openseo-link-prospecting
Skill33 starsChanged 6 months agoMITView on GitHub
Find realistic link prospects with SERP and backlink evidence, discover contact paths via web tools, and draft personalized outreach — with targets saved to .seo/backlink-targets.json for off-page-seo campaigns. Use this skill when the user has a linkable asset (study, tool, guide, template, product page) and wants backlinks, resource-page inclusions, or comparison mentions. Triggers: "link prospecting", "find backlink opportunities", "resource page outreach", "get backlinks for", "link building outreach".
- Reads credentials
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
- Very specific: line 38
Read brand/positioning.md for angle/audience fit (tolerate missing).
- Very specific: line 70
Write targets to .seo/backlink-targets.json:
- Very specific: line 93
After writing files, log completion so mktg plan / mktg status count the work (bare mktg run only logs loaded):
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
OpenSEO Link Prospecting
Find pages, sites, and authors that might realistically reference the user's linkable asset — then hand off-page-seo a qualified target list at .seo/backlink-targets.json instead of a cold start.
On Activation
- Readiness + binding:
mktg seo status --json --fields readiness,catalog.endpointError,project.not_configured→ prospect with Exa search only (queries below still apply) and label authority dataunknown. For a ready state, verify live access with the freewhoamiMCP tool before paid calls. - Clarify the asset: what page/study/tool/template is being promoted and WHY someone would reference it. No clear asset + reason → fix that first; outreach without a reason is spam.
- Read
brand/positioning.mdfor angle/audience fit (tolerate missing).
OpenSEO MCP Tools
get_serp_results: find ranking articles, listicles, resource pages, comparisons, statistics pages (≤10 queries per call).get_backlinks_overview: competitor backlink/referring-domain patterns — where do THEY get links (may be unavailable; continue without).get_backlinks_profile: page-level source/target/anchor/dofollow/lost/broken evidence. Preserve target scope, pagination, filters, and one-per-domain mode in.seo/backlink-targets.jsonprovenance.get_domain_overview: qualify strong prospect domains.get_ranked_keywords: topical-fit checks on prospects/competitors.research_keywords: expand prospecting queries.
Contact Discovery (NOT OpenSEO)
Contact paths come from web/search/browser tools (Firecrawl fetch, Exa search, browser automation) — never attribute these to OpenSEO:
- Author byline pages, contact pages, editorial guidelines, about/team pages
- LinkedIn/X/Bluesky profiles, newsletter mastheads
- Public emails in HTML or visible text;
Person/Organization/sameAs/emailstructured data
Record only contact details actually found, each with its source URL.
Prospecting Query Patterns
<topic> resources · best <category> tools · <competitor> alternatives · <topic> statistics · <topic> guide · <topic> examples · <topic> templates · <topic> software · <topic> for <audience>
Workflow
- Build 5–10 prospecting queries from the asset;
get_serp_resultsin batches. - Competitors supplied?
get_backlinks_overviewtheir strongest domains first. - Filter: keep editorial pages, resource lists, comparisons, statistics, templates, curated directories. Drop homepages, login walls, thin affiliate, spam, and direct competitors (unless a comparison angle is valid).
- Per prospect, define the angle: broken/missing resource, better current data, useful tool/template, comparison inclusion, expert quote.
- Contact discovery on the strongest prospects via web tools (source URLs recorded).
- Write targets to
.seo/backlink-targets.json:
{ "version": 1, "updatedAt": "<iso>", "asset": "<url>", "targets": [{ "url": "", "domain": "", "source": "", "relevance": "", "angle": "", "contactPath": "", "contactSource": "", "priority": "high|med|low", "status": "new" }] }- Draft 2–3 reusable outreach messages (resource inclusion, article update, comparison angle). Hand the list to
off-page-seofor the campaign cadence.
Output Format
| Prospect URL | Domain | Source | Relevance | Suggested angle | Contact path | Priority |
Anti-Patterns
- Inventing emails, handles, or contact names — because a single fabricated contact burns the user's credibility with a real human. Only record what was found, with the source URL; otherwise name the next discovery step.
- Attributing contact discovery to OpenSEO — because OpenSEO finds PROSPECTS; web/browser tools find CONTACTS. The misattribution teaches a wrong tool model and hides the real source when details need re-verification.
- Mass-template outreach — because editors can smell a blast, and one spam report damages the domain's future deliverability. Personalize by page and reason, or don't send.
- Prospecting without a linkable asset and reason — because "please link to my homepage" converts at ~0%. No asset + reason, no outreach.
- Skipping competitor/paid-placement flags — because pitching a direct competitor or a pay-to-play listicle wastes the user's outreach capital and can backfire publicly. Flag both in the target list.
Close the loop
After writing files, log completion so mktg plan / mktg status count the work (bare mktg run only logs loaded):
mktg run openseo-link-prospecting --complete --writes <paths written> --result success --jsonAdapted from every-app/open-seo .agents/skills/link-prospecting (MIT). Workflow upstream; mktg artifact paths, off-page-seo handoff, and contact-attribution discipline added here.
In this repository79 other files it gives its agents.
- AGENTS.mdAGENTS.md
- studio/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- studio/CLAUDE.mdCLAUDE.md
- agent-email-inboxSkill
- ai-seoSkill
- app-store-screenshotsSkill
- audience-researchSkill
- axiSkill
- brainstormSkill
- brand-kit-playgroundSkill
- brand-voiceSkill
- build-with-exaSkill
- churn-preventionSkill
- cmo-remotionSkill
- cmoSkill
- company-researchSkill
- competitive-intelSkill
- competitor-alternativesSkill
- content-atomizerSkill
- conversion-flow-croSkill
- create-skillSkill
- creativeSkill
- deepen-planSkill
- direct-response-copySkill
- document-reviewSkill
- email-sequencesSkill
- exa-contentsSkill
- exa-searchSkill
- firecrawlSkill
- free-tool-strategySkill
- frontend-slidesSkill
- higgsfield-generateSkill
- higgsfield-product-photoshootSkill
- higgsfield-soul-idSkill
- image-genSkill
- keyword-researchSkill
- landscape-scanSkill
- launch-strategySkill
- lead-generationSkill
- lead-magnetSkill
- manimce-best-practicesSkill
- manim-composerSkill
- manimgl-best-practicesSkill
- marketing-demoSkill
- marketing-psychologySkill
- mktg-setupSkill
- mktg-xSkill
- newsletterSkill
- off-page-seoSkill
- openseo-coachSkill
- openseo-competitive-landscapeSkill
- openseo-competitor-analysisSkill
- openseo-keyword-clusteringSkill
- openseo-keyword-researchSkill
- openseo-project-setupSkill
- openseoSkill
- page-croSkill
- paper-marketingSkill
- positioning-anglesSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

