tweet-writer
Write viral, persuasive, engaging tweets and threads. Uses web research to find viral examples in your niche, then models writing based on proven formulas and X algorithm optimization. Use when creating tweets, threads, or X content strategy.
What this skill does
# Tweet Writer Skill
## Overview
This skill helps you write viral, persuasive tweets and threads optimized for X's algorithm. It combines proven copywriting frameworks, viral hook formulas, and real-time research to model your content after successful examples in your niche.
**Keywords**: twitter, X, tweets, threads, viral content, social media, engagement, hooks, copywriting
## Process Workflow
### Phase 1: Niche Research (CRITICAL)
Before writing ANY tweet, you MUST research viral examples in the user's specific niche.
**Research Steps:**
1. **Identify the niche/topic** — What is the user writing about?
2. **Search for viral examples** — Use WebSearch to find:
- `"[niche] viral tweet examples"`
- `"[niche] twitter thread went viral"`
- `"[topic] best performing tweets"`
- `site:twitter.com OR site:x.com "[niche keyword]" high engagement`
3. **Analyze patterns** — Extract:
- Hook styles that worked
- Content structure
- Tone and voice
- Specific numbers/results used
- CTAs that drove engagement
4. **Document insights** — Create a brief analysis before writing
**Example Research Prompt:**
```
Searching for: "SaaS founder viral tweets"
"startup advice twitter thread viral"
"tech entrepreneur best tweets engagement"
```
### Phase 2: Tweet Creation
Use the frameworks below to craft content modeled after successful examples.
---
## The X Algorithm (2026)
Understanding what the algorithm rewards is critical:
### Engagement Hierarchy (Most to Least Valuable)
1. **Replies** — Most weighted signal
2. **Quote tweets** — High value, shows your content sparks conversation
3. **Bookmarks** — Strong signal of value
4. **Retweets** — Amplification signal
5. **Likes** — Baseline engagement
### Time Sensitivity
- **First hour is critical** — If you don't gain traction in 60 minutes, reach drops significantly
- **Peak times**: 9-11 AM and 7-9 PM EST weekdays, 9-11 AM weekends
- Fresh content prioritized — X rewards recency
### Dwell Time
X tracks how long users spend on your content. Longer = more reach.
- Threads naturally increase dwell time
- Visual content keeps eyes on post longer
- Compelling hooks stop the scroll
### Format Boosts
- **Native video**: Priority over external links
- **Images/carousels**: 2x engagement vs text-only
- **Threads**: 3x engagement vs single tweets
- **Polls**: High participation signals
### What to AVOID
- **External links**: Severely penalized (especially for non-Premium accounts)
- **Generic content**: No differentiation = no reach
- **Asking for engagement**: "Like and RT" hurts reach
---
## Hook Formulas (The Most Critical Element)
Your hook determines 80-90% of your tweet's success. You have ~1 second to stop the scroll.
### The Bold Statement
```
"Nobody talks about this, but..."
"Unpopular opinion: [controversial take]"
"Everything you've been told about [X] is wrong."
"[Common belief] is a myth. Here's the truth:"
```
### The Specific Result
```
"I [specific result] in [specific timeframe]. Here's how:"
"[Number] [achievement] in [timeframe]. The breakdown:"
"From [bad state] to [good state] in [time]. Thread:"
```
**Example**: "I grew from 0 to 50K followers in 90 days. Here's the exact playbook:"
### The Curiosity Gap
```
"I found a [adjective] [topic] hack that no one talks about..."
"The one thing [type of person] gets wrong about [topic]"
"Why most people fail at [X] (and how to fix it)"
```
### The Question Hook
```
"Want to know the real secret to [X]?"
"What if everything you knew about [X] was wrong?"
"Ever wonder why [common frustration]?"
```
### The Story Hook
```
"3 years ago I was [bad state]. Today I [good state]."
"I almost quit [X]. Then this happened:"
"The story of how I [achievement] (with $0 budget):"
```
### The Pattern Interrupt
```
"Everyone says [X]. They're wrong."
