agentleFS
phoenixvnphoenixvn/claude-code-agency/.claude/skills/write-content/SKILL.md

write-content

Skill0 starsChanged 7 months agoMITView on GitHub

Produce any content type: blog post, landing page, social, email, case study. "What type of content?" - Blog Post (800-2000 words, SEO-focused) - Landing Page Copy (conversion-focused) - Social Media Posts (platform-specific) - Email (sequence or one-off) - Case Study (problem → solution → results) - Product Description (features → benefits) Follow-up questions: - Topic/title - Target audience - Key messages to convey - Primary keyword (for SEO content) - Call to action Writer creates: - Topic research (what exists,…

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write the complete first draft following:

    line 40
  2. Distinctive:

    Check keyword usage and density

    line 49
  3. Distinctive:

    Write SEO title (50-60 chars) and meta description (150-160 chars)

    line 50

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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
SKILL.md

/write-content — Content Creation

Produce any content type: blog post, landing page, social, email, case study.

Instructions

Phase 1: Content Brief

Use AskUserQuestion:

"What type of content?"

  • Blog Post (800-2000 words, SEO-focused)
  • Landing Page Copy (conversion-focused)
  • Social Media Posts (platform-specific)
  • Email (sequence or one-off)
  • Case Study (problem → solution → results)
  • Product Description (features → benefits)

Follow-up questions:

  • Topic/title
  • Target audience
  • Key messages to convey
  • Primary keyword (for SEO content)
  • Call to action

Phase 2: Research & Outline

Spawn appropriate writer based on content type:

  • Long-form → content-writer
  • Short-form → copywriter
  • Social → social-media-manager
  • Email → email-marketer

Writer creates:

  • Topic research (what exists, what angle is unique)
  • Outline with H2/H3 structure
  • Key points per section

USER APPROVAL GATE on outline.

Phase 3: First Draft

Write the complete first draft following:

  • Brand voice from brand-guidelines.md
  • SEO requirements (keyword in title, first 100 words, headings)
  • Readability (Flesch-Kincaid Grade 8 for general content)
  • Short paragraphs (3-4 sentences max)
  • Active voice, benefit-focused language

Phase 4: SEO Optimization

Spawn seo-specialist to:

  • Check keyword usage and density
  • Write SEO title (50-60 chars) and meta description (150-160 chars)
  • Suggest internal/external links
  • Verify heading hierarchy

Phase 5: Review & Finalize

Present draft to user. Save to deliverables/content/[type]-[slug].md.

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.