keyword-cluster
Build a pillar+spokes content cluster plan from seed keywords with SERP-overlap clustering, intent grouping, internal-link map, and a four-gate quality scorecard
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/indranilbanerjee/digital-marketing-pro/HEAD/commands/keyword-cluster.md -o ~/.claude/commands/keyword-cluster.mdkeyword-cluster.md
# Keyword Cluster
> If you see unfamiliar placeholders or need to check which keyword data sources are connected, see [CONNECTORS.md](../CONNECTORS.md).
Takes a set of seed keywords and produces a publication-ready cluster plan: pillar pages with their spokes, intent-grouped, prioritised by an opinionated scoring formula, with an internal-link map and a four-gate quality scorecard. Routes to `skills/keyword-cluster/SKILL.md`.
## Trigger
User runs `/digital-marketing-pro:keyword-cluster` or asks for:
- "Cluster these keywords into a content plan"
- "Build a pillar/spokes architecture for this topic"
- "Design a topic hub for X"
- "Dedupe my cannibalising pages"
- "Plan a programmatic SEO rollout"
## Inputs
1. **Seeds** — either a list of 3–20 seed keywords inline, or a path to a CSV with at least a `keyword` column (plus optional `volume`, `kd`, `intent`)
2. **Target country / language** (optional — uses brand profile default)
3. **SERP data** (strongly recommended) — JSON map of keyword → top-N result URLs from connected rank-tracker MCP. Without this, falls back to lower-confidence lexical clustering.
4. **Filter thresholds** (optional) — minimum search volume, maximum keyword difficulty
## Process
1. Load brand context + auto-apply industry / compliance rules
2. Optionally expand seeds via brand's keyword-research MCP (`/keyword-research`) if input is < 20 keywords
3. Filter seeds by min-volume / max-KD / banned-word lists
4. Fetch top-10 SERPs per keyword via connected rank-tracker (with budget guard at 500-credit threshold)
5. Run `scripts/keyword_cluster.py` with SERP mode (or lexical fallback)
6. Validate the four quality gates (cannibalisation / orphan / coverage / anchor_diversity) — surface `needs_review` diagnostics if any fail
7. Draft pillar-page briefs for clusters with `priority_score >= 0.5`
8. Build internal-link map
9. Sort by priority for build-order recommendation
10. Write `PLAN.md` to `${CLAUDE_PLUGIN_DATA}/{brand}/seo/keyword-cluster/{date}/`
## Output
Numbered intermediate files under `${CLAUDE_PLUGIN_DATA}/{brand}/seo/keyword-cluster/{YYYY-MM-DD}/`:
- `00-input.md`, `01-seed-expansion.md`, `02-filtered.csv`, `03-serps.json` (if SERP mode)
- `04-cluster-run.json` (raw script output), `05-quality-scorecard.md`
- `06-pillar-pages.md`, `07-internal-link-map.md`, `08-build-order.md`
- `PLAN.md` (the deliverable)
## After the cluster
Ask: "Would you like me to:
- Brief the top pillar pages? (`/digital-marketing-pro:content-brief`)
- Start writing the highest-priority pillar? (`/digital-marketing-pro:content-engine`)
- Apply the internal-link map to your CMS? (`/digital-marketing-pro:seo-implement`)
- Schedule a quarterly re-run via `/digital-marketing-pro:seo-drift`?"
For the full skill spec including the four quality gates, priority-score formula, and chain handoffs, see [skills/keyword-cluster/SKILL.md](../skills/keyword-cluster/SKILL.md).Invoke when the user needs to manage multiple client brands, view portfolio-level dashboards, generate client reports, manage SOPs, switch credential profiles, assign team tasks, configure regions, or generate executive summaries. Triggers on requests involving multi-client management, agency workflows, client onboarding, or portfolio oversight.
Invoke when the user needs help with marketing measurement, KPI definition, dashboard design, attribution modeling, performance analysis, anomaly detection, competitive benchmarking, or translating data into marketing decisions. Triggers on requests involving metrics, reporting, analytics setup, or data interpretation.
Invoke when marketing content needs quality control review — brand voice consistency checks, regulatory compliance verification (GDPR, CAN-SPAM, CCPA, HIPAA, FTC, industry-specific), accessibility auditing (WCAG 2.1), inclusive language review, or brand safety assessment. Automatically invoked as a final review step before any content is published or delivered.
Invoke when the user needs competitor analysis — content strategy teardowns, SEO gap analysis, paid ad analysis from ad libraries, social media benchmarking, AI visibility comparisons, pricing and positioning research, or market landscape mapping. Triggers on requests mentioning competitors, competitive gaps, market analysis, or benchmarking.
Use when the task requires ongoing competitive monitoring, competitor change detection, share of voice tracking, competitive alerts, ad monitoring, price monitoring, win/loss analysis, or competitive narrative mapping.
Invoke when the user needs any form of marketing content created or refined — blog posts, ad copy, email campaigns, social media posts, landing page copy, press releases, video scripts, product descriptions, or newsletter content. Triggers on requests to write, draft, rewrite, or improve marketing copy.
Invoke when the user needs to manage CRM operations — creating contacts, importing leads, updating deals, syncing campaign data, segmenting audiences, managing pipelines, or connecting marketing data to Salesforce, HubSpot, Zoho, or Pipedrive. Triggers on requests involving CRM data, lead management, pipeline updates, or sales-marketing alignment.
Invoke when the user needs help with conversion rate optimization — landing page audits, A/B test design, form optimization, pricing page strategy, checkout flow improvement, personalization, statistical significance calculations, page speed impact analysis, or mobile conversion optimization. Triggers on requests involving conversions, landing pages, A/B testing, or optimization experiments.