"Stop doing [common practice]. Do this instead:"
"Delete [common thing]. Here's why:"
```
### The List Promise
```
"[Number] [things] that will [benefit] (thread):"
"[Number] lessons from [experience/achievement]:"
"The [number] [category] I wish I knew earlier:"
```
**Example**: "7 AI tools that saved me 20+ hours last week:"
---
## Tweet Formats That Go Viral
### Format 1: The Listicle (Highest Engagement)
```
Hook: "[Number] [things] that [benefit]:"
1. [Item] — [Brief explanation]
2. [Item] — [Brief explanation]
...
[CTA or summary]
```
### Format 2: The Contrarian Take
```
Hook: "[Popular belief] is wrong."
Here's why: [2-3 sentences of reasoning]
What actually works: [Your alternative]
```
### Format 3: The Before/After
```
[Time period] ago: [Bad state]
Today: [Good state]
The difference? [One key insight]
```
### Format 4: The Framework
```
Hook: "The [Name] Framework for [Result]:"
Step 1: [Action]
Step 2: [Action]
Step 3: [Action]
[Optional: brief expansion on each]
```
### Format 5: The "Fill in the Blank"
```
"The most underrated skill for _____ is _____."
"If I could only use one tool for [X], it would be _____."
```
*Generates massive replies*
### Format 6: The Universal Experience
```
"When you finally [common experience/realization]"
"Why does nobody talk about [shared frustration]?"
"That moment when [relatable situation]"
```
---
## Thread Structure (7-Tweet Sweet Spot)
### Thread Template
**Tweet 1 (Hook)**:
- Most compelling insight or result
- Include specific numbers
- Signal it's a thread: "🧵" or "(thread)"
**Tweet 2 (Context)**:
- Expand on the hook
- Set up why this matters
- Create more curiosity
**Tweets 3-6 (Core Value)**:
- ONE key insight per tweet
- Use numbered formatting (1/, 2/, etc.)
- Add visual breaks every 3-4 tweets (images, charts)
- Each tweet should be valuable standalone
**Tweet 7 (Bridge/Summary)**:
- Summarize key takeaways
- Connect to broader application
**Tweet 8 (CTA)**:
- Ask a question (generates replies)
- Quote your first tweet (drives retweets)
- Direct to profile/newsletter
### Thread Writing Rules
1. Each tweet must earn the next click
2. No filler — every word must carry weight
3. Short sentences (under 250 characters per tweet)
4. "Your words should read like a slippery slope"
5. Number your tweets (2/12, 3/12, etc.)
---
## Copywriting Frameworks for Tweets
### PAS (Problem → Agitate → Solution)
**Most reliable formula for engagement**
```
[Problem]: You're [specific situation]
[Agitate]: And it's costing you [consequence]
[Solution]: Here's what works: [your answer]
```
### AIDA (Attention → Interest → Desire → Action)
**Best for promotional content**
```
[Attention]: Hook that stops scroll
[Interest]: "Here's what most people don't realize..."
[Desire]: "Imagine if you could [benefit]"
[Action]: "DM me [X] to get started"
```
### BAB (Before → After → Bridge)
**Best for transformation stories**
```
[Before]: I was [bad state]
[After]: Now I'm [good state]
[Bridge]: The difference? [Your insight/solution]
```
---
## Persuasion Principles
Apply these to make any tweet more compelling:
**Specificity** — "23% increase" beats "big increase"
- Numbers add credibility
- Specific timeframes add urgency
- Details make claims believable
**Social Proof** — "500+ customers" beats "many customers"
- Results from real people
- Numbers of users/followers
- Recognizable names/brands
**Curiosity Gap** — Create information asymmetry
- Hint at valuable info without revealing all
- Promise specific outcomes
- Use "Here's what most people miss..."
**Controversy** — Challenge existing beliefs
- "Popular opinion is wrong"
- Contrarian takes get engagement
- Avoid offensive — aim for thought-provoking
**Relatability** — Shared experiences resonate
- "When you realize..."
- Universal frustrations
- Common journey points
---
## Growth Hacks
### The 30-Day Subtopic Strategy
Pick ONE narrow subtopic in your niche. Post about ONLY that for 30 days straight.
**Example**: If you're in marketing, focus solely on "email subject lines" for a month.
Result: X's algorithm categorizes yoRelated in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.