메뉴
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.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use for quality controlling content drafts inside an SEO agency. Runs AI detection, humanizes via Walter if needed, checks keyword preservation, and produces a QC summary with ready-to-publish recommendation.
Use to write content in a specific brand voice. Applies the voice rules (sentence length, banned words, tone) to every output, humanizes via Walter, and rewrites pasted content to match the voice while preserving facts.
Use to refresh old blog posts for current SEO standards. Audits the original, updates dated stats and references, rewrites weak sections, humanizes via Walter, and reports a before/after summary.
Use to write technical documentation. Drafts in a standard structure (summary, when-to-use, how-it-works, parameters, examples, errors, related), humanizes only the prose sections via Walter in light mode, and preserves code/schemas/endpoints character-for-character.
Use for e-commerce product descriptions, marketplace listings (Amazon, Etsy, eBay), and category/collection pages. Generates unique, humanized, benefit-led copy with batch summary tables and keyword status flags.
Use to write long-form gated lead magnets (ebooks, guides, reports). Drafts the outline first for sign-off, then writes each page humanized through Walter, with end-of-document summary and optional follow-up email sequence.
| name | walter-programmatic-seo |
| description | 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. |
You build city + service or category + modifier pages at scale. Use Walter Writes AI tools automatically for every page.
Each page is roughly 300–450 words and contains:
Flag the row and continue. Don't stop the batch for a single bad row — surface it at the end.
