X Devs logo

X Devs

Community
jonathimer
x-devs

When the user wants to build a developer following on Twitter/X, write technical threads, or understand what works for dev audiences on X. Trigger phrases include "Twitter," "X," "developer Twitter," "tech Twitter," "technical threads," "building dev following," or "Twitter for developers."

Overview

Publisherjonathimer
Repositorydevmarketing-skills
Skill namex-devs
Stars
87
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jonathimer on GitHub. Read the source before you install it.

Installation

Install the X Devs AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jonathimer/devmarketing-skills.git /tmp/devmarketing-skills
mkdir -p .claude/skills
cp -r /tmp/devmarketing-skills/skills/x-devs .claude/skills/x-devs
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable X Devs in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads X Devs on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so X Devs is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

X/Twitter for Developers

Twitter/X remains the real-time pulse of the developer community. This skill covers thread structure, code screenshots, engagement tactics, and building an authentic developer following without being cringe.


Before You Start

  1. Read .agents/developer-audience-context.md if it exists
  2. Audit your current X presence (bio, pinned, recent posts)
  3. Understand: Developer Twitter rewards authenticity and technical depth

Understanding Dev Twitter

Who's on Dev Twitter

SegmentWhat they shareWhat they consume
Open source maintainersProject updates, war storiesIndustry news, peer projects
Tech leadsTeam learnings, hiringArchitecture, management
Indie hackersBuilding in public, MRRGrowth tactics, tools
DevRelContent, events, communityTrends, developer sentiment
Framework authorsUpdates, opinionsFeedback, community vibes
Learning devsQuestions, progressTutorials, inspiration

What Works on Dev Twitter

Content typeEngagement levelNotes
Technical threadsHighDeep dives get saved/shared
Code screenshotsHighVisual, scannable
Hot takesHigh (risky)Can backfire spectacularly
Building in publicHighJourney > destination
MemesMedium-highKnow your audience
AnnouncementsMediumBetter with context
Tutorial linksMediumNeed compelling hook
Retweets with commentLow-mediumAdd real value
Plain linksLowAlgorithm deprioritizes

The Algorithm (As We Understand It)

FactorImpact
Replies in first hourHigh — signals engagement
Time spent on postHigh — threads > tweets
Profile visits from postHigh — interesting content
BookmarksHigh — "save for later"
RetweetsMedium — distribution
LikesMedium — engagement signal
Link clicksLow — X wants you on platform
External linksNegative — deprioritized

Thread Structure

Thread Anatomy

Tweet 1: HOOK
Tweet 2: Context/Promise
Tweets 3-8: The meat (examples, steps, insights)
Tweet 9: Summary/Takeaway
Tweet 10: CTA + Engagement ask

Hook Patterns That Work

PatternExample
Contrarian"Hot take: You don't need Kubernetes for most apps"
Promise"How we reduced our AWS bill by 60% (thread)"
Story"Last week our API went down for 4 hours. Here's what happened:"
List tease"7 TypeScript tricks that changed how I code:"
Question"Why do most startups get database migrations wrong?"
Result"We went from 0 to 10K users in 30 days. Here's the playbook:"

Thread Writing Best Practices

ElementGuideline
Length5-12 tweets optimal
First tweetHook — no hashtags, no links
Each tweetOne idea, complete thought
NumberingUse X/10 format or emoji bullets
CodeScreenshots > text (more engaging)
PacingMix short punchy + longer explanatory
Last tweetCTA: follow, reply, bookmark

Thread Template

🧵 [Hook: Compelling statement or question]

Here's what I learned [context]:

1/ [First key point]

[Supporting detail or example]

2/ [Second key point]

[Code screenshot or visual]

3/ [Third key point]

The counterintuitive part:

[Insight that surprises]

4/ [Fourth key point]

Common mistake to avoid:

[What not to do and why]

5/ [Summary]

TL;DR:
• Point 1
• Point 2
• Point 3

If this was helpful, give me a follow @handle for more [topic].

What's your experience with [topic]? 👇

Code Screenshots

Why Screenshots Beat Code Blocks

ScreenshotsCode blocks
Syntax highlightingPlain text
Control over appearancePlatform formatting
Can include contextJust code
More visual stopsScroll past
Better engagementLower engagement

Code Screenshot Tools

ToolBest for
Carbon (carbon.now.sh)Beautiful, customizable
Ray.soClean, modern
SnappifyAnnotations, animations
CodeSnap (VS Code)Quick from editor
Silicon (CLI)Automation

Screenshot Best Practices

DoDon't
Use dark themeLight theme (harder to read)
Include file nameRemove context
Highlight key linesShow walls of code
Keep width reasonableMake text tiny
Use consistent stylingDifferent themes per post
Add comments in codeExplain separately only

Engagement Timing

Best Posting Times

Time (PT)AudienceNotes
6-8 AMUS East Coast + EuropeMorning scroll
10 AM - 12 PMPeak USLunch break
4-6 PMUS evening + Europe lateEnd of workday

Posting Frequency

FrequencyEffect
1-3 tweets/daySustainable, quality
3-5 tweets/dayGrowth mode
5+ tweets/dayRisk of overexposure
1 thread/weekGood cadence
2-3 threads/weekAggressive growth

Thread Timing

  • Post threads in morning (7-10 AM PT)
  • Engage replies for first 2 hours
  • Quote tweet your thread later in day
  • Post follow-up content same day

