agentleFS
pobstetapobsteta/aigora/.claude/skills/content-writer/SKILL.md

content-writer

Skill0 starsChanged 45 days agoMITView on GitHub

Create content in the user's voice — LinkedIn posts, emails, blog posts, proposals, or ad copy. Use when user says "write a post about X", "draft an email to X", "create content about X", or "write copy for X".

13 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use content-planner, google-ads-audit and 1 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bradautomatesSkill

    content-planner

    Orchestrate comprehensive content research across X, Instagram, YouTube, and TikTok platforms. Runs all research skills in parallel via subagents, then aggregates findings into actionable content plans and platform-specific intelligence playbooks.

    Also in 3 projects that use this

  • itallstartedwithaideaSkill

    google-ads-audit

    Structured Google Ads account audit across 7 dimensions. Activate when the user asks to "audit my account", "check for problems", "find issues", "review my campaigns", or requests a comprehensive account health assessment. Delivers findings with severity ratings and prioritized action items.

    Also in 3 projects that use this

  • indranilbanerjeeSkill

    keyword-research

    Research keywords via the connected data source: intent, gaps. Grouping → keyword-cluster. \"what keywords should we target\"

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create content that sounds like the user, not like AI.

    line 10
  2. Very specific:

    If context/my-voice.md is a placeholder, tell the user to run the business-setup wizard first.

    line 19
  3. Distinctive:

    Use line breaks for readability

    line 36
  4. Distinctive:

    Never write without reading the voice guide first

    line 77
  5. Distinctive:

    Never present first drafts as final — always do the voice check

    line 78
  6. Distinctive:

    If the user doesn't like the output, ask what specifically doesn't sound like them and update the voice guide

    line 79

“Common” is measured: kept by at least 6 in 10 of the 13 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

Content Writer

Create content that sounds like the user, not like AI.

Before Writing Anything

Mandatory reads:

  1. context/my-voice.md — How the user communicates
  2. context/my-business.md — Business context for relevance
  3. config/preferences.yaml — Platform preference, post length

If context/my-voice.md is a placeholder, tell the user to run the business-setup wizard first.

Process

  1. Understand intent — What type of content? What's the goal? Who's the audience?
  2. Read context files — Voice guide and business context (mandatory)
  3. Draft — Write content matching the user's voice
  4. Voice check — Review against voice guide. Does this sound like them or like AI?
  5. Refine — Fix any generic AI patterns (see anti-patterns below)
  6. Present — Show the content ready to use

Content Types

LinkedIn Posts

  • Short: ~300 characters (quick thought)
  • Medium: ~600 characters (insight + example)
  • Long: ~1200 characters (story + lesson + CTA)
  • Use line breaks for readability
  • Hook in the first line
  • End with engagement prompt or CTA

Emails

  • Subject line + body
  • Match user's email tone (usually different from social tone)
  • Professional but not stiff (unless that's their style)

Blog Posts

  • Structured with headers
  • User's voice throughout
  • Practical, not theoretical (unless requested)

Proposals

  • Professional, persuasive
  • Reference business context for credibility
  • Clear pricing/scope sections

AI Anti-Patterns (Never Use)

  • "In today's fast-paced world..."
  • "Let's dive in..."
  • "Here's the thing..."
  • "Game-changer"
  • "Leverage", "synergy", "ecosystem" (unless user actually uses these)
  • Starting every sentence with "I"
  • Generic motivational conclusions
  • Overusing em-dashes and semicolons

Input Sources

Content can be created from:

  • A topic ("write about lead generation")
  • A transcript ("turn this video into a post")
  • Notes ("here are my thoughts, clean them up")
  • A brief ("LinkedIn post, targeting CTOs, about AI automation")
  • An existing piece ("rewrite this in my voice")

Rules

  • Never write without reading the voice guide first
  • Never present first drafts as final — always do the voice check
  • If the user doesn't like the output, ask what specifically doesn't sound like them and update the voice guide

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.