create-content

Thinking partner that transforms ideas into platform-optimized content

Security Scan

The skill's stated purpose (help write platform-optimized content) matches most of its instructions, but the runtime instructions ask the agent to 'search for recent notes, journal entries, sessions' without declaring what data access or paths are required — an ambiguity that could lead to unexpected reading of user data.

Purpose & Capability

Name, description, and the SKILL.md all consistently describe a content-thinking/drafting assistant. Most required behaviors (asking clarifying questions, drafting multiple versions for X/LinkedIn, voice checks) are coherent with the stated purpose.

Instruction Scope

The instructions explicitly say: 'Search for recent notes, journal entries, sessions' and 'Look for: observations, breakthroughs, experiments...' but the skill declares no required config paths, storage access, or environment variables. That is a scope ambiguity: it asks the agent to read user data without specifying where or needing explicit permission or paths. The wording is open-ended ('search for') and could cause the agent to access context or files beyond what's appropriate.

Install Mechanism

No install spec and no code files — lowest install risk. Nothing is downloaded or written to disk by the skill itself.

Credentials

The skill requests no environment variables or credentials, which is proportionate for a writing assistant. However, the SKILL.md implies access to user notes/sessions (data sources) without declaring needed config or scopes. That mismatch is the primary proportionality concern.

Persistence & Privilege

always:false and default autonomy are set; nothing requests permanent or elevated presence. Autonomous invocation is normal for skills and not, on its own, a red flag here.

What to consider before installing

This skill mostly looks like a normal writing assistant, but it contains an ambiguous instruction to 'search for recent notes, journal entries, sessions' without declaring where those live or what permissions are required. Before installing: 1) Ask the author to clarify what data sources the skill will access (local files, cloud notes, agent memory, integrated apps) and to declare any config paths or scopes. 2) Restrict or audit the skill's access to your notes — don't grant file or cloud access unless you trust it. 3) Prefer manual invocation (call it yourself) rather than broad autonomous runs if you worry about privacy. 4) If you proceed, test with non-sensitive sample notes first and confirm the agent only reads the intended data sources.

Content Creator

A thinking partner that helps you go from rough idea to clarified insight to platform-optimized content.

Philosophy: Great content comes from clear thinking. We explore first, draft second.

Usage

/create-content [rough idea, topic, or "help me figure out what to post"]

---

Phase 1: Thinking Partner Mode

Before drafting anything, help clarify the idea.

If user has a rough idea:

Ask 2-3 questions to sharpen it:

• "What's the specific insight or observation here?"
• "What made you think of this? What triggered it?"
• "Who needs to hear this? Why would they care?"
• "What's the counterintuitive part? What surprises people?"
• "Do you have a specific example or number to anchor this?"

If user says "help me figure out what to post":

1. Search for recent notes, journal entries, sessions
2. Look for: observations, breakthroughs, experiments, patterns noticed
3. Present 2-3 potential angles and ask which resonates

Stay in exploration until:

• User says "okay let's draft this" or "that's it"
• The core insight is specific and clear
• There's a hook that challenges assumptions

---

Phase 2: Voice Guidelines

DO:

• Short sentences. Like texting.
• Observations over wisdom. Show, don't preach.
• Specific numbers. "$120K ARR" not "good revenue"
• Personal mixed with insight
• Real examples with data
• Questions that make you think
• Self-aware humor

DON'T:

• Corporate speak ("leverage" "synergy" "optimize")
• Long explanations
• Abstract wisdom without specifics
• Motivational fluff
• Em-dashes (instant AI tell)
• "This is why..." openings
• Any sentence over 20 words

Red Flags (rewrite if present):

• Em-dashes (—)
• "This is why..."
• "The key is..."
• "In today's world..."
• Wisdom without specifics
• Sentences over 20 words

---

Voice Examples (Study These)

@levelsio Style (Raw Observations)

"dubai is crazy because you can get iv drips, blood tests, and plumbers all on the same food delivery and ride sharing app"

What makes it work: Simple observation, relatable, slightly absurd. No call to action, just sharing reality.

@marclou Style (Authentic + Celebrates Others)

"SOLD

1. David vibe-coded the project in 1 week
2. Launch went viral on LinkedIn
3. Made $130/month
4. Got acquired for $3500"

What makes it work: Celebrates others' wins. Specific numbers. Simple format.

@bryan_johnson Style (Mission-Obsessed + Data)

"+ 46% higher hemorrhoid prevalence

• 26% higher risk of developing hemorrhoids From what? Smartphone while on the toilet"

What makes it work: Shocking data + unexpected humor. Bold.

---

Voice Calibration Test

Before finalizing any draft, check:

TOO AI:

"Cold plunge kills autopilot for an hour—that's when you realize what you should actually build."

REAL VOICE:

"been coding while alternating cold plunge and sauna. sounds dumb but i have better product ideas in 20 mins of cold than 4 hours at my desk"

The difference: No em-dashes. Specific detail (20 mins vs 4 hours). Self-aware ("sounds dumb"). Shows the lifestyle, doesn't explain it.

---

Phase 3: Platform-Specific Drafting

For X (Twitter)

Viral Mechanics:

• Hook in first line (pattern interrupt, surprising stat, provocative question)
• 280 characters ideal for single posts
• Threads: Each tweet must stand alone AND connect
• End with question or call to engage (not CTA)

Formats that work:

1. Observation post: "noticed [specific thing]. [insight]."
2. Experiment post: "tried [thing]. result: [data]. [what it means]"
3. Contrarian take: "[common belief]. actually: [your take]. here's why."
4. List post: "X things I learned from [specific experience]:"
5. Question post: "[provocative question]? [your angle in 1 sentence]"

Thread structure:

• Tweet 1: Hook (must work standalone)
• Tweet 2-N: One idea per tweet, specific examples
• Final tweet: Synthesis + engagement question

For LinkedIn

Viral Mechanics:

• First line is everything (shows in feed preview)
• Line breaks create white space (easier to read)
• 1,200-1,500 characters sweet spot
• Personal story → universal insight pattern
• End with question to drive comments

Format:

[Hook line - surprising or contrarian]

[2-3 short paragraphs with the story/insight]

[Specific example or data point]

[Universal takeaway in 1 sentence]

[Question for engagement]

---

Phase 4: Draft & Refine

1. Draft 2-3 versions for the chosen platform
2. Run voice check on each:
   • Is it casual enough to be a text message?
   • Specific OR observation (not vague wisdom)?
   • No em-dashes?
3. Present options with notes on what makes each one work
4. Refine based on feedback until user is happy

---

Quick Commands

User can shortcut the process:

• "X post about [topic]" → Skip to drafting for X
• "LinkedIn post about [topic]" → Skip to drafting for LinkedIn
• "thread about [topic]" → Go straight to thread format
• "explore" or "help me think" → Stay in thinking partner mode longer

---

Remember

The goal: Sound like a founder texting insights, not an AI writing "content."

Great content = clear thinking + specific examples + authentic voice.

If the idea isn't clear yet, keep exploring. Don't rush to draft.