icp-profiles

icp-profiles

Source of truth: Notion ICP profiles database under Marketing foundations. The database has slim properties; the rich content (role, segment, geography, language, buying stage, concerns, channels, objections, triggers, existing stack, notes) lives inside each row's page body under structured H2 headings. Always fetch both.

Notion source (pinned)

Resource	Notion ID	URL
ICP profiles database	75d1b32c-f157-4d52-9b31-ad4b8d71ef88	https://www.notion.so/75d1b32cf1574d529b31ad4b8d71ef88
Data source (collection)	829adc11-5642-47d9-bd58-9436da3d5d05	collection://829adc11-5642-47d9-bd58-9436da3d5d05
Parent: Marketing foundations	35cf15e1-b3e7-8168-a618-de718878bdf3	https://www.notion.so/35cf15e1b3e78168a618de718878bdf3

When to load this

• Any content brief that has a target_icp field.
• Orchestrator triage when the user has named an audience (or hasn't, in which case the orchestrator should prompt).
• When the user asks "who are we writing this for" or wants to inspect an ICP.

How to fetch

Two-step fetch:

1. Query the database via query_data_sources against the pinned data source. Filter by Status = Live by default. When the caller specifies an ICP by name, also filter on Name. Returns row metadata: name, status, priority, last reviewed, page URL.
2. Fetch each row's page body via notion-fetch on the page URL from step 1. The page body contains the rich ICP detail under structured H2 headings.

If the pinned ID returns an error, fall back to notion-search for ICP profiles in the Marketing teamspace, then update this skill's pinned ID.

Database properties (slim, by design)

Property	Type	Use
Name	Title	Short label, e.g., "Broker — generalist"
Status	Select (Draft / In review / Live / Archived)	Plugin filters to Live by default
Priority	Select (Primary / Secondary / Tertiary)	Strategic priority for orchestrator default
Last reviewed	Date	Staleness check

Everything else is in the page body.

Page body structure

Each row's page body uses these H2 headings (set by the team's standard template):

• Role / title
• Segment & geography
• Working language
• Buying stage
• Decision power
• Top concerns
• Channels
• Objections
• Trigger events
• Existing stack
• Notes

When parsing the page body, extract content under each heading. Empty sections mean "not yet defined" — surface to the caller.

Output shape

icp:
  name: <text>
  priority: <text>
  status: <text>
  last_reviewed: <date>
  notion_source: <row url>
  body:
    role: <text>
    segment_geography: <text>
    working_language: <text>
    buying_stage: <text>
    decision_power: <text>
    top_concerns: <text>
    channels: <text>
    objections: <text>
    trigger_events: <text>
    existing_stack: <text>
    notes: <text>
last_fetched: <timestamp>
gaps_flagged: <list of empty headings>

Multiple ICPs

If the brief targets more than one ICP, fetch both rows (properties + page bodies) and call out where messaging will need to fork. Do not silently merge into a composite profile.

Empty database state (v1)

In v1 the database is created but not yet populated. When invoked against an empty database, return:

• status: empty
• note: "ICP profiles database exists at <url> but has no rows yet. The marketing team is in the process of formalizing ICPs. Output skills should flag this gap to the user rather than generating against thin context."

This behavior should change as the team adds rows.

Note on use

Output skills should not paste raw ICP fields into customer-facing copy. They use the ICP profile to shape angle, vocabulary, examples, and proof points. The ICP is context for the writer, not source material for the reader.

Drift detection

When fetching ICP rows, watch for: stale Last reviewed (>6 months), Draft rows that should be Live, empty page-body sections, contradictions with brand-foundations audience descriptions. Flag concrete suggestions to the team via the conversation per the standing drift-detection rule.