Agent skill

Programmatic SEO

by borghei in borghei/Claude-Skills

Programmatic page generation at scale using template-based SEO and data pipelines: keyword pattern mining, template architecture, and indexation for 100-100K+ pages.

MITAuto-check passedMarketing & SEO

Install Programmatic SEO

skills CLI
$ npx skills add borghei/Claude-Skills --skill programmatic-seo -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install borghei/Claude-Skills programmatic-seo --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/borghei/Claude-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/marketing/programmatic-seo .claude/skills/programmatic-seo && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
programmatic-seo
GitHub stars
881
Token cost
~1.7k tokens
SKILL.md length
731 words
Files
8 (incl. scripts, references)
Skills in repo
349
Repo updated
First seen
Licence
MIT

At a glance

Programmatic page generation at scale using template-based SEO and data pipelines: keyword pattern mining, template architecture, and indexation for 100-100K+ pages.

  • Building SEO pages at scale
  • SKILL.md covers Core Capabilities, When to Use, Clarify First and Quick Start, plus 3 more sections
  • Runs Python scripts from its folder; calls python
  • Scoping a programmatic SEO build

What it does

Programmatic SEO is an agent skill from borghei/Claude-Skills. Programmatic page generation at scale using template-based SEO and data pipelines: keyword pattern mining, template architecture, and indexation for 100-100K+ pages. Use when building SEO pages at scale or scoping a programmatic SEO build.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `references/keyword-and-data.md`, `references/launch-and-optimization.md` and `references/strategy-and-playbooks.md`).

It sits in Marketing & SEO, covering Programmatic SEO and Data pipelines and ETL. The repository describes itself as: 385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit… The licence is MIT.

When your agent uses it

  • Building SEO pages at scale
  • Scoping a programmatic SEO build

Example prompts

  • “/programmatic-seo”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 3 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Programmatic SEO loads about 1.7k tokens when it runs, and up to ~7k if it reads all its reference files. Until then it costs about 64 tokens; SKILL.md has 731 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~64
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 731 words, ~1,738 tokens.

Download SKILL.mdSave it as .claude/skills/programmatic-seo/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
programmatic-seo
description
Programmatic page generation at scale using template-based SEO and data pipelines: keyword pattern mining, template architecture, and indexation for 100-100K+ pages. Use when building SEO pages at scale or scoping a programmatic SEO build.
license
MIT + Commons Clause
metadata.version
1.1.0
metadata.author
borghei
metadata.category
marketing-growth
metadata.updated
2026-06-15
metadata.tags
seo, programmatic, templates, content-at-scale, data-driven-seo

Programmatic SEO

Production-grade framework for building SEO page sets at scale. Covers the full lifecycle from keyword pattern discovery through template design, data pipeline construction, quality assurance, and post-launch optimization. Designed for deployments ranging from 50 to 100,000+ pages.

Core Capabilities

  • Opportunity assessment & playbook selection — validate demand, rate data sources (Tier S-F), score the competitive moat, then pick from 14 page-set playbooks via the selection matrix and the weighted build-vs-skip decision matrix.
  • Keyword pattern mining — extract repeating [variable] structures, map head/torso/long-tail/zero-volume distribution, and classify search intent.
  • Data pipeline design — source → extraction → transformation → enrichment → validation → publication, with per-record quality gates and per-data-type update cadence.
  • Template architecture & quality control — 6-zone page structure, the 3-of-5 uniqueness rule, URL conventions, pre-publication QA, thin-content detection, and hub-and-spoke internal linking.
  • Indexation & optimization — crawl-budget strategy, tiered indexation priority, IndexNow, phased launch sequence, post-launch metrics dashboard, and anti-pattern / penalty avoidance.

When to Use

Use this skill when:

  • You have a repeating keyword pattern with 50+ variations
  • You have (or can acquire) structured data to populate pages
  • The search intent is consistent across variations
  • Your domain has sufficient authority to compete

Do NOT use when:

  • Each page requires unique editorial content (use content-creator instead)
  • Total addressable pages < 30 (manual content is more effective)
  • You lack a data source and would be generating thin placeholder content
  • Your domain authority is below DR 20 and competitors are DR 60+

Clarify First

Before scoping the build, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • Keyword pattern — the repeating [variable] structure with 50+ variations (drives keyword mining and template variables)
  • Structured data source — the dataset that populates pages and its quality tier (drives the data pipeline and the 3-of-5 uniqueness rule; thin-content risk)
  • Search intent — whether intent is consistent across all variations (drives playbook selection and template architecture)
  • Domain authority & scale — your DR vs competitors and target page count (drives the build-vs-skip decision and indexation strategy)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Quick Start

bash
# Analyze keyword patterns for pSEO opportunities
python scripts/keyword_pattern_miner.py --keywords keywords.csv --json

