x-twitter-growth

$npx mdskill add alirezarezvani/claude-skills/x-twitter-growth

Grow X/Twitter audience with algorithm-optimized content and strategy

  • Helps build audience, craft viral tweets, and analyze engagement
  • Uses web search, X API, and competitive intelligence tools
  • Analyzes trends, thread structure, and reply engagement patterns
  • Delivers actionable content plans and profile optimization tips

SKILL.md

.github/skills/x-twitter-growthView on GitHub ↗
---
name: "x-twitter-growth"
description: "X/Twitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X/Twitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search."
license: MIT
metadata:
  version: 1.0.0
  author: Alireza Rezvani
  category: marketing
  updated: 2026-03-10
---

# X/Twitter Growth Engine

X-specific growth skill. For general social media content across platforms, see `social-content`. For social strategy and calendar planning, see `social-media-manager`. This skill goes deep on X.

## When to Use This vs Other Skills

| Need | Use |
|------|-----|
| Write a tweet or thread | **This skill** |
| Plan content across LinkedIn + X + Instagram | social-content |
| Analyze engagement metrics across platforms | social-media-analyzer |
| Build overall social strategy | social-media-manager |
| X-specific growth, algorithm, competitive intel | **This skill** |

---

## Step 1 — Profile Audit

Before any growth work, audit the current X presence. Run `scripts/profile_auditor.py` with the handle, or manually assess:

### Bio Checklist
- [ ] Clear value proposition in first line (who you help + how)
- [ ] Specific niche — not "entrepreneur | thinker | builder"
- [ ] Social proof element (followers, title, metric, brand)
- [ ] CTA or link (newsletter, product, site)
- [ ] No hashtags in bio (signals amateur)

### Pinned Tweet
- [ ] Exists and is less than 30 days old
- [ ] Showcases best work or strongest hook
- [ ] Has clear CTA (follow, subscribe, read)

### Recent Activity (last 30 posts)
- [ ] Posting frequency: minimum 1x/day, ideal 3-5x/day
- [ ] Mix of formats: tweets, threads, replies, quotes
- [ ] Reply ratio: >30% of activity should be replies
- [ ] Engagement trend: improving, flat, or declining

Run: `python3 scripts/profile_auditor.py --handle @username`

---

## Step 2 — Competitive Intelligence

Research competitors and successful accounts in your niche using web search.

### Process
1. Search `site:x.com "topic" min_faves:100` via Brave to find high-performing content
2. Identify 5-10 accounts in your niche with strong engagement
3. For each, analyze: posting frequency, content types, hook patterns, engagement rates
4. Run: `python3 scripts/competitor_analyzer.py --handles @acc1 @acc2 @acc3`

### What to Extract
- **Hook patterns** — How do top posts start? Question? Bold claim? Statistic?
- **Content themes** — What 3-5 topics get the most engagement?
- **Format mix** — Ratio of tweets vs threads vs replies vs quotes
- **Posting times** — When do their best posts go out?
- **Engagement triggers** — What makes people reply vs like vs retweet?

---

## Step 3 — Content Creation

### Tweet Types (ordered by growth impact)

#### 1. Threads (highest reach, highest follow conversion)
```
Structure:
- Tweet 1: Hook — must stop the scroll in <7 words
- Tweet 2: Context or promise ("Here's what I learned:")
- Tweets 3-N: One idea per tweet, each standalone-worthy
- Final tweet: Summary + explicit CTA ("Follow @handle for more")
- Reply to tweet 1: Restate hook + "Follow for more [topic]"

Rules:
- 5-12 tweets optimal (under 5 feels thin, over 12 loses people)
- Each tweet should make sense if read alone
- Use line breaks for readability
- No tweet should be a wall of text (3-4 lines max)
- Number the tweets or use "↓" in tweet 1
```

#### 2. Atomic Tweets (breadth, impression farming)
```
Formats that work:
- Observation: "[Thing] is underrated. Here's why:"
- Listicle: "10 tools I use daily:\n\n1. X — for Y"
- Contrarian: "Unpopular opinion: [statement]"
- Lesson: "I [did X] for [time]. Biggest lesson:"
- Framework: "[Concept] explained in 30 seconds:"

Rules:
- Under 200 characters gets more engagement
- One idea per tweet
- No links in tweet body (kills reach — put link in reply)
- Question tweets drive replies (algorithm loves replies)
```

#### 3. Quote Tweets (authority building)
```
Formula: Original tweet + your unique take
- Add data the original missed
- Provide counterpoint or nuance
- Share personal experience that validates/contradicts
- Never just say "This" or "So true"
```

#### 4. Replies (network growth, fastest path to visibility)
```
Strategy:
- Reply to accounts 2-10x your size
- Add genuine value, not "great post!"
- Be first to reply on accounts with large audiences
- Your reply IS your content — make it tweet-worthy
- Controversial/insightful replies get quote-tweeted (free reach)
```

Run: `python3 scripts/tweet_composer.py --type thread --topic "your topic" --audience "your audience"`

---

## Step 4 — Algorithm Mechanics

### What X rewards (2025-2026)
| Signal | Weight | Action |
|--------|--------|--------|
| Replies received | Very high | Write reply-worthy content (questions, debates) |
| Time spent reading | High | Threads, longer tweets with line breaks |
| Profile visits from tweet | High | Curiosity gaps, tease expertise |
| Bookmarks | High | Tactical, save-worthy content (lists, frameworks) |
| Retweets/Quotes | Medium | Shareable insights, bold takes |
| Likes | Low-medium | Easy agreement, relatable content |
| Link clicks | Low (penalized) | Never put links in tweet body — use reply |

