Twitter X GTM

Twitter/X go-to-market strategy for founders and product builders. Use when planning Twitter content strategy, analyzing engagement, identifying accounts to...

Security Scan

Instruction-only Twitter/X go-to-market guide that is internally consistent: it asks the agent to research public tweets and produce content, requests no credentials or installs, and does not perform unexpected actions.

Purpose & Capability

The name/description (Twitter/X GTM) aligns with the instructions: researching public tweets, extracting hooks/patterns, and producing tweets/threads for founders. No unrelated binaries, env vars, or installs are requested.

Instruction Scope

SKILL.md instructs the agent to search Twitter (via WebSearch or browser) and record patterns from public tweets — this is within expected scope. Note: it implies collecting public tweet content for analysis; the instructions do not direct reading local files, environment variables, or other unrelated system state. Consider whether you want the agent to perform live web browsing/scraping and ensure that behavior aligns with your policies and platform Terms of Service.

Install Mechanism

No install spec and no code files are included (instruction-only), so nothing will be written to disk or downloaded during install.

Credentials

The skill requires no environment variables, credentials, or config paths. There are no unexplained secret or credential requests that would be disproportionate to the stated purpose.

Persistence & Privilege

always is false and no special persistence is requested. Agent autonomous invocation is allowed (platform default) but this is expected for a skill of this nature.

Assessment

This is an instruction-only content strategy guide — it doesn't request secrets or install software. Before adding it: 1) decide whether you are comfortable letting the agent perform live web searches/scraping of public tweets (check Twitter/X terms and your organization's data rules); 2) avoid asking the agent to include or fabricate unverified numbers or private information; 3) note the skill has an unnecessary OS restriction (darwin/linux) despite being platform-agnostic — minor oddity but not a security problem; 4) if you don't want the agent to autonomously run this workflow, disable autonomous invocation / restrict when the skill can be used. Otherwise the skill appears coherent with its stated purpose.

Twitter/X GTM Strategy

Founder-led personal brand strategy targeting DTC brands and investors with blunt, sharp, authentic voice.

---

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 WebSearch or browser)
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)

Search Examples:

Twitter [topic] viral thread
site:twitter.com founder [topic] lessons
[topic] "here's what I learned" site:x.com

Step 2: Extract Winning Patterns

Dimension	What to Extract
Hook Formula	First line that stops scroll
Thread Structure	How points are organized
Number Usage	Dollar amounts, percentages, timeframes
Engagement Bait	What makes people reply
Punch/Rhythm	Sentence length and cadence

Step 3: Adapt with Your Brand Voice

Brand Voice:

• Blunt, sharp, authentic
• "Build-in-public meets sharp takes"
• Anti-AI-slop — real human voice
• Specific numbers, no vague claims

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

Voice: Blunt, sharp, authentic — "build-in-public meets sharp takes" Audiences: DTC brand operators, investors/VCs, AI/tech community Differentiation: Anti-AI-slop positioning — real human voice with builder credibility

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

Element	Spec
Frequency	3-5 quality tweets/day
Threads	1-2x/week, 7-10 tweets optimal
Best times	9-10 AM EST, 1-3 PM EST
Best days	Tuesday, Wednesday, Monday
Reply target	50 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:

• "AI that actually learns your brand voice"
• "Saved our team 10 hours last week"
• "Here's what I learned building [your product]"

Avoid:

• "Revolutionary AI platform"
• "Game-changing technology"
• "Seamless integration"

Conference/Event Content Strategy (CES/MWC etc.)

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

Type	Example	When 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

What Works on Twitter for Events

• Specific numbers and dollar amounts
• Contrarian observations (what others are missing)
• Quick, actionable tips
• Behind-the-scenes honesty
• Threads with clear structure

What to Avoid

• "So excited to be at CES!" (zero value)
• Reposting official announcements
• Product pitches disguised as insights
• Vague observations without specifics

---

Input/Output Examples

Example 1: Single Tweet Request

User Input:

"帮我写一条关于 CES 的 tweet"

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 ✓

Example 2: Thread Request

User Input:

"写一个关于 AI creative tools 的 thread"

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:
- Midjourney: Great art, zero brand memory
- ChatGPT: Generic copy every time
- Jasper: 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 at [Your Company].

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?

---
Thread length: 7 tweets ✓
Hook formula: "dirty secret" (curiosity gap) ✓
Includes numbers: 15+ tools, 6 months, 10 hours ✓
CTA: Question at end ✓

Example 3: Build-in-Public Update

User Input:

"我们刚 ship 了一个新功能，帮我写个 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."