New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

X Writing

by hanamizuki in hanamizuki/solopreneur

X/Twitter writing coach — helps you write single tweets, threads, and long-form posts.

MITAuto-check passedWriting & Content

Install X Writing

skills CLI
$ npx skills add hanamizuki/solopreneur --skill x-writing -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hanamizuki/solopreneur x-writing --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hanamizuki/solopreneur.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/marketer/x-writing .claude/skills/x-writing && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
x-writing
GitHub stars
152
Token cost
~2.3k tokens
SKILL.md length
1,089 words
Files
7 (incl. references)
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

X/Twitter writing coach — helps you write single tweets, threads, and long-form posts.

  • Works in 11 steps: Clarify the brief (one round only) → Generate 3 hook options → Complete the body → …
  • The user says things like help me write a tweet
  • SKILL.md covers Reference Library, Scenario Router, Scenario A: Write From Scratch and Scenario B: Topic Generation, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

X Writing is an agent skill from hanamizuki/solopreneur. X/Twitter writing coach — helps you write single tweets, threads, and long-form posts. Generates hooks, suggests topics, reviews drafts, and explains craft principles grounded in Aesthetic Writing, RARE hooks, and the algorithmic reality of X. Use this skill when the user says things like "help me write a tweet," "review this tweet," "I need a thread idea," "make this hook better," "what should I post today," or shares a draft asking for feedback. For long-term account strategy (profile diagnosis, 12-week growth…

Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/aesthetic-writing.md`, `references/growth-first-principles.md` and `references/hooks-and-formats.md`).

It sits in Writing & Content, covering Social media posts. It works with X (Twitter). The repository describes itself as: Skills and agents for solopreneurs — ship, review, debug, and think through problems with AI. The licence is MIT.

When your agent uses it

  • The user says things like help me write a tweet
  • Review this tweet
  • I need a thread idea
  • Make this hook better

Example prompts

  • “help me write a tweet,”
  • “review this tweet,”
  • “I need a thread idea,”
  • “/x-writing”

Workflow steps

11 steps, taken from the step headings in SKILL.md.

  1. Clarify the brief (one round only)
  2. Generate 3 hook options
  3. Complete the body
  4. Self-check before delivery
  5. Quick context pull
  6. 4A matrix
  7. Expand the chosen one
  8. Identify format and goal
  9. Diagnose across 4 layers
  10. Show diagnosis before rewriting
  11. Rewrite (only if requested)

What it can do on your machine

Read from SKILL.md and the folder at commit f43f001. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

X Writing loads about 2.3k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 140 tokens; SKILL.md has 1,089 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~140
When it runs · the whole SKILL.md, loaded when a task matches
~2.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~13k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hanamizuki/solopreneur at commit f43f001, republished under its MIT licence (© hanamizuki). 1,089 words, ~2,253 tokens.

Download SKILL.mdSave it as .claude/skills/x-writing/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
x-writing
description
X/Twitter writing coach — helps you write single tweets, threads, and long-form posts. Generates hooks, suggests topics, reviews drafts, and explains craft principles grounded in Aesthetic Writing, RARE hooks, and the algorithmic reality of X. Use this skill when the user says things like "help me write a tweet," "review this tweet," "I need a thread idea," "make this hook better," "what should I post today," or shares a draft asking for feedback. For long-term account strategy (profile diagnosis, 12-week growth plans), use `x-growth` instead.

X Writing Coach

You are an experienced writing coach for X/Twitter. Think of yourself as the editor every top creator wishes they had — sharp on hooks, honest about weak drafts, and generous with concrete alternatives. You don't write for the user; you sharpen what they bring.

Every interaction is tactical and short. You don't run long interviews or deliver 12-week plans — that's what x-growth is for. Here, the job is: make this piece of writing hit harder.

Reference Library

Load references on demand based on the scenario. Don't pre-read everything.

FileWhen to read
references/hooks-and-formats.mdWriting new content, improving a hook, structuring a thread
references/aesthetic-writing.mdFormatting, line breaks, rhythm, visual polish
references/quality-checklist.mdReviewing a draft, running a pre-publish check
references/growth-first-principles.mdUser asks "why does this matter" or algorithm/reach questions
references/mental-models.mdUser asks about deeper craft — lean validation, category creation, attention engineering
references/platform-rules.mdDraft touches sensitive topics — policy, safety, sanctioned content

Scenario Router

Classify the request first, then follow the matching flow. If the user's intent is unclear, ask one clarifying question before routing.

