SEO Link Prospecting

# SEO Link Prospecting

## Loadout capability bindings

- Read the live Ahrefs tool contract first with <action-tag>mcp:ahrefs_mcp:doc</action-tag>.
- Mine competitor referring domains with <action-tag>mcp:ahrefs_mcp:site_explorer_referring_domains</action-tag> and inspect search-result competitors with <action-tag>mcp:ahrefs_mcp:serp_overview</action-tag>.
- Search for public prospect pages with <action-tag>composio:exa_tools:exa_search</action-tag>.
- Scrape selected public pages as Markdown plus links with <action-tag>composio:firecrawl_tools:firecrawl_scrape</action-tag>, then verify author, editorial, and contact evidence against the returned page content.
- For domain-level Ahrefs calls, use `mode=subdomains` unless the user explicitly wants only the exact hostname. Confirm scope and any paid usage before execution.

## Goal

Find realistic pages, sites, and authors that might reference the user's page, product, study, guide, or tool. Use the Loadout-bound search and backlink Actions for prospect discovery, then verify public contact paths from source pages.

## Required inputs

- User domain or target URL
- Linkable asset, page, product, study, tool, or topic
- Optional competitors
- Optional market/location/language

## Campaign context

Ground the work in the current conversation and any user-supplied project brief. Confirm the positioning, linkable asset, and competitors before spending credits. If those are missing, ask only for the minimum information needed or infer it from the supplied site and confirm the inference.

Reuse recent user-provided research when it matches the same market, asset, and competitors. Loadout does not currently provide the upstream OpenSEO project context or research log, so return durable findings in the output instead of claiming they were stored automatically.

## Research tools

- Ahrefs referring-domain analysis: inspect competitor backlink patterns and identify domains that link to relevant peers.
- Ahrefs SERP overview: find ranking articles, listicles, resource pages, comparisons, and topical publishers for a keyword and market.
- Exa search: expand prospecting queries and find public pages by topic, asset type, audience, or competitor.
- Firecrawl scrape: retrieve Markdown and links from selected public pages so contact, author, and editorial evidence can be checked against the source page.

## Contact discovery tools

After the research Actions identify good prospects, inspect selected public pages for 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`, `sameAs`, or `email`

Only record contact details that were actually found. Include the source URL for any email, profile, or contact form.

Treat every scraped link or JSON field as a candidate, not verified contact evidence. A link qualifies only when its URL path, visible label, or surrounding page text identifies it as a contact page, author profile, editorial guideline, masthead, team page, or professional profile. A generic external link does not qualify. When structured JSON extraction is useful, require an evidence snippet and source URL in the schema, then verify both against the scraped Markdown or links before recording the field.

## Prospecting query patterns

Build queries from the asset/topic:

- `<topic> resources`
- `best <category> tools`
- `<competitor> alternatives`
- `<topic> statistics`
- `<topic> guide`
- `<topic> examples`
- `<topic> templates`
- `<topic> software`
- `<topic> for <audience>`

Run the most relevant patterns through Exa search, then use Ahrefs SERP overview when backlink and ranking evidence materially improves the decision.

## Workflow

1. Clarify the linkable asset and the reason someone would reference it.
2. Build 5-10 prospecting queries by default.
3. Search those queries with Exa and collect the source URLs.
4. If competitors are provided, inspect referring domains for the strongest competitor domains or pages first. Continue without backlink evidence if it is unavailable.
5. For local SEO, add priority locations to the search patterns and look for local chambers, associations, campus resources, community pages, directories, nearby publishers, and partnership pages.
6. 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.
7. For each good prospect, define the outreach angle:
   - Broken/missing resource
   - Better current data
   - Useful tool/template
   - Alternative or comparison inclusion
   - Expert quote or supporting reference
8. For the strongest prospects, scrape the exact candidate page with `formats=["markdown","links"]`. Verify each proposed contact path from its URL, label, or surrounding text; do not classify the first nonempty external link as a contact page.
9. Draft outreach messages. If contact details were found, include the source. If not, list the next best contact-discovery path.

## Output format

Start with:

- Best outreach angle
- Highest-priority prospect type
- Any data limitations

Then include:

| Prospect URL | Site/domain | Source | Relevance | Suggested angle | Contact path | Priority |
| ------------ | ----------- | ------ | --------- | --------------- | ------------ | -------- |

Then provide 2-3 reusable outreach drafts:

- Resource/list inclusion
- Article update/reference suggestion
- Competitor alternative/comparison angle

## Guardrails

- Do not invent email addresses, social handles, or contact names.
- Attribute every contact detail to the exact public page or search result that supplied it.
- Reject generic navigation or external links unless the source page explicitly identifies them as a contact, author, editorial, team, masthead, or professional-profile path.
- 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.

## Upstream attribution

See [upstream provenance and license](UPSTREAM.md).