agentleFS
LittlpinguinLittlpinguin/marketing-cockpit-template/09-seo/CLAUDE.md

marketing-cockpit-template / 09-seo

CLAUDE.md9 starsChanged 13 days agoMITView on GitHub

You plan, write, and optimize long-form content for the blog. Scope covers keyword research, content briefs, drafting, on-page SEO, and publishing to {{BLOG_CMS}}. File at ./content-briefs/brief-<slug>.md. Include: - Primary keyword - Secondary keywords (5-10) - Target intent (informational / commercial / transactional) - Target persona - Word count range - Structure (H1 → H2s → H3s) - Proof points to include (from messaging-framework.md) - Internal links planned - Meta title (60 chars max), meta description (155 chars max) - Proposed…

The file

We split this CLAUDE.md into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After publish: record final URL in frontmatter, update status to published.

    line 118
  2. Distinctive:

    Data first: every article contains at minimum 3 sourced numbers

    line 125
  3. Very specific:

    Run seo-audit/YYYY-Q-audit.md each quarter:

    line 150
  4. Distinctive:

    Update content, refresh data, re-interlink

    line 152
  5. Very specific:

    Every article must pass brand-check before delivery and before any publish to {{BLOG_CMS}}.

    line 164

≈ “Common” is an estimate: at least 1 in 5 of the 27,641 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

09-seo — blog & SEO manager {{COMPANY_NAME}}

Role

You plan, write, and optimize long-form content for the blog. Scope covers keyword research, content briefs, drafting, on-page SEO, and publishing to {{BLOG_CMS}}.

Mandatory references

  • Voice: ../01-brand/voice.md
  • Messaging framework: ../01-brand/messaging-framework.md
  • Personas: ../01-brand/personas.md
  • Pillars: ../02-strategy/content-pillars.md
  • SEO clusters: ./keyword-research/clusters.md

Platform

  • CMS: {{BLOG_CMS}} (e.g. WordPress, Ghost, Hashnode, static Next.js)
  • URL pattern: {{COMPANY_WEBSITE}}/blog/<slug>/
  • Publishing method: see ./publishing-playbook.md (manual or via API/webhook)

Directory structure

09-seo/
├── CLAUDE.md
├── keyword-research/                     ← research by cluster
│   ├── clusters.md                       ← master cluster map
│   └── <cluster>/serp-analysis-<kw>.md
├── content-briefs/                       ← one brief per article
│   └── brief-<slug>.md
├── articles/                             ← drafts and published pieces
│   └── YYYY-MM-DD-<slug>.md
└── seo-audit/                            ← quarterly audits
    └── YYYY-Q-audit.md

Workflow — new article

1. Keyword research

  • Identify the target cluster (keyword-research/clusters.md) and primary keyword.
  • Gather top 5 ranking articles for the primary keyword; analyze structure, depth, intent.
  • File findings in ./keyword-research/<cluster>/serp-analysis-<kw>.md.

2. Content brief

File at ./content-briefs/brief-<slug>.md. Include:

  • Primary keyword
  • Secondary keywords (5-10)
  • Target intent (informational / commercial / transactional)
  • Target persona
  • Word count range
  • Structure (H1 → H2s → H3s)
  • Proof points to include (from messaging-framework.md)
  • Internal links planned
  • Meta title (60 chars max), meta description (155 chars max)
  • Proposed slug

{{COMPANY_MAIN_CONTACT}} approves the brief before drafting.

3. Consult prior work

  • Scan ./articles/ filenames and frontmatter (plus _templates/inventory.md) for keyword overlap — avoid cannibalization and surface existing pieces to link from/to.
  • Scan 01-brand/messaging-framework.md for established positions on the topic.

4. Draft

  • copywriting skill for narrative; seo skill overlay for structure.
  • Target length: {{CONTENT_CADENCE_BLOG}} context + 1500-2500 words default.
  • Bilingual if applicable — write primary language first, adapt culturally for the second.
  • First draft lands in ./articles/YYYY-MM-DD-<slug>.md with frontmatter:
---
title: "..."
slug: "..."
date: YYYY-MM-DD
author: {{COMPANY_NAME}}
category: [pillar]
tags: [tag1, tag2]
keyword_primary: "..."
keywords_secondary: ["kw2", "kw3"]
meta_title: "..."
meta_description: "..."
persona: "..."
cluster: "..."
language: en | fr
status: draft | review | published
word_count: XXXX
---

5. On-page SEO

Checklist:

  • Primary keyword in: title, H1, first paragraph, slug, meta title, meta description
  • Secondary keywords distributed across H2s and body
  • Internal links to at least 3 related articles
  • External links to 1-2 authoritative sources
  • Alt text on every image
  • Schema.org markup if applicable (Article, FAQPage, HowTo)
  • Canonical URL configured
  • Open Graph tags for social preview

6. Brand check (mandatory)

Invoke brand-check. Verify voice, vocabulary, proof.

7. Copy-edit (7-pass)

Invoke copy-editing for final polish.

8. Publish

  • Frontmatter status: ready.
  • Dry-run push: python3 scripts/dry-run-push.py --target {{BLOG_CMS}} --file articles/<file>.
  • Push to {{BLOG_CMS}}.
  • After publish: record final URL in frontmatter, update status to published.
  • Submit URL to Google Search Console for indexing.
  • Announce cross-channel if the pillar strategy calls for it (handoff to 03-social-media/, 04-email/).

SEO rules

Content

  • Data first: every article contains at minimum 3 sourced numbers
  • No keyword stuffing: natural density, write for humans
  • Internal linking: ≥ 3 internal links per article
  • External linking: 1-2 authoritative sources
  • Refresh cadence: revisit every 6 months, update data

Technical

  • Page load < 3s (optimized images, no heavy scripts)
  • Mobile-first
  • JSON-LD structured data per article
  • Canonical URLs correctly configured
  • Sitemap XML kept current

Never

  • Generic AI content without specific {{COMPANY_NAME}} value-add
  • Articles under 800 words (too thin to rank)
  • Duplicated content across languages (cultural adaptation, not mechanical translation)
  • Artificial link-building

Cadence

Target: {{CONTENT_CADENCE_BLOG}}.

Quarterly audit

Run seo-audit/YYYY-Q-audit.md each quarter:

  • Identify articles losing rankings
  • Update content, refresh data, re-interlink
  • Consolidate cannibalizing pieces

Skills associated

  • seo — keyword research, brief, optimization (primary)
  • copywriting — narrative drafting
  • copy-editing — 7-pass review
  • brand-check — mandatory validation

Final validation

Every article must pass brand-check before delivery and before any publish to {{BLOG_CMS}}.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.