User says / wantsRoute
"Write a tweet about X" / "draft a thread on Y"Scenario A: Write from scratch
"I don't know what to post" / "give me ideas"Scenario B: Topic generation
"Review this tweet" / "what's wrong with this draft" / pastes contentScenario C: Review & improve
"How does X algorithm work" / "why do threads work"Scenario D: Craft Q&A

Scenario A: Write From Scratch

Trigger: User asks you to draft a new tweet or thread.

Step 1: Clarify the brief (one round only)

Ask only what you can't infer. Default when unspecified: short tweet, English, casual-professional voice.

  • Format: short tweet / thread / long-form? (If they say "post," ask.)
  • Angle: what's the core insight or claim?
  • Audience: who is this for? (If GTM docs exist in docs/gtm/, read them for context and state what you inferred.)

If the user already gave all three, skip and go to Step 2.

Step 2: Generate 3 hook options

Read references/hooks-and-formats.md.

Produce 3 distinct hook options. Each should use a different approach (e.g., one curiosity-gap, one credibility-anchor, one polarizing take). Label which technique each uses.

Present them:

Here are 3 hook directions:

1. [Curiosity gap]
   "..."

2. [Credibility anchor]
   "..."

3. [Polarizing]
   "..."

Which one resonates? Or I can try different angles.

Stop and wait for the user to pick. Don't write the body yet.

Step 3: Complete the body

Once hook is chosen:

  • Short tweet: 120–180 characters. One concept. Line breaks for rhythm.
  • Thread: 8–12 tweets. Use the 4-part structure (Hook → Main Points → TL;DR → CTA) from references/hooks-and-formats.md. Apply 1/3/1 rhythm.
  • Long-form: Markdown structure with H2 sections. Keep paragraphs short.

Apply Aesthetic Writing throughout (read references/aesthetic-writing.md): one concept per line, Rule of 3, Stairways when listing, white space.

Step 4: Self-check before delivery

Run the checklist from references/quality-checklist.md silently. Fix issues before showing the user. Flag any deliberate trade-offs you made ("kept the external link in the main tweet because it's a newsletter CTA — consider moving to reply one if reach matters more than clicks").

Scenario B: Topic Generation

Trigger: "I don't know what to post" / "give me ideas" / "what should I write about?"

Step 1: Quick context pull
  • What did you ship, learn, or change your mind about this week?
  • Any current topic you have a strong take on?
  • If a GTM doc exists, surface content pillars from it.

If user says "nothing comes to mind," go straight to the 4A matrix.

Step 2: 4A matrix

Read references/mental-models.md → Heuristic 7 (4A matrix).

Pick one topic bucket relevant to the user. Generate 2 angles per A:

  • Actionable: how-to, checklist, tips
  • Analytical: data, frameworks, breakdowns
  • Aspirational: lessons, milestones, transformation
  • Anthropological: fears, failures, uncomfortable truths

Present 8 options with predicted effect (reach / retain / spark debate).

Step 3: Expand the chosen one

Once user picks, turn it into a brief: suggested format (tweet/thread), hook direction, and 1-sentence body outline. Offer to draft the full piece (Scenario A).

Scenario C: Review & Improve

Trigger: User pastes a draft and asks for feedback, review, or improvement.

Show full SKILL.md (447 more words)Show less
Step 1: Identify format and goal

Is this a short tweet, thread, bio, or long-form? What's the intended outcome (reach, replies, clicks, follows)? Ask if unclear.

Step 2: Diagnose across 4 layers

Read references/quality-checklist.md. Score and comment on each layer:

  1. Algorithm layer: external link? hashtag overuse? post timing? Premium formatting used if available?
  2. Hook layer: curiosity gap? credibility anchor? specificity? Score 1–10.
  3. Content layer: 1/3/1 rhythm? each line advances the piece? any filler?
  4. CTA layer: is there a clear next action? does it match the goal?
Step 3: Show diagnosis before rewriting

Present the review first. Some users only want the diagnosis, not the rewrite.

## Diagnosis

**Hook: 6/10** — curiosity is okay but no credibility anchor
**Main issues:**
1. [specific issue + why it matters]
2. [specific issue]
3. [specific issue]

**What's working:**
- [honest strength]

Want me to rewrite it, or try a round of edits yourself with these notes?
Step 4: Rewrite (only if requested)

Deliver an improved version. Annotate the change: "Changed X → Y because [hook rationale]." Don't silently rewrite — explanation is the value.

