openseo-link-prospecting

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

1. Catalog + binding: mktg catalog info openseo --json --fields configured + .seo/openseo.json. No OpenSEO → prospect with Exa search only (queries below still apply) and label authority data unknown.
2. 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.
3. Read brand/positioning.md for 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_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/email structured 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

1. Build 5–10 prospecting queries from the asset; get_serp_results in batches.
2. Competitors supplied? get_backlinks_overview their strongest domains first.
3. 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).
4. Per prospect, define the angle: broken/missing resource, better current data, useful tool/template, comparison inclusion, expert quote.
5. Contact discovery on the strongest prospects via web tools (source URLs recorded).
6. 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" }] }

7. Draft 2–3 reusable outreach messages (resource inclusion, article update, comparison angle). Hand the list to off-page-seo for the campaign cadence.

Output Format

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.

Adapted 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.