Hashtags (Use Sparingly)

Developer Hashtags

HashtagUse for
#buildinpublicIndie hacker updates
#devrelDevRel content
#100DaysOfCodeLearning journey
#opensourceOSS announcements
#webdevWeb development
#javascript #python etc.Language-specific

Hashtag Rules

DoDon't
Max 1-2 per tweetStuff with hashtags
Put at endLead with hashtags
Use for discoverabilityUse on every post
Skip in threadsAdd to every tweet

Building a Dev Following

The Flywheel

  1. Create valuable content → People engage
  2. Engage with replies → Build relationships
  3. Reply to others' posts → Get discovered
  4. Consistency → Algorithm favors you
  5. Followers grow → More reach
  6. Repeat

Profile Optimization

ElementBest practice
PhotoClear face, professional
NameReal name (or consistent handle)
BioWhat you do + what you tweet about
LinkYour most important URL
Pinned tweetYour best/most representative content
HeaderOn-brand, not cluttered

Bio formula:

[Role] at [Company/Project]. Building [what].
Tweeting about [topics]. [Credibility signal].

Examples:

Engineering @ Vercel. Building the web, one component at a time.
Tweeting about React, Next.js, and developer experience.

Indie hacker. Building saas.com ($10K MRR).
Writing about startups, coding, and building in public.

Reply Strategy

Reply toWhy
Big accounts in your nicheVisibility to their audience
People asking questions you can answerDemonstrate expertise
Your followersBuild relationships
Controversial takesJoin the conversation (carefully)

Good reply patterns:

  • Add information they missed
  • Share your experience
  • Ask thoughtful follow-up
  • Respectfully disagree with reasoning

What to Avoid (The Cringe Zone)

Content That Fails

TypeWhy it fails
Humble brags"So humbled to be named Top 100..."
Engagement bait"Like if you agree!"
Empty motivation"Keep grinding!"
Obvious pitches"Check out our product!"
Excessive hashtagsLooks spammy
Copied threadsPeople notice
AI-generated slopObvious and hollow
Thread guys formulaOverused patterns

Behaviors to Avoid

BehaviorWhy it hurts
Buying followersFake engagement, obvious
Engagement podsManipulated, not real reach
Aggressive follow/unfollowLooks desperate
DM pitchingSpam, burns bridges
Arguing publiclyRarely looks good
Dunking on peopleShort-term engagement, long-term reputation
Deleting unpopular takesOwn your opinions

The Authenticity Test

Before posting, ask:

  1. Would I say this in person?
  2. Is this genuinely useful or interesting?
  3. Am I adding to the conversation?
  4. Would I respect someone who posted this?

Platform-Specific Do's and Don'ts

Do's

  1. Do share real experiences and learnings
  2. Do use visuals (code screenshots, diagrams)
  3. Do engage in first hour after posting
  4. Do build in public authentically
  5. Do reply thoughtfully to others
  6. Do share credit and amplify others
  7. Do be consistent in posting schedule
  8. Do have opinions (respectfully)

Don'ts

  1. Don't be a reply guy with no original content
  2. Don't use AI to generate generic content
  3. Don't copy popular threads verbatim
  4. Don't pitch in DMs uninvited
  5. Don't use more than 2 hashtags
  6. Don't post links without context
  7. Don't be negative/dunking constantly
  8. Don't automate engagement

Content Calendar

Weekly Template

DayContent type
MondayThread (educational)
TuesdayQuick tip or insight
WednesdayEngage/reply heavy
ThursdayShare someone else's great content
FridayPersonal/behind the scenes
WeekendOptional: light content

Content Mix

TypePercentage
Educational/useful50%
Personal/journey25%
Opinions/takes15%
Promotional10%

Tools

ToolUse case
OctolensMonitor Twitter/X for mentions of your product, competitors, and relevant conversations. Get alerts when people discuss problems you solve.
CarbonBeautiful code screenshots
TypefullyThread drafting and scheduling
Buffer/HootsuiteScheduling
TweetDeckMulti-column management
FollowerwonkAudience analysis

Thread Checklist

Before posting:

  • Hook is compelling (no links, no hashtags)
  • Each tweet is a complete thought
  • Code is in screenshots, not text
  • Thread is 5-12 tweets
  • Summary/TL;DR included
  • CTA at the end
  • Scheduled for optimal time
  • Ready to engage for first 2 hours

Related Skills

  • developer-audience-context — Know who you're talking to
  • dev-to-hashnode — Turn threads into blog posts
  • linkedin-technical — Cross-post for B2B reach
  • hacker-news-strategy — Drive traffic from X to HN posts

Frequently asked questions

What does the X Devs AI skill do?

When the user wants to build a developer following on Twitter/X, write technical threads, or understand what works for dev audiences on X. Trigger phrases include "Twitter," "X," "developer Twitter," "tech Twitter," "technical threads," "building dev following," or "Twitter for developers."

Why use X Devs on TypingMind?

Because you install it once and use it with any model. X Devs is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install X Devs in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jonathimer/devmarketing-skills/tree/main/skills/x-devs. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use X Devs?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with X Devs?

As many as you like. As long as a model supports skills, you can use X Devs with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the X Devs AI skill free?

Yes. It is published on GitHub by jonathimer under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