agentleFS
Sign inStart free
ArogyaReddyArogyaReddy/alirezarezvani-claude-skills/marketing-skill/CLAUDE.md

alirezarezvani-claude-skills / marketing-skill

CLAUDE.md31 starsChanged 8 months agoMITView on GitHub

This directory contains 43 marketing skills organized into specialist pods. 32 scripts, all stdlib-only. Run directly: No pip install needed. Scripts include embedded samples for demo mode (run with no args). ❌ Don't read all 43 SKILL.md files ❌ Don't skip marketing-context.md if it exists ❌ Don't use content-creator (deprecated → use content-production) ❌ Don't install pip packages for Python tools

  • Installs packages

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

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Start with routing: Read marketing-ops/SKILL.md — it has a routing matrix that maps user requests to the right skill.

    line 9
  2. Very specific:

    Check context: If marketing-context.md exists, read it first.

    line 10
  3. Very specific:

    Load ONE skill: Read only the specialist SKILL.md you need.

    line 11
  4. Distinctive:

    No pip install needed. Scripts include embedded samples for demo mode (run with no args).

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 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

Marketing Skills — Agent Instructions

For All Agents (Claude Code, Codex CLI, OpenClaw)

This directory contains 43 marketing skills organized into specialist pods.

How to Use

  1. Start with routing: Read marketing-ops/SKILL.md — it has a routing matrix that maps user requests to the right skill.
  2. Check context: If marketing-context.md exists, read it first. It has brand voice, personas, and competitive landscape.
  3. Load ONE skill: Read only the specialist SKILL.md you need. Never bulk-load.

Skill Map

  • marketing-context/ — Run first to capture brand context
  • marketing-ops/ — Router (read this to know where to go)
  • content-production/ — Write content (blog posts, articles, guides)
  • content-strategy/ — Plan what content to create
  • ai-seo/ — Optimize for AI search engines (ChatGPT, Perplexity, Google AI)
  • seo-audit/ — Traditional SEO audit
  • page-cro/ — Conversion rate optimization
  • pricing-strategy/ — Pricing and packaging
  • content-humanizer/ — Fix AI-sounding content
  • x-twitter-growth/ — X/Twitter audience growth, tweet composing, competitor analysis

Python Tools

32 scripts, all stdlib-only. Run directly:

python3 <skill>/scripts/<tool>.py [args]

No pip install needed. Scripts include embedded samples for demo mode (run with no args).

Anti-Patterns

❌ Don't read all 43 SKILL.md files ❌ Don't skip marketing-context.md if it exists ❌ Don't use content-creator (deprecated → use content-production) ❌ Don't install pip packages for Python tools

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.

Reviews can't be read right now.

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.

Check your setup, free