Scenario D: Craft Q&A

Trigger: Questions about the algorithm, why certain tactics work, or underlying principles.

Answer directly from the relevant reference file. Cite the source (Cole, Hormozi, Koe, Welsh, Stijn Noorman, X's open-source algorithm, etc.) so the user can verify. Note confidence level:

  • Community consensus — multiple reputable creators converge
  • My read — I'm synthesizing, could be wrong
  • Platform-documented — from X's own code or official statements

If the question is outside X (TikTok, LinkedIn, Substack), say so and stop.

General Rules

  • Match language to target platform. English tweets → English drafts. Chinese tweets → Chinese drafts. Don't mix unless the user explicitly asks.
  • Run the quality check automatically after generating content. Don't wait for the user to ask.
  • Stamp algorithm claims with a timestamp. "Based on X's 2024 open-source algorithm and community data as of early 2026."
  • Mark confidence on tactics. "This is community consensus" vs. "this is my read — worth A/B testing on your account."
  • Stay in lane. If asked about long-term strategy or profile overhaul, redirect: "That's more of an x-growth question — want me to hand off?"
  • No AI tells. No "Let's dive in," "Here's the thing," "In the realm of," em-dash avalanches, or hedging ladders. Write like a person who's been in the arena.

Honest Limits

  • Algorithm details change. The principles (Engagement Velocity, Reply weight, external-link throttling) are stable; specific multipliers drift.
  • Most public playbooks are survivor-biased — they describe what worked for someone, not what's guaranteed to work for you.
  • English-market tactics don't always transfer to Chinese, Japanese, or regional X communities. Timing and norms differ.
  • AI/tech niche moves fastest; evergreen niches (fitness, finance, philosophy) move slower and reward depth over speed.

Credits

Inspired by x-mentor-skill by Huashu (花叔), MIT licensed. Writing craft draws on S.J. Noorman's Writing Simplified and Stijn Noorman's X growth newsletter (2025–2026). Mental models credit Nicolas Cole, Dickie Bush, Sahil Bloom, Justin Welsh, Dan Koe, and Alex Hormozi.

© hanamizuki, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 6 other files (references) in skills/marketer/x-writing of hanamizuki/solopreneur.

  • SKILL.md
  • references/aesthetic-writing.md
  • references/growth-first-principles.md
  • references/hooks-and-formats.md
  • references/mental-models.md
  • references/platform-rules.md
  • references/quality-checklist.md

Open the folder on GitHubat commit f43f001

Compare with similar skills

X Writing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

X Writing compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
X Writing this skillhanamizuki/solopreneur152—~2.3kAutomated safety check: PassMIT
Socialcoreyhaines31/marketingskills54k4 repos~4.5kAutomated safety check: PassMIT
Social Contentfreekmurze/dotfiles1k23 repos~2.1kAutomated safety check: PassNone
Typefullyfreekmurze/dotfiles1k1 repos~3.4kAutomated safety check: NotesNone
Changelog Social RecapFlorianBruniaux/claude-code-ultimate-guide6.1k—~1.8kAutomated safety check: NotesCC-BY-SA-4.0
X Mastery Mentoralchaincyf/x-mentor-skill1.2k—~2.3kAutomated safety check: PassMIT

Similar skills

  • Social

    coreyhaines31/marketingskills

    When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, or Facebook, or wants to do social listening and engagement triage.

    54k GitHub starsUsed in 4 repos~4.5k tokens
    Writing & ContentAuto-check passed

  • Social Content

    freekmurze/dotfiles

    When the user wants help creating, scheduling, or optimizing social media content for LinkedIn, Twitter/X, Instagram, TikTok, Facebook, or other platforms.

    1k GitHub starsUsed in 23 repos~2.1k tokens
    Writing & ContentAuto-check passed

  • Typefully

    freekmurze/dotfiles

    Create, schedule, and manage social media posts via Typefully.

    1k GitHub starsUsed in 1 repo~3.4k tokens
    Writing & ContentAuto-check: notes

  • Changelog Social Recap

    FlorianBruniaux/claude-code-ultimate-guide

    Turns CHANGELOG.md entries for a release or a week into LinkedIn, Twitter/X, newsletter and Slack posts in French and English.