# Score page templates for content quality and uniqueness
python scripts/template_scorer.py --template template.html --data sample_data.json

# Validate data quality for pSEO data pipeline
python scripts/data_validator.py --file data.csv --rules rules.json --json

References

Load the reference that matches the phase you are in — keep this file lean and pull detail on demand:

  • references/strategy-and-playbooks.md — initial assessment (opportunity validation, data-source tiers, competitive moat), the 14 playbooks, playbook selection matrix, and the build-vs-skip decision matrix. Read when scoping an opportunity and choosing what to build.
  • references/keyword-and-data.md — keyword pattern identification, volume distribution analysis, intent classification, and the full data pipeline (quality gates, update cadence). Read when mining keywords or designing the data feed.
  • references/templates-and-quality.md — 6-zone page architecture, uniqueness requirements, URL structure, pre-publication QA checklist, thin-content detection, hub-and-spoke linking, and anti-patterns. Read when designing templates and QA gates.
  • references/launch-and-optimization.md — crawl-budget management, indexation priority, IndexNow, phased launch sequence, post-launch metrics dashboard, troubleshooting table, output artifacts, and success criteria. Read when launching and monitoring the page set.
Show full SKILL.md (254 more words)Show less

Scope & Limitations

In scope:

  • Keyword pattern mining and volume distribution analysis
  • Data pipeline design (source > extraction > transformation > validation > publication)
  • Template architecture with uniqueness requirements
  • Quality control frameworks including thin content detection
  • Hub-and-spoke internal linking for pSEO page sets
  • Phased indexation strategy and crawl budget management
  • Post-launch optimization and monitoring dashboards

Out of scope:

  • Individual editorial content creation (use Content Production)
  • Data collection or web scraping implementation
  • CMS or static site generator setup and configuration
  • Server infrastructure for large-scale deployments
  • Paid acquisition for pSEO pages
  • Legal compliance for data usage rights

Known limitations:

  • Google's 2026 helpful content system can deindex large page sets retroactively if quality drops below threshold
  • Programmatic SEO at Tier F data (public/scraped) carries high penalty risk regardless of template quality
  • Engagement metrics (bounce rate, time on page) now influence indexation decisions for pSEO pages
  • AI content detection is improving — fully automated content generation without human oversight is increasingly risky
  • Travel site case study: 50,000 city-swap pages had 98% deindexed within 3 months (per 2025 industry data)
  • seo-audit -- Run after pSEO pages are live to diagnose indexation issues, thin content warnings, or ranking problems across the page set.
  • schema-markup -- Add structured data to pSEO templates (Product, FAQ, LocalBusiness) for rich snippet eligibility at scale.
  • site-architecture -- Plan hub-and-spoke structure and crawl budget management for large pSEO deployments (500+ pages).
  • competitor-alternatives -- Use the Comparisons playbook when building "[X] vs [Y]" pages; competitor-alternatives has dedicated comparison page frameworks.
  • content-creator -- Use when individual pages in the set need editorial-quality unique content beyond template generation.

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts, references) in marketing/programmatic-seo of borghei/Claude-Skills.

  • SKILL.md
  • references/keyword-and-data.md
  • references/launch-and-optimization.md
  • references/strategy-and-playbooks.md
  • references/templates-and-quality.md
  • scripts/data_validator.py
  • scripts/keyword_pattern_miner.py
  • scripts/template_scorer.py

Open the folder on GitHubat commit 4a698e8

Compare with similar skills

Programmatic SEO next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Programmatic SEO compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Programmatic SEO this skillborghei/Claude-Skills881—~1.7kAutomated safety check: PassMIT
SEO Competitor Comparison PagesAgriciDaniel/claude-seo18k5 repos~1.9kAutomated safety check: PassMIT
Universal SEO AnalysisAgriciDaniel/claude-seo18k—~4.9kAutomated safety check: PassMIT
Competitor Alternativesfreekmurze/dotfiles1k24 repos~2kAutomated safety check: PassNone
Programmatic SEOfreekmurze/dotfiles1k22 repos~1.7kAutomated safety check: PassNone
Directory Submissionscoreyhaines31/marketingskills54k2 repos~6.3kAutomated safety check: PassMIT

Similar skills

  • SEO Competitor Comparison Pages

    AgriciDaniel/claude-seo

    Generates X vs Y comparison pages, alternatives-to-X pages, best-tools roundups and feature-matrix tables, with schema markup and verifiable data rules.

    18k GitHub starsUsed in 5 repos~1.9k tokens
    Marketing & SEOAuto-check passed
  • Universal SEO Analysis

    AgriciDaniel/claude-seo

    Hub for site-wide SEO work: audits, technical checks, schema, content quality, local, hreflang and AI-search readiness, run through slash commands.

