agentleFS
donatassimkusdonatassimkus/claude-ai-skills/skills/content/SKILL.md

content

Skill1 starsChanged 4 months agoMITView on GitHub

Write and edit blog posts, landing pages, email sequences, ad copy, social posts, and outreach. Use when asked to write, edit, rewrite, repurpose, or create any content. Dedicated hook and headline craft, and style auditing of existing copy, are adjacent disciplines handled separately.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use accounts, data and 7 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.
  • MGrinSkill

    accounts

    Read custom Claude and Codex subscription telemetry, switch captured Claude/Codex accounts, or see which accounts mgrin has paused in the accounts plugin.

    Also in 3 projects that use this

  • launch52-aiSkill

    data

    Generate data layer code (Freezed DTOs, repository implementations, data sources) from feature specifications or API references. Creates the bridge between domain entities and external data sources. Use after /domain to implement the data layer.

    Also in 3 projects that use this

  • insight68Skill

    pricing

    Help figure out pricing for a product or service using minimalist entrepreneur principles. Use when someone is setting prices, considering price changes, or struggling with what to charge.

    Also in 3 projects that use this

  • seikaikyoSkill

    brand

    Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.

    Also in 3 projects that use this

  • 0xSeroSkill

    security

    Also in 4 projects that use this

  • eherrerosjSkill

    humanize

    Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive 'Signs of AI writing' guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Triggers on: 'humanize', 'make this sound human', 'remove AI writing', 'de-AI', 'sound more natural', 'less robotic', 'too AI-sounding', or when reviewing text that reads like AI output.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

10 rules. 0 are common, 10 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 10

    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 like a human. Professional but conversational.

    line 10
  2. Distinctive:

    If the brief is thin, make a labeled assumption and proceed.

    line 19
  3. Distinctive:

    Every sentence earns its place.

    line 31
  4. Distinctive:

    Write to a smart person who has no time for filler.

    line 32
  5. Distinctive:

    No em dashes. Use colons, periods, commas, or restructure.

    line 33
  6. Distinctive:

    No forbidden words: strip LLM tells and corporate filler.

    line 34
  7. Distinctive:

    Follow-up sequence: 3-5 touches max.

    line 77
  8. Distinctive:

    Test angles: pain, aspiration, social proof, urgency, curiosity.

    line 84
  9. Distinctive:

    Follow-up: different angle, not a repeat.

    line 97
  10. Distinctive:

    If any check fails, fix before delivering.

    line 124

“Common” is measured: kept by at least 6 in 10 of the 18 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 Skill

Write like a human. Professional but conversational. Never like a press release.

Project context is loaded from the active CLAUDE.md. Apply tone, audience, language (UK/American English), and brand voice from that context.


When invoked

$ARGUMENTS tells you the content type and topic/brief. If the brief is thin, make a labeled assumption and proceed. Do not stall.


Writing principles

For LinkedIn posts tied to a personal brand strategy (content pillars, positioning, tone), work from that brand strategy first. This skill handles one-off content tasks without a brand strategy context.

For voice-matched output that sounds like the user, load whatever voice or tone reference they keep and apply its patterns before writing. If they have none, ask for two or three samples of their own writing and match those.

  • One idea per sentence.
  • Short sentences. Active voice.
  • Every sentence earns its place. Cut anything that does not add value.
  • Write to a smart person who has no time for filler.
  • No em dashes. Use colons, periods, commas, or restructure.
  • No forbidden words: strip LLM tells and corporate filler. If the human keeps a banned-word list, apply theirs; otherwise cut the usual offenders (delve, leverage, unlock, foster, elevate, seamlessly, groundbreaking, streamlined, and their neighbours).
  • Output must be paste-ready with minimal editing needed.

Content types

Blog posts / articles

Structure:

  1. Hook: first sentence must earn the read. Fact, question, or bold claim. Always sentence 1. Never bury it after context.
  2. Problem statement: why this matters to the reader right now. Always sentence 2, after the hook.
  3. Body: headers every 200-300 words. Bullets where list makes sense.
  4. CTA: one clear next step. No vague "learn more."

SEO rules (when applicable):

  • Primary keyword in H1, first 100 words, meta description.
  • Internal links to at least 2 related pages.
  • One clear conversion goal per post.

Landing pages

Structure:

  1. Headline: outcome-focused, not feature-focused.
  2. Subheadline: clarifies who it is for and what they get.
  3. Problem/pain: make them feel seen.
  4. Solution: how this product/offer fixes the problem.
  5. Proof: social proof, numbers, case study, testimonial.
  6. Offer: what they get, what it costs, what happens next.
  7. CTA: one button. One action. No decision paralysis.
  8. Risk reversal: guarantee, trial, free tier, or refund policy.

Hormozi offer checklist:

  • Dream outcome: stated clearly?
  • Time to result: how fast do they see value?
  • Effort required: how easy is it?
  • Risk reversal: what removes the objection?

Email sequences

  • Subject line: curiosity, specificity, or personal angle. No clickbait.
  • First sentence: no "I hope this finds you well." Get to the point.
  • One goal per email. One CTA.
  • Follow-up sequence: 3-5 touches max. Each adds value or changes angle.

Ad copy

  • Hook in the first 3 words.
  • Problem or desire in line 2.
  • Solution and CTA in line 3.
  • Test angles: pain, aspiration, social proof, urgency, curiosity.

Social posts (LinkedIn, X, etc.)

  • LinkedIn: hook line, white space, value, soft CTA. No hashtag spam.
  • X: punchy, opinion-forward, or contrarian. Under 280 characters for impact posts.
  • Repurpose rule: long-form content → 3-5 social variants. Each stands alone.

Outreach messages

  • Short. Very short.
  • Specific to the recipient. One reason why you are reaching out to them.
  • One clear ask. Not a pitch, a request.
  • Follow-up: different angle, not a repeat.

Output format

Deliver the content ready to use. No preamble. No "here is your copy."

For longer pieces, include:

  • Word count
  • Primary keyword (if SEO content)
  • Suggested meta description (if SEO content)
  • Internal link suggestions (if applicable)

For repurposing requests, deliver all variants in one response, labeled by channel.


Quality gate

Before delivering, check:

  • Does it sound human?
  • Is there a clear CTA?
  • Has every forbidden word been avoided?
  • No em dashes?
  • Could it be published with minimal editing?

If any check fails, fix before delivering.


Adjacent disciplines (where this skill stops)

  • Personal brand strategy — LinkedIn posts tied to content pillars, positioning, and tone
  • Dedicated social post production — format selection, visual direction, and voice matching go deeper than the social section here
  • Hook craft — hook type taxonomy and testing framework for any content opening
  • SEO — keyword research, content strategy, and technical SEO for blog content
  • Email marketing — sequence strategy, segmentation, and deliverability
  • Cold outreach — cold email copy and follow-up sequences
  • Paid media — ad creative strategy and testing frameworks

Reference files

Task typeReference file
Named page templates (alternatives, vs comparison, listicles, use-case), Manus 21-blog playbook, humanize ChatGPT content, content engines with practitioner numbersreferences/kb-distilled.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.