Programmatic SEO
Design a programmatic SEO strategy for "$ARGUMENTS". Plan template-driven pages that target long-tail keywords at scale — landing pages, directories, comparison pages, or location-based pages.
Arguments. $ARGUMENTS may contain the project name and optional flags. Take the first token as <project> and treat --skip-checks as a flag; never include flags in file paths. All paths below use <project>. If --skip-checks is present, skip the prerequisite check and, before writing any artifact, append one line to .singularskills/log.jsonl: {"ts":"<ISO timestamp>","skill":"marketing-programmatic-seo","workflow":"marketing","phase":1,"project":"<project>","event":"skipped","artifact":"01-reach.md","note":"<reason or \"none given\">"}.
Prerequisites
Part of a workflow. This skill is phase 1 (Reach) of the RACE Framework workflow (marketing); cross-domain workflows run it too. First check .singularskills/log.jsonl for an open run for this project: a run-started line with "project":"<project>" and no later run-finished line for the same workflow and project. If one exists, the conductor is running you: continue here. Otherwise, if the user asked to start, run, continue or resume a process or workflow rather than this one step, do not continue here: invoke the workflow skill with the workflow the user asked for, or marketing when they named none, followed by <project>; it runs this phase in order, asks before it writes and records the run. Otherwise continue here: a later phase runs on its own, behind its gate.
Run this skill's gate before writing: sh <this skill's folder>/scripts/gate.sh <project> <project root>, where <project root> is the folder that contains .singularskills/ (use . when you are already there). If it exits non-zero, stop and tell the user what it printed, unless --skip-checks was given (see Arguments). On a refusal, before you stop, append this line to .singularskills/log.jsonl (create the folder and file if missing): {"ts":"<ISO timestamp>","skill":"marketing-programmatic-seo","workflow":"marketing","phase":1,"project":"<project>","event":"refused","artifact":"01-reach.md","note":"<what the gate printed>"}. Once the gate has passed, or under --skip-checks once you have appended the skipped line, append this line before you start work: {"ts":"<ISO timestamp>","skill":"marketing-programmatic-seo","workflow":"marketing","phase":1,"project":"<project>","event":"started","artifact":"01-reach.md","note":""}.
Read .singularskills/marketing/<project>/00-strategy.md and .singularskills/marketing/<project>/01-reach.md (if exists). If 00-strategy.md does not exist, tell the user:
Phase 0 (Strategy) has not been completed for "". Run
/marketing-customer-research <project>first, or use--skip-checksto bypass.
Process
Read context:
- Read
.singularskills/marketing/<project>/00-strategy.mdfor audience and competitive data - Read
.singularskills/marketing/<project>/01-reach.mdfor SEO and content context if available
- Read
Identify programmatic opportunities:
- Use WebSearch to find long-tail keyword patterns (e.g., "[tool] for [industry]", "[tool] vs [competitor]", "[tool] in [city]")
- Estimate total addressable keyword volume across templates
- Prioritize by search volume, competition, and conversion intent
Design page templates:
- For each template type: layout, required data fields, content structure
- How will unique value be added per page? (avoid thin content)
- Internal linking strategy between programmatic pages
- CTA and conversion path per template
Data source planning:
- What data populates each template? (database, API, manual, AI-generated)
- Data quality and freshness requirements
- Scale: how many pages in the initial launch?
Quality and indexing strategy:
- How to avoid duplicate or thin content penalties
- Indexing approach: sitemap, internal links, pagination
- Content enrichment strategy per page
Write the artifact — append to
.singularskills/marketing/<project>/01-reach.mdunder a## Programmatic SEOsection. Create the file with a# Reach — <project>heading if it does not exist; if a## Programmatic SEOsection already exists, replace only that section. The section contains:- Keyword Patterns — template types with volume estimates
- Page Templates — layout and content structure per type
- Data Sources — what populates each template
- Quality Plan — how to avoid thin content
- Implementation Roadmap — phases and page counts
Output
Programmatic SEO strategy appended to .singularskills/marketing/<project>/01-reach.md. Present a summary highlighting:
- Number of template types identified
- Total estimated keyword opportunity
- Recommended first template to build
Record the run. After you have written your section, append this line to .singularskills/log.jsonl (the started line of Prerequisites, with "event":"finished"): {"ts":"<ISO timestamp>","skill":"marketing-programmatic-seo","workflow":"marketing","phase":1,"project":"<project>","event":"finished","artifact":"01-reach.md","note":""}.
This artifact is shared by every skill of phase 1 (Reach). The frontmatter is written once, by whoever creates the file: if you create it, open it with the block below (skill is the phase title, started the time of that first write; gate is passed when the gate ran clean and skipped under --skip-checks); if it already exists, leave the block alone except to update finished and to set gate to the worst value among the sections (skipped over passed).
---
skill: Reach
workflow: marketing
phase: 1
project: <project>
started: <ISO timestamp>
finished: <ISO timestamp>
agent: <the agent you run in, or "unknown">
gate: <passed|skipped>
---
Open your ## Programmatic SEO section with one italic line, *<skill name> · <ISO timestamp> · gate: <passed|skipped>* (your skill name is marketing-programmatic-seo).
End your section with ### Decisions and ### Open questions (one level under your ## Programmatic SEO heading, so the section stays one block), in this shape:
### Decisions
- <what was chosen> — <why> — <what was rejected>
### Open questions
- <what the next phase or a reviewer must settle>