### What kills reach
- Links in tweet body (put in first reply instead)
- Editing tweets within 30 min of posting
- Posting and immediately going offline (no early engagement)
- More than 2 hashtags
- Tagging people who don't engage back
- Threads with inconsistent quality (one weak tweet tanks the whole thread)

### Optimal Posting Cadence
| Account size | Tweets/day | Threads/week | Replies/day |
|-------------|------------|--------------|-------------|
| < 1K followers | 2-3 | 1-2 | 10-20 |
| 1K-10K | 3-5 | 2-3 | 5-15 |
| 10K-50K | 3-7 | 2-4 | 5-10 |
| 50K+ | 2-5 | 1-3 | 5-10 |

---

## Step 5 — Growth Playbook

### Week 1-2: Foundation
1. Optimize bio and pinned tweet (Step 1)
2. Identify 20 accounts in your niche to engage with daily
3. Reply 10-20 times per day to larger accounts (genuine value only)
4. Post 2-3 atomic tweets per day testing different formats
5. Publish 1 thread

### Week 3-4: Pattern Recognition
1. Review what formats got most engagement
2. Double down on top 2 content formats
3. Increase to 3-5 posts per day
4. Publish 2-3 threads per week
5. Start quote-tweeting relevant content daily

### Month 2+: Scale
1. Develop 3-5 recurring content series (e.g., "Friday Framework")
2. Cross-pollinate: repurpose threads as LinkedIn posts, newsletter content
3. Build reply relationships with 5-10 accounts your size (mutual engagement)
4. Experiment with spaces/audio if relevant to niche
5. Run: `python3 scripts/growth_tracker.py --handle @username --period 30d`

---

## Step 6 — Content Calendar Generation

Run: `python3 scripts/content_planner.py --niche "your niche" --frequency 5 --weeks 2`

Generates a 2-week posting plan with:
- Daily tweet topics with hook suggestions
- Thread outlines (2-3 per week)
- Reply targets (accounts to engage with)
- Optimal posting times based on niche

---

## Scripts

| Script | Purpose |
|--------|---------|
| `scripts/profile_auditor.py` | Audit X profile: bio, pinned, activity patterns |
| `scripts/tweet_composer.py` | Generate tweets/threads with hook patterns |
| `scripts/competitor_analyzer.py` | Analyze competitor accounts via web search |
| `scripts/content_planner.py` | Generate weekly/monthly content calendars |
| `scripts/growth_tracker.py` | Track follower growth and engagement trends |

## Common Pitfalls

1. **Posting links directly** — Always put links in the first reply, never in the tweet body
2. **Thread tweet 1 is weak** — If the hook doesn't stop scrolling, nothing else matters
3. **Inconsistent posting** — Algorithm rewards daily consistency over occasional bangers
4. **Only broadcasting** — Replies and engagement are 50%+ of growth, not just posting
5. **Generic bio** — "Helping people do things" tells nobody anything
6. **Copying formats without adapting** — What works for tech Twitter doesn't work for marketing Twitter

## Related Skills

- `social-content` — Multi-platform content creation
- `social-media-manager` — Overall social strategy
- `social-media-analyzer` — Cross-platform analytics
- `content-production` — Long-form content that feeds X threads
- `copywriting` — Headline and hook writing techniques

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditAccessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ab-test-setupWhen the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
ad-creativeWhen the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
aeoAnswer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize for ChatGPT', 'get cited by Perplexity', 'LLM citation strategy', 'answer engine optimization', 'content for AI search', 'E-E-A-T audit'. Output is a markdown audit report (default) or JSON for pipeline integration. Stdlib-only Python tools.
agent-decision-receiptsMint a tamper-evident, post-quantum-signed receipt for a consequential agent action (deploy, delete, pay, grant-access, model decision) so it can be verified later from the certificate alone. Use when an autonomous agent takes a side-effecting action that may need to be proven later, or when satisfying EU AI Act Article 12 record-keeping. Three decisions: whether an action needs a receipt, minting it, verifying it. Signing is delegated to the open-source OpenAgentOntology package. Not after-the-fact log analysis; not a hosted notary; not a legal opinion.
agent-designerUse when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
agent-harnessTurn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).
agent-launcher-orchestratorUse when a user wants to build, launch, grade, or schedule a Claude Managed Agent (CMA) in their own Anthropic account — "build me an agent", "launch this as a managed agent", "run this on a schedule", "grade my agent against a rubric", "set up a nightly worker". Reads the per-session goal (./my-agent/goal.json), routes deterministically to one of five phase sub-skills (interview → stage-launch → grade-iterate → run-without-you → wrap-up) via goal_router.py, and compiles the goal+phase into an execution shape (single-pass workflow / bounded grade→iterate loop / recurring cron deployment loop) via loop_compiler.py. Forks context so heavy intake (build sheets, payloads, eval cases) stays out of the parent thread. All launches are emitted as BYOK curl the user runs with their own key; no tool makes API calls. Inspired by anthropics/launch-your-agent (Apache-2.0). Distinct from engineering/agent-harness (generic domain loop) and engineering/write-a-skill (authors Claude Code skills, not CMAs).
agent-memoryUse when a project's CLAUDE.md has grown past what anyone reads and you want the agent to learn durable facts from its own sessions instead — or when asking why the agent keeps re-learning the same correction, why a remembered rule is wrong, or where a memory line came from. Implements a four-tier store (L0 transcripts / L1 candidates / L2 project context / L3 stable persona) where promotion is earned by recurrence across sessions and days, never by one confident statement, and nothing reaches a committed file without a human adopting it.