link-prospecting
Skill2 starsChanged 52 days agoMITView on GitHub
Find link prospects from SERPs and backlink signals, discover public contact paths, and draft outreach for a page, product, study, guide or tool. Use when the user wants backlinks or mentions for a linkable asset.
- Reads credentials
10 other projects use a version of this, 9 of them edited.
Adopted by
Most recently taken up by
- foverse/seoverseedited, first seen Nov 8, 2026
- winsley-jeune/harborrank-skillsedited, first seen Oct 27, 2026
- jwuthri-cloud/Tracely-aiedited, first seen Oct 20, 2026
- petera2c/simple-tableedited, first seen Oct 8, 2026
- VladSez/easy-invoice-pdfedited, first seen Oct 8, 2026
- every-app/open-seoedited, first seen Oct 8, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 9
- every-app/open-seo★ 27k65% same
- Jwuthri/Tracely-ai★ 1.3k58% same
- VladSez/easy-invoice-pdf★ 1.1k58% same
- jwuthri-cloud/Tracely-ai★ 97958% same
- petera2c/simple-table★ 23358% same
- foverse/seoverse★ 465% same
- ventra-rocket/EchoSEO★ 258% same
- winsley-jeune/harborrank-skills★ 219% same
- ictlondon/kraftskills★ 056% same
Wrote their own version · 1
- fenjo26/OpenGSC★ 56same name
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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- competitive-landscapeSkill
- competitor-analysisSkill
- keyword-clusteringSkill
- keyword-researchSkill
- local-seoSkill
- seo-auditSkill
- seo-coachSkill
- seo-project-setupSkill
- seo-reportSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 5 are common, 0 are distinctive, and 9 are very specific to this project.
5
Common
Most of the 10 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
9
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Use the installed agenticseo command.
- Very specific: line 25
Run agenticseo context first and ground the outreach in it: positioning supplies the claim that makes a link worth giving, and the saved …
- Very specific: line 27
Before paying, check researchLog.
- Very specific: line 46
After agenticseo identifies good prospects, use your web search, page fetch or browser tools for public contact discovery.
- Common: line 59
Only record contact details that were actually found.
- Very specific: line 75
Run agenticseo serp for the most relevant patterns, up to 10 queries per call.
- Very specific: line 81
Run agenticseo serp for those queries.
- Very specific: line 82
If competitors are provided, run agenticseo backlinks overview for the strongest competitor domains or pages first, and page through their …
- Common: line 85
Keep topical relevance and editorial pages.
- Very specific: line 101
If a report template applies (see seo-report), its sections and tone replace this list.
- Common: line 115
Do not invent email addresses, social handles or contact names.
- Very specific: line 116
Do not say agenticseo found contact details.
- Common: line 117
If contact details are not available after a reasonable search, recommend specific discovery steps such as checking the author page, …
- Common: line 118
Avoid spammy mass outreach.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Adapted from OpenSEO plugins/openseo/skills/link-prospecting/SKILL.md (https://github.com/every-app/open-seo, MIT, Copyright (c) 2026 Ben Senescu) for the AgenticSEO CLI. -->Link prospecting
Goal
Find realistic pages, sites and authors that might reference the user's page, product, study, guide or tool. Use agenticseo for prospect discovery, then use your web, search or browser tools for contact discovery.
Use the installed agenticseo command. Lookups are billed by DataForSEO and need DATAFORSEO_API_KEY; each result states its cost and points to an evidence file.
Required inputs
- The user's domain or target URL
- The linkable asset, page, product, study, tool or topic
- Optional competitors
- Optional market/location/language
Project context
- Run
agenticseo contextfirst and ground the outreach in it:positioningsupplies the claim that makes a link worth giving, and the savedcompetitorsare the backlink profiles to mine. If there is no project, set one up asseo-project-setupstep 1 describes. - This skill needs
positioningand competitors. If either is empty, run a minimal inline setup: ask the user why someone would cite them and who they compete with, or infer it from the site andagenticseo competitorsand confirm, write it to.agenticseo/context.json, then continue. Never front-load the full interview; suggestseo-project-setupat the end for the rest. - Before paying, check
researchLog. If the same research ran within the last 30 days, reuse its evidence and say so instead of buying it again. - On finish, write back what is durable: the linkable asset in
keyPages, any competitor whose backlink profile proved useful incompetitors, and append{ "entryDate": "<today from agenticseo context>", "summary": "Link prospecting: <asset/target page>. Verdict: <conclusion>. Evidence: <paths>" }toresearchLog. Runagenticseo contextto validate.
