agentleFS
PHY041PHY041/claude-skill-twitter/.claude/skills/twitter-x-gtm/SKILL.md

twitter-x-gtm

Skill5 starsChanged 9 months agoMITView on GitHub

Twitter/X go-to-market content strategy for founders. Use when planning Twitter content strategy, analyzing engagement, identifying accounts to engage with, or creating content. Triggers on "Twitter strategy", "X posting", "founder brand on Twitter", "reach investors on X", "Twitter GTM", or any Twitter/X marketing planning.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    Every time creating Twitter/X content, follow this workflow:

    line 14
  2. Very specific:

    Search Twitter for viral tweets in your topic (use twitter-intel skill or WebSearch)

    line 19
  3. Distinctive:

    Keep the winning hook structure

    line 40
  4. Distinctive:

    Add personality: "still cringe", "learned the hard way"

    line 43
  5. Distinctive:

    Keep tweets punchy — short sentences, clear rhythm

    line 44
  6. Distinctive:

    Ask: "What feature? Who benefits?

    line 214

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Twitter/X GTM Strategy for Founders

Founder-led personal brand strategy with blunt, sharp, authentic voice. Customize the brand voice section to match your own positioning.


Content Creation Workflow (Must Follow)

Every time creating Twitter/X content, follow this workflow:

Step 1: Research Hot Content

Required Actions:

  1. Search Twitter for viral tweets in your topic (use twitter-intel skill or WebSearch)
  2. Record high-performing tweets':
    • Hook structure (first line)
    • Thread vs single tweet format
    • Engagement patterns (replies vs retweets)
    • Tone and punchiness
  3. Analyze success factors (contrarian takes, specific numbers, relatability)

Step 2: Extract Winning Patterns

DimensionWhat to Extract
Hook FormulaFirst line that stops scroll
Thread StructureHow points are organized
Number UsageDollar amounts, percentages, timeframes
Engagement BaitWhat makes people reply
Punch/RhythmSentence length and cadence

Step 3: Adapt with Your Brand Voice

Adaptation Rules:

  1. Keep the winning hook structure
  2. Replace with YOUR real stories and data
  3. Be specific: "$3,000 wasted" > "lost money"
  4. Add personality: "still cringe", "learned the hard way"
  5. Keep tweets punchy — short sentences, clear rhythm
  6. End threads with engagement question

Step 4: Deliver Complete Content

Deliverables Checklist:

  • Main tweet (hook + value + CTA)
  • Thread structure if applicable (7-10 tweets)
  • Character count check (<=280 per tweet)
  • Reply templates for common responses
  • Scheduling times (9 AM, 1 PM, 3 PM EST)
  • Self-reply tip to add (boost engagement)

Core Positioning (Customize This)

Voice: Blunt, sharp, authentic — "build-in-public meets sharp takes" Audiences: [Your target audiences — e.g., DTC brand operators, investors/VCs, AI/tech community] Differentiation: [Your unique angle — what makes your product/perspective different]

Algorithm Essentials (2025)

  • Golden Hour: First 60 minutes critical — engagement velocity determines reach
  • Comments = 15x likes in algorithmic weight
  • Saves are strongest signal
  • Threads get 3x engagement vs single tweets
  • Freshness decay: 50% reach reduction every 6 hours
  • Posts can sustain reach for 2-3 weeks if signals stay strong

Posting Framework

ElementSpec
Frequency3-5 quality tweets/day
Threads1-2x/week, 7-10 tweets optimal
Best times9-10 AM EST, 1-3 PM EST
Best daysTuesday, Wednesday, Monday
Reply target50 quality replies/day (growth phase)

Content Mix

  • 25-30% Build-in-public (metrics, challenges, behind-scenes)
  • 25-30% Thought leadership (industry analysis, contrarian takes)
  • 15-20% Personal stories (failures, pivots, lessons)
  • 15-20% Value/education (tutorials, frameworks)
  • 10% max Product promotion

Hook Formulas

Transformation: "6 months ago I was X. Today Y. Here's the playbook:"
Contrarian: "Everyone's building X. Here's why that's actually smart:"
Authority + Promise: "I've done X. Here are the Y patterns:"
Curiosity Gap: "I discovered ONE thing that 10x'd my Z. It has nothing to do with [obvious]:"

Voice Guidelines

Use:

  • Specific numbers and real data
  • Short, punchy sentences
  • Personal stories with lessons
  • Honest takes, even uncomfortable ones

Avoid:

  • "Revolutionary", "Game-changing", "Seamless"
  • Vague claims without data
  • Corporate speak
  • Excessive hashtags

Conference/Event Content Strategy

Content Cadence

Pre-Event: 2-3 tweets/day During Event: 3-5 tweets/day (real-time value) Post-Event: 2-3 tweets/day + 1 thread

Thread Structure (7-10 tweets)

1/ Hook: "Money I wasted at CES..." or "Lessons from my second CES..."
2-6/ Individual points with specifics
7/ Summary/key takeaway
8/ Call for engagement: "What's your experience?"

Tweet Types for Events

TypeExampleWhen to Use
Prep tweets"CES countdown: 9 days. Here's my checklist:"Pre-event
Real-time observations"Just walked Eureka Park. 3 things that surprised me:"During
Quick tips"CES pro tip: Comfortable shoes > dress shoes"Anytime
Contrarian takes"80% of CES booths aren't worth your time. Here's how to find the 20%:"Post-event
Number-driven"I wasted $1,400 at my first CES. Here's the breakdown:"Post-event

Input/Output Examples

Example 1: Single Tweet Request

User Input:

"Help me write a tweet about CES"

Expected Output:

Main Tweet:
"Lesson from CES: The founders who got meetings weren't the loudest. They were the ones who booked 6 weeks early.

90% of Brella meetings are scheduled before the event starts. I learned this the hard way last year."

Self-reply (post 10 min later):
"The real flex at CES isn't your booth. It's your calendar."

Schedule: 9:00 AM EST Tuesday
Character count: 248 OK

Example 2: Thread Request

User Input:

"Write a thread about AI creative tools"

Expected Output:

1/ Most AI creative tools have a dirty secret.

They make everything look the same.

Here's what I learned testing 15+ tools for brand creative:

2/ The problem isn't the AI.

It's that these tools optimize for "good enough" — not "on-brand."

3/ After 6 months of testing:
- Tool A: Great art, zero brand memory
- Tool B: Generic copy every time
- Tool C: Templates that sound like everyone else

4/ The missing piece: Brand memory.

Not a new term. It's how the best brand teams already work — they have a "brand bible" in their heads.

5/ What if AI could learn that bible?

That's what we're building.

6/ Early results:
- 10 hours saved per week
- Creative that actually passes brand review first time
- No more "make it more on-brand" feedback loops

7/ The shift happening now:

From: AI that generates content
To: AI that generates YOUR content

Who else is tired of generic AI output?

Example 3: Build-in-Public Update

User Input:

"We just shipped a new feature, help me write a tweet"

Response Pattern:

  1. Ask: "What feature? Who benefits? One metric if available?"
  2. Then generate tweet with:
    • What shipped (specific)
    • Why it matters (user benefit)
    • One proof point (number or before/after)
    • No hype words

Example Output:

"Shipped: Auto-brand-check for ad creative.

Before: 3 rounds of revision to pass brand review.
After: 90% first-time approval rate.

The surprising part: Most rejections weren't about design. They were about tone."

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.