | 68 | {3 of 5} | "best yoga studios" | Resource list | Topical fit | 92 |
| 2 | ... | ... | ... | ... | ... | ... | ... |
## Outreach brief
- Segment these prospects into 3 batches by link type and pitch each batch with a tailored template.
- For editorial links: pitch a unique-angle comparison or original research.
- For resource lists: suggest inclusion with a specific anchor.
- For directories: apply directly.
- For forums/UGC: engage before pitching; these are not cold-outreachable.
## Counts
- Total unique referring domains across competitors: {n}
- Passed filters: {n}
- Already linking to {target}: {n} (excluded)
- Final prospects: {n}
## Files
- prospects.csv: import to Hunter.io, Pitchbox, or your outreach tool
- Per-competitor raw data: 02-competitor-*.mdprospects.csv columns:
rank,referring_domain,domain_trust,links_to_count,links_to_competitors,sample_anchor,link_type,outreach_angle,score
Tips
- Data API rate limit: 10 requests per second. With 5 competitors, expect 5-10 seconds of sequential API time plus enrichment.
- Do not include subdomains of already-linked domains in the prospect list. If news.example.com links to the target but blog.example.com links only to competitors, treat as already-linked unless the user asks otherwise.
- The "Angle" column is the most important output for outreach. Keep it specific: "Their 'best X tools' list from 2024 is out of date and doesn't include you" beats "topical fit".
- Exclude obvious spam/low-quality domains even if they pass DT thresholds. Use the WebFetch step to sanity-check any prospect scoring above 80.
- If the target already outranks all competitors for branded terms, prioritise non-branded editorial placements over parity directories.
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
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.