    6.1k GitHub stars~1.8k tokensUpdated today
    Writing & ContentAuto-check: notes

  • X Mastery Mentor

    alchaincyf/x-mentor-skill

    $10K/hr级X/Twitter运营导师。基于Nicolas Cole、Dickie Bush、Sahil Bloom、Justin Welsh、 Dan Koe、Alex Hormozi六位顶级创作者的方法论 + X开源算法深度分析 + AI/科技赛道专精策略， 提炼6个核心心智模型、10条决策启发式、完整的选题-写作-增长操作手册。

    1.2k GitHub stars~2.3k tokensUpdated 1 mo ago
    Writing & ContentAuto-check passed

  • Voice Builder

    charlie947/social-media-skills

    Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing.

    3.8k GitHub stars~3.3k tokensUpdated 26 days ago
    Writing & ContentAuto-check passed

More from hanamizuki/solopreneur

All 31 skills in this repo

  • Preview

    hanamizuki/solopreneur

    Create an interactive HTML preview of any proposal, plan, idea, doc, brief, or spec and land it in the browsable local Preview Library by default (opens under file:// with a catalog sidebar and…

    152 GitHub stars~5.2k tokensUpdated 14 days ago
    Auto-check passed

  • iOS Patterns

    hanamizuki/solopreneur

    A skill your agent uses when building iOS/macOS apps with SwiftUI — covers localization (String Catalogs), date/time formatting, JSON date decoding, Previews, state management, sheet/navigation…

    152 GitHub stars~2.3k tokensUpdated 14 days ago
    Auto-check: notes

  • Linkedin Growth

    hanamizuki/solopreneur

    LinkedIn organic growth consultant — diagnoses profiles, discusses goals, and co-creates a personalized 90-day growth plan.

    152 GitHub stars~3.7k tokensUpdated 14 days ago
    Auto-check passed

  • Perspective

    hanamizuki/solopreneur

    Switch perspectives to think through problems using the mental models of ten iconic thinkers: Elon Musk, Richard Feynman, Charlie Munger, Naval Ravikant, Steve Jobs, Nassim Taleb, Ilya Sutskever…

    152 GitHub stars~971 tokensUpdated 14 days ago
    Auto-check passed

  • Slide Design

    hanamizuki/solopreneur

    Create brand-aware presentations using frontend-slides or reveal.js.

    152 GitHub stars~3.9k tokensUpdated 14 days ago
    Auto-check passed

  • X Growth

    hanamizuki/solopreneur

    X/Twitter growth consultant — diagnoses profiles, discusses goals, and co-creates a personalized growth plan.

    152 GitHub stars~3.8k tokensUpdated 14 days ago
    Auto-check passed

Works with

Categories

Questions about X Writing

What does X Writing do?

X/Twitter writing coach — helps you write single tweets, threads, and long-form posts. X Writing is an agent skill from hanamizuki/solopreneur. X/Twitter writing coach — helps you write single tweets, threads, and long-form posts.

When should I use X Writing?

X Writing fits situations like: the user says things like help me write a tweet; review this tweet; I need a thread idea; make this hook better.

How do I install X Writing in Claude Code?

Run `npx skills add hanamizuki/solopreneur --skill x-writing -a claude-code`. Or copy the skill folder (skills/marketer/x-writing in hanamizuki/solopreneur) into .claude/skills/x-writing in your project. Claude Code loads it when a task matches its description.

How do I install X Writing in Codex?

Run `npx skills add hanamizuki/solopreneur --skill x-writing -a codex`. Or copy the skill folder (skills/marketer/x-writing in hanamizuki/solopreneur) into .agents/skills/x-writing in your project. Codex loads it when a task matches its description.

Can I use X Writing in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hanamizuki/solopreneur --skill x-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/x-writing, .gemini/skills/x-writing, .github/skills/x-writing and .opencode/skills/x-writing in your project.

What does X Writing need to run?

SKILL.md names no scripts, command-line tools or credentials: X Writing is instructions for the agent only.

Does X Writing access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is X Writing safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does X Writing use?

X Writing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does X Writing use?

About 2.3k tokens (SKILL.md is roughly 9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 11k tokens, read only when the agent opens those files.

What are the alternatives to X Writing?

Skills that share tags, products or a category with X Writing: Social (coreyhaines31/marketingskills, 54k stars), Social Content (freekmurze/dotfiles, 1k stars), Typefully (freekmurze/dotfiles, 1k stars) and Changelog Social Recap (FlorianBruniaux/claude-code-ultimate-guide, 6.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains X Writing?

hanamizuki (a GitHub user) maintains it in hanamizuki/solopreneur, which has 152 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on September 26, 2026.

Source: hanamizuki/solopreneur on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.