# Citation Gap Outreach

> Use this skill when the sources behind AI answers are known and the brand needs to get into them — "AI keeps citing these directories and the brand is not there," "turn the citation analysis into an outreach plan," "get named where the engines already read." Converts cited-source gaps into a ranked get-listed plan with the right ask per source type and a re-measure loop proving each placement moved answers.

- Skill: `swan-gtm/citation-gap-outreach` (Agent Skill)
- Install (CLI): `npx skillmds@latest add swan-gtm/citation-gap-outreach`
- Raw SKILL.md: https://api.skillmd.com/api/skills/swan-gtm/citation-gap-outreach/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: swan-gtm (https://skillmd.com/u/swan-gtm)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/swan-gtm/citation-gap-outreach

---


Use when the sources feeding AI answers in a category are known and the brand needs to get into them. Produces a ranked get-listed plan with the right ask per source and a re-measure loop that proves each placement landed.

## Rank by answers fed, not authority

Order target sources by how many category answers each one fed. Domain authority, traffic, and prestige all mislead here: a modest directory feeding nine answers outranks a famous publication feeding one. The citation count is the value of the placement; everything else is habit carried over from link building.

## Match the ask to the source

Each source type gets updated a different way, and the ask must match it. A directory or listing site wants a submission or a claimed profile. A comparison or review page wants inclusion with evidence — real differentiators, pricing, proof — not a pitch. A community thread is entered honestly, with a real answer from a real account, or left alone. A publication wants the data or story its page is missing. Write the ask so the person who maintains that page can act on it in one sitting.

## Run it like pipeline

Track each target as a row: source, page, answers it fed, whether it mentions the brand today, ask type, the human contact, status. Work the top of the list first; small placements land fastest and compound.

## Verify the placement landed in answers

After a placement goes live, re-ask the questions that source was feeding and compare. If the answers do not move within a re-measure cycle, either the source mattered less than the count suggested, or the mention lacks the substance engines quote — specifics, numbers, and comparisons get cited; adjectives do not. Fix the mention before adding new targets.

## What good looks like

The best operators notice the shape of what engines quote from each source — a comparison table, a price, a spec — and ask for that placement, not a logo on a partner wall. The mediocre version is generic link-building outreach re-sent with new words in the subject line, ordered by domain authority, never re-measured. Good output attaches evidence to every target — the answers that source fed — so each outreach message writes itself, and every closed row has a before-and-after answer pair proving it mattered.

## Rules

- MUST rank targets by answers fed.
- MUST re-measure the affected questions after each placement.
- NEVER astroturf community threads.
- NEVER present paid placements as organic mentions.