peec-cluster

Content Cluster Builder

Role

Reduce a flat Peec prompt set to 4–8 strategic zones — each with a structural weakness in the competition, one measurable metric, and one "do exactly this now" action. Not keyword clusters. Not a content calendar.

A zone is coherent only when three axes line up:

      Intent
       ↑
Visibility gap
       ↑
Demand signal

If a candidate zone fails any axis, it gets merged or dropped.

Input

• project_id — Peec project
• optional date_range — default last 30 days
• optional target_zones — default 4–8 (skill picks the resolution)
• optional focus_funnel_stage — restrict to one stage

Output

One markdown zone map (schema in §Output schema), plus one Peec tag per zone (zone:<slug>) with all prompts retagged, so peec-report can measure zone lift later.

When to use

• ≥20 Peec prompts and the team has lost the overview
• After @peec-setup, before @content-write per article
• Quarterly strategy refresh
• Before an investment conversation ("what is our AI content strategy?")

Do not use when:

• <10 prompts (not enough mass for real zones)
• Prompts aren't split into Awareness / Consideration / Decision / Retention yet (run @peec-setup first)

---

Pipeline

0. Pre-flight — setup state required

Per _shared/SETUP_STATE.md, this skill refuses to run without a completed setup:

Read <project>/growth_loop/setup_state.json
If missing OR completed_at missing OR phases_completed lacks
   {competitors, prompts, topics, tags}:
     STOP. Output:
       "No Peec setup state found at <project>/growth_loop/setup_state.json.
        Run /peec-setup first."
If completed_at older than 90 days: WARN once, continue.
Use peec_project_id from state — don't re-resolve via list_projects.

1. Pull prompt inventory + visibility state

mcp__peec-ai__list_prompts(project_id)
mcp__peec-ai__get_brand_report(
  project_id, start_date, end_date,
  dimensions=["prompt_id"],
  filters=[{field: "brand_id", operator: "in", values: [own_brand_id]}]
)
mcp__peec-ai__get_url_report(
  project_id, start_date, end_date,
  dimensions=["prompt_id"],
  filters=[{field: "gap", operator: "gt", value: 0}]
)