Deliver as a report
Deliver through the seo-report skill. If that skill is not available, say so and stop before writing the report.
Commands
agenticseo serp "QUERY"...: find ranking articles, listicles, resource pages, comparisons and topical publishers, up to 10 queries per call.agenticseo backlinks overview DOMAIN: a competitor domain's or page's backlink and referring-domain profile, with its top referring domains.agenticseo backlinks domains DOMAINandagenticseo backlinks links DOMAIN: page through a competitor's referring domains and individual backlinks (--include,--min-domain-rank,--link-type dofollow,--hide-lost) when its profile is the best source of prospects.agenticseo domain DOMAIN: qualify important prospect domains.agenticseo ranked DOMAIN: what a prospect or competitor ranks for, when topical fit matters.agenticseo local businessesandagenticseo local serp: for local link prospecting, when nearby businesses, local competitors or Maps categories can reveal partnership targets.agenticseo research "SEED"...: expand prospecting queries.
Contact discovery tools
After agenticseo identifies good prospects, use your web search, page fetch or browser tools for public contact discovery.
Look for:
- Author byline pages
- Contact pages
- Editorial guidelines
- About/team pages
- LinkedIn, X, Bluesky or other professional profiles
- Newsletter or publication masthead pages
- Public email addresses in page HTML or visible page text
- Structured data such as
Person,Organization,sameAsoremail
Only record contact details that were actually found. Include the source URL for any email, profile or contact form.
Prospecting query patterns
Build queries from the asset or topic:
<topic> resourcesbest <category> tools<competitor> alternatives<topic> statistics<topic> guide<topic> examples<topic> templates<topic> software<topic> for <audience>
Run agenticseo serp for the most relevant patterns, up to 10 queries per call.
Workflow
- Clarify the linkable asset and the reason someone would reference it.
- Build 5–10 prospecting queries by default.
- Run
agenticseo serpfor those queries. - If competitors are provided, run
agenticseo backlinks overviewfor the strongest competitor domains or pages first, and page through their referring domains when the overview shows a useful profile. Continue without backlink evidence if it fails. - For local SEO, use
agenticseo local businessesandagenticseo local serparound priority locations to identify nearby competitors, categories and local SERP evidence before searching for local chambers, associations, campus resources, community pages and directories. - Filter prospects:
- Keep topical relevance and editorial pages.
- Prioritize articles, directories, resource pages, comparisons, statistics pages, templates and curated lists.
- Deprioritize homepages, login pages, thin affiliate pages, spam, unrelated forums, and direct competitors unless a comparison angle is valid.
- For each good prospect, define the outreach angle:
- Broken or missing resource
- Better current data
- Useful tool/template
- Alternative or comparison inclusion
- Expert quote or supporting reference
- For the strongest prospects, visit or search the prospect site to find the best contact path.
- Draft outreach messages. If contact details were found, include the source. If not, list the next best contact-discovery path.
Output format
Title: Link Prospecting: <linkable asset> — <date> (see seo-report).
If a report template applies (see seo-report), its sections and tone replace this list.
Sections in this order:
- The angle: one or two opening sentences naming the best outreach angle and the prospect type to work first.
- Prospects: a table of prospect URL, site, source, suggested angle, contact path and priority. Keep it under about eight columns; drop the ones that add nothing for this run.
- Why these: one finding per prospect worth explaining: the evidence that they link to things like this, then the exact ask.
- Outreach drafts: the message text for each of two or three reusable angles: resource or list inclusion, an article update, and a comparison mention.
- Limitations: notes: contact paths not found, prospects that are direct competitors or likely paid placements, and which source found each contact detail.
- What to do next: an ordered list: who to send to first, and in what order.
- How this report was made: opens with the skill link line from
seo-report, pointing athttps://github.com/kid7st/agenticseo/blob/main/.agents/skills/link-prospecting/SKILL.md("AgenticSEO Link Prospecting skill"), then which commands returned prospects (with costs and evidence paths) and which came from the web or the browser.
Guardrails
- Do not invent email addresses, social handles or contact names.
- Do not say
agenticseofound contact details; it does not return them. Attribute contact discovery to the web, search or browser source used. - If contact details are not available after a reasonable search, recommend specific discovery steps such as checking the author page, contact page, LinkedIn, X or a reputable contact-enrichment tool.
- Avoid spammy mass outreach. Personalize by page and reason.
- Flag prospects that are direct competitors or likely paid placements.
- On exit code 3, ask the user to fix the key; on exit code 4, report the error and any charged cost, and do not retry in a loop.
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.

