返回技能列表

x-devs

jonathimer
更新于 2 days ago
6 次查看
76
4
76
在 GitHub 上查看
design

关于

The x-devs skill helps developers build their following on Twitter/X by creating effective technical threads and understanding what resonates with developer audiences. It provides guidance on thread structure, code presentation, and authentic engagement tactics. Use this skill when prompted with terms like "tech Twitter," "technical threads," or "building dev following."

快速安装

Claude Code

推荐
主要方式
npx skills add jonathimer/devmarketing-skills -a claude-code
插件命令备选方式
/plugin add https://github.com/jonathimer/devmarketing-skills
Git 克隆备选方式
git clone https://github.com/jonathimer/devmarketing-skills.git ~/.claude/skills/x-devs

在 Claude Code 中复制并粘贴此命令以安装该技能

技能文档

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

GitHub 仓库

jonathimer/devmarketing-skills
路径: skills/x-devs
0

相关推荐技能

content-collections

Content Collections 是一个 TypeScript 优先的构建工具,可将本地 Markdown/MDX 文件转换为类型安全的数据集合。它专为构建博客、文档站和内容密集型 Vite+React 应用而设计,提供基于 Zod 的自动模式验证。该工具涵盖从 Vite 插件配置、MDX 编译到生产环境部署的完整工作流。

查看技能

polymarket

这个Claude Skill为开发者提供完整的Polymarket预测市场开发支持,涵盖API调用、交易执行和市场数据分析。关键特性包括实时WebSocket数据流,可监控实时交易、订单和市场动态。开发者可用它构建预测市场应用、实施交易策略并集成实时市场预测功能。

查看技能

creating-opencode-plugins

该Skill帮助开发者创建OpenCode插件,用于接入命令、文件、LSP等25+种事件。它提供了插件结构、事件API规范和JavaScript/TypeScript实现模式,适合需要拦截操作、扩展功能或自定义事件处理的场景。开发者可通过它快速构建响应式模块来增强OpenCode AI助手的能力。

查看技能

sglang

SGLang是一个专为LLM设计的高性能推理框架,特别适用于需要结构化输出的场景。它通过RadixAttention前缀缓存技术,在处理JSON、正则表达式、工具调用等具有重复前缀的复杂工作流时,能实现极速生成。如果你正在构建智能体或多轮对话系统,并追求远超vLLM的推理性能,SGLang是理想选择。

查看技能