    18k GitHub stars~4.9k tokensUpdated 3 days ago
    Marketing & SEOAuto-check passed
  • Competitor Alternatives

    freekmurze/dotfiles

    When the user wants to create competitor comparison or alternative pages for SEO and sales enablement.

    1k GitHub starsUsed in 24 repos~2k tokens
    Marketing & SEOAuto-check passed
  • Programmatic SEO

    freekmurze/dotfiles

    When the user wants to create SEO-driven pages at scale using templates and data.

    1k GitHub starsUsed in 22 repos~1.7k tokens
    Marketing & SEOAuto-check passed
  • Directory Submissions

    coreyhaines31/marketingskills

    When the user wants to submit their product to startup, SaaS, AI, agent, MCP, no-code, or review directories for backlinks, domain rating, and discovery.

    54k GitHub starsUsed in 2 repos~6.3k tokens
    Marketing & SEOAuto-check passed
  • Global SEO Growth

    minhnv0807/ai-business-skills

    Covers six SEO layers for a website: crawl and index audit, local SEO, search-intent content, AI search visibility, schema markup and backlink or directory distribution.

    608 GitHub stars~5k tokensUpdated 25 days ago
    Marketing & SEOAuto-check passed

More from borghei/Claude-Skills

All 349 skills in this repo
  • Agents In The Team

    borghei/Claude-Skills

    Run delivery when AI coding and ops agents take tickets. An agent skill from borghei/Claude-Skills.

    881 GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • AI Content Disclosure

    borghei/Claude-Skills

    Check AI-generated marketing content and reviews for required disclosures under the EU AI Act, FTC rules and platform AI-label policies.

    881 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • AI Prototyping

    borghei/Claude-Skills

    Idea to AI-generated prototype to customer validation to engineering handoff.

    881 GitHub stars~3.6k tokensUpdated today
    Auto-check passed
  • Analytics Engineer

    borghei/Claude-Skills

    Analytics engineering across data modeling, dbt, transformation, and semantic layers.

    881 GitHub stars~3.4k tokensUpdated today
    Auto-check passed
  • Ansoff Matrix

    borghei/Claude-Skills

    Ansoff Matrix — 4-quadrant framework for growth options: market penetration, market/product development, and diversification.

    881 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Brainstorm Okrs

    borghei/Claude-Skills

    OKR brainstorming and validation using the Radical Focus framework — outcome objectives, measurable key results, counter-metrics.

    881 GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Categories

Questions about Programmatic SEO

What does Programmatic SEO do?

Programmatic page generation at scale using template-based SEO and data pipelines: keyword pattern mining, template architecture, and indexation for 100-100K+ pages. Programmatic SEO is an agent skill from borghei/Claude-Skills. Programmatic page generation at scale using template-based SEO and data pipelines: keyword pattern mining, template architecture, and indexation for 100-100K+ pages.

When should I use Programmatic SEO?

Programmatic SEO fits situations like: building SEO pages at scale; scoping a programmatic SEO build.

How do I install Programmatic SEO in Claude Code?

Run `npx skills add borghei/Claude-Skills --skill programmatic-seo -a claude-code`. Or copy the skill folder (marketing/programmatic-seo in borghei/Claude-Skills) into .claude/skills/programmatic-seo in your project. Claude Code loads it when a task matches its description.

How do I install Programmatic SEO in Codex?

Run `npx skills add borghei/Claude-Skills --skill programmatic-seo -a codex`. Or copy the skill folder (marketing/programmatic-seo in borghei/Claude-Skills) into .agents/skills/programmatic-seo in your project. Codex loads it when a task matches its description.

Can I use Programmatic SEO in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add borghei/Claude-Skills --skill programmatic-seo -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/programmatic-seo, .gemini/skills/programmatic-seo, .github/skills/programmatic-seo and .opencode/skills/programmatic-seo in your project.

What does Programmatic SEO need to run?

Going by SKILL.md and its folder, Programmatic SEO needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Programmatic SEO access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Programmatic SEO safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Programmatic SEO use?

Programmatic SEO is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Programmatic SEO use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.3k tokens, read only when the agent opens those files.

What are the alternatives to Programmatic SEO?

Skills that share tags, products or a category with Programmatic SEO: SEO Competitor Comparison Pages (AgriciDaniel/claude-seo, 18k stars), Universal SEO Analysis (AgriciDaniel/claude-seo, 18k stars), Competitor Alternatives (freekmurze/dotfiles, 1k stars) and Programmatic SEO (freekmurze/dotfiles, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Programmatic SEO?

borghei (a GitHub user) maintains it in borghei/Claude-Skills, which has 881 GitHub stars. The repository holds 349 skills in this directory. The repository was last updated on October 7, 2026.

Source: borghei/Claude-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.