Seo programmatic

seo-programmatic: ship one capped batch of programmatic pages

When NOT to use this (read first)

Programmatic SEO is the fastest way to get a site deindexed when done wrong. Do NOT proceed if ANY of these holds:

• No verified search volume for the individual pages (a glossary term nobody searches is dead weight that dilutes the whole site).
• Nothing UNIQUE to say per page: if two pages would share 80% of their content, the cluster is one article, not a page set.
• The site is young: fewer than ~10 indexed editorial pieces. Programmatic pages ride on existing site trust; they do not create it.
• The goal is page count. Google's spam policies name "scaled content abuse" explicitly; mass thin pages put the entire domain at risk, not just the batch.

If blocked by these, say so, mark the topic skipped with the reason in angle, and suggest what would unblock it.

Before anything

1. Read SEO.md at the project root, in full. It is the only source of truth for product, audience, voice, rules, and paths. If it does not exist: stop and tell the user to run the seo-init skill (or fill SEO.template.md by hand).
2. Never invent product or audience facts that are not in SEO.md.
3. Default paths (overridable in SEO.md § State): backlog .seo/backlog.json.

Step 1: Pick the cluster and pattern

Take the top-priority todo of type programmatic or glossary from the backlog. If none: report and suggest seo-plan. STOP.

Pattern	Only when
Glossary	each term has verified definition-intent volume
X vs Y / alternatives	the ICP genuinely weighs these options; you can be honest about where the competitor wins
For-[industry]	each industry has distinct, nameable needs (not the same page with a swapped noun)
Templates / examples	each template is genuinely usable, not a placeholder

Step 2: Build the dataset BEFORE any page

Create a table (one row per future page) with the columns that will make each page unique: facts, numbers, features, pricing, quirks, use cases. Research each row for real (WebSearch, product pages, real screenshots per the SEO.md screenshot rule).

The row rule: a row you cannot fill with unique, verified values is a page that does not get created. This single rule is what separates programmatic SEO from spam.

Step 3: Generate template + pages

• One template in the host content system (SEO.md § Content System), pages generated from the dataset rows.
• Per-page minimum UNIQUE content (shared boilerplate does not count toward it): glossary 400 words; comparisons and alternatives 700 words; for-industry 700 words.
• Each page: meta title 50-60 chars with its keyword, description 140-160, voice and banned patterns per SEO.md.
• A hub page links every child; siblings cross-link where relevant; 1-2 published articles link to the hub.

Step 4: Batch discipline

• Cap per run: SEO.md § Content Mix & Cadence (default 10 pages). A 40-term glossary ships in 4+ runs, weeks apart.
• One batch = one coherent cluster. Never mix patterns in a run.
• Stagger publishedAt across the batch (realistic past window, at most one page dated today), exactly as in seo-write's batch rule.

Step 5: Quality gate (blocking)

• Pick 3 random pages from the batch; verify each against the unique-content minimum (sed + wc technique from seo-write, minus the shared boilerplate).
• Banned-pattern grep clean across the batch.
• Diff two sibling pages: if the diff is mostly the keyword swapped, the batch fails.
• Project build passes.

Then mark the backlog entry done (or update it with remaining rows if the cluster continues) and publish per the SEO.md publish mode.

Red flags: stop and re-read the top section

• "The volume is probably there for most terms"
• "I can raise the cap just this once, the pages are ready anyway"
• "The boilerplate is good enough content"
• "Swapping the industry name is basically customization"

Never do

• Uncapped generation, whatever the excuse.
• Pages for zero-volume or unverified-volume terms.
• Near-duplicate siblings.
• Publishing the whole batch dated the same day.