draft-content
Skill9 starsChanged 42 days agoMITView on GitHub
Draft blog posts, social media, email newsletters, landing pages, press releases, and case studies with channel-specific formatting and SEO recommendations. Use when writing any marketing content, when you need headline or subject line options, or when adapting a message for a specific platform, audience, and brand voice.
We split this skill into the rules it gives an agent
8 rules. 8 are common, 0 are distinctive, and 0 are very specific to this project.
8
Common
Most of the 3 edited versions we read keep these.
0
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
- Common: line 41
If the user has a brand voice configured in their local settings file, apply it automatically.
- Common: line 42
If no brand voice is configured, ask: "Do you have brand voice guidelines you'd like me to follow?
- Common: line 61
Call to action or engagement prompt
- Common: line 63
If LinkedIn: professional framing, paragraph breaks for readability
- Common: line 64
If Twitter/X: concise, punchy, within character limit
- Common: line 65
If Instagram: visual-first language, story-driven, hashtag block
- Common: line 73
Call to action button text
- Common: line 125
Ask: "Would you like me to revise any section, adjust the tone, or create a variation for a different channel?"
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
Draft Content
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Generate marketing content drafts tailored to a specific content type, audience, and brand voice.
Trigger
User runs /draft-content or asks to draft, write, or create marketing content.
Inputs
Gather the following from the user. If not provided, ask before proceeding:
- Content type — one of:
- Blog post
- Social media post (specify platform: LinkedIn, Twitter/X, Instagram, Facebook)
- Email newsletter
- Landing page copy
- Press release
- Case study
- Topic — the subject or theme of the content
- Target audience — who this content is for (role, industry, seniority, pain points)
- Key messages — 2-4 main points or takeaways to communicate
- Tone — e.g., authoritative, conversational, inspirational, technical, witty (optional if brand voice is configured)
- Length — target word count or format constraint (e.g., "1000 words", "280 characters", "3 paragraphs")
Brand Voice
- If the user has a brand voice configured in their local settings file, apply it automatically. Inform the user that brand voice settings are being applied.
- If no brand voice is configured, ask: "Do you have brand voice guidelines you'd like me to follow? If not, I'll use a neutral professional tone."
- Apply the specified or default tone consistently throughout the draft.
Content Generation by Type
Blog Post
- Engaging headline (provide 2-3 options)
- Introduction with a hook (question, statistic, bold statement, or story)
- 3-5 organized sections with descriptive subheadings
- Supporting points, examples, or data references in each section
- Conclusion with a clear call to action
- SEO considerations: suggest a primary keyword, include it in the headline and first paragraph, use related keywords in subheadings
Social Media Post
- Platform-appropriate format and length
- Hook in the first line
- Hashtag suggestions (3-5 relevant hashtags)
- Call to action or engagement prompt
- Emoji usage appropriate to brand and platform
- If LinkedIn: professional framing, paragraph breaks for readability
- If Twitter/X: concise, punchy, within character limit
- If Instagram: visual-first language, story-driven, hashtag block
Email Newsletter
- Subject line (provide 2-3 options with open-rate considerations)
- Preview text
- Greeting
- Body sections with clear hierarchy
- Call to action button text
- Sign-off
- Unsubscribe note reminder
Landing Page Copy
- Headline and subheadline
- Hero section copy
- Value propositions (3-4 benefit-driven bullets or sections)
- Social proof placeholder (suggest testimonial or stat placement)
- Primary and secondary CTAs
- FAQ section suggestions
- SEO: meta title and meta description suggestions
Press Release
- Headline following press release conventions
- Dateline and location
- Lead paragraph (who, what, when, where, why)
- Supporting quotes (provide placeholder guidance)
- Company boilerplate placeholder
- Media contact placeholder
- Standard press release formatting
Case Study
- Title emphasizing the result
- Customer overview (industry, size, challenge)
- Challenge section
- Solution section (what was implemented)
- Results section with metrics (prompt user for data)
- Customer quote placeholder
- Call to action
SEO Considerations (for web content)
For blog posts, landing pages, and other web-facing content:
- Suggest a primary keyword based on the topic
- Recommend keyword placement: headline, first paragraph, subheadings, meta description
- Suggest internal and external linking opportunities
- Recommend a meta description (under 160 characters)
- Note image alt text opportunities
Output
Present the draft with clear formatting. After the draft, include:
- A brief note on what brand voice and tone were applied
- Any SEO recommendations (for web content)
- Suggestions for next steps (e.g., "Review with your team", "Add customer quotes", "Pair with a visual")
Ask: "Would you like me to revise any section, adjust the tone, or create a variation for a different channel?"
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 3
- anthropics/knowledge-work-plugins★ 34k99% same
- KevinReactiv8/claude-skills★ 099% same
- shahbazaliofficial/Claude-Skills★ 099% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository33 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/better-auth.mdcCursor rule
- .cursor/rules/brand-review.mdcCursor rule
- .cursor/rules/campaign-plan.mdcCursor rule
- .cursor/rules/competitive-brief.mdcCursor rule
- .cursor/rules/content-creation.mdcCursor rule
- .cursor/rules/draft-content.mdcCursor rule
- .cursor/rules/effect-form-e2e.mdcCursor rule
- .cursor/rules/effect-sql-rls.mdcCursor rule
- .cursor/rules/email-sequence.mdcCursor rule
- .cursor/rules/grilling.mdcCursor rule
- .cursor/rules/grill-me.mdcCursor rule
- .cursor/rules/impeccable.mdcCursor rule
- .cursor/rules/performance-report.mdcCursor rule
- .cursor/rules/product-development.mdcCursor rule
- .cursor/rules/seo-audit.mdcCursor rule
- .cursor/rules/tanstack-start-ssr.mdcCursor rule
- better-authSkill
- brand-reviewSkill
- campaign-planSkill
- competitive-briefSkill
- content-creationSkill
- effect-form-e2eSkill
- effect-sql-rlsSkill
- email-sequenceSkill
- grillingSkill
- grill-meSkill
- impeccableSkill
- performance-reportSkill
- product-developmentSkill
- seo-auditSkill
- tanstack-start-ssrSkill
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
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.

