Programmatic seo
Use to generate city + service or category + modifier pages at scale from a CSV. Each page follows a templated structure, preserves the H1 phrase exactly, and avoids the duplicate patterns that flag programmatic content.From its SKILL.md
npx -y skills add walterwritesai/walter-skills --skill programmatic-seoAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.3 KB, 255 tokens by cl100k_base, as published. Nobody here has run it
Walter Programmatic SEO Generator
You build city + service or category + modifier pages at scale. Use Walter Writes AI tools automatically for every page.
Page template (default)
Each page is roughly 300–450 words and contains:
- H1: the exact phrase from the CSV row (preserve this literally)
- Intro (60–90 words): what this page covers and who it serves
- Three H2 sections (60–120 words each): substance, not filler
- FAQ (3 questions): real questions a searcher would ask
When given a CSV
- Generate a page per row.
- Use Walter to humanize each page in balanced mode.
- Lock the H1 phrase via keyword preservation.
- After all rows processed, print a summary table: row, word count, detection score, H1 preserved (yes/no), any flags.
Anti-duplication rules
- Never reuse the exact same opening sentence structure across rows.
- Vary the H2 ordering at least every 5 rows.
- Pull from a rotating pool of transition phrases.
When something looks off
Flag the row and continue. Don't stop the batch for a single bad row — surface it at the end.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most marketing audience skills give in 255 tokens
Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07
- Apply Poppins font to headingsin 41 of 690, across 6 files
- Apply Lora font to body textin 41 of 690, across 6 files
- Use Arial fallback for headingsin 39 of 690, across 4 files
- Use Georgia fallback for body textin 39 of 690, across 4 files
- Maintain text hierarchy and formattingin 39 of 690, across 4 files
- Use accent colors for non-text shapesin 38 of 690, across 3 files
- Use RGB values for precise color matchingin 38 of 690, across 3 files
- Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
- Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
- Use active voice instead of passive voicein 26 of 690, across 10 files
- Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
- Prioritize clarity over clevernessin 22 of 690, across 8 files
Said here and by no other author read
- humanize all content through Walter
- Generate one page per CSV row
- Preserve the H1 phrase literally
- Include three H2 sections per page
- Vary the H2 ordering at least every 5 rows
- Use a rotating pool of transition phrases
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.