vercel-labs/eve-content-agent-template/x-style
Claude Code and agent skill by vercel-labs/eve-content-agent-template
- community
Checking that the SKILL.md file is still in the repository.
Use when drafting or editing a post or thread for X (Twitter) — voice, hooks, length, threads, hashtags, and links.
Install
npx vskill@latest install vercel-labs/eve-content-agent-template/x-styleSKILL.md
X (Twitter) voice & style
When writing or editing a post for X:
- Hook first. The first line decides whether anyone stops scrolling — open on the
surprising claim, the number, the contradiction, or the moment. No throat-clearing, no "A thread on…". A hook isn't clickbait: promise only value the post actually delivers.
- One idea per post. Free accounts cap at 280 characters. If you have more to say, write a
thread, don't cram. Even when the account has Premium, the in-feed preview is still ~280 — so the point has to land in the first 280 either way.
- Plain and punchy. Short sentences. Cut every word that isn't load-bearing. Aim tight —
~240–259 characters tends to travel well. Lowercase openers are fine when they read naturally.
- Concrete over abstract: a result, a number, a before/after. No vague inspiration.
- Text carries on X — add an image or native video only when it carries the point, not for its
own sake. Prefer native video over a link out.
- At most 0–2 real hashtags. 1–2 can help; 3+ tends to hurt. No hashtag walls, no emoji clutter.
- No engagement bait ("RT if you agree", "read that again", "let that sink in"). The algorithm
rewards genuine replies, so end on an open question or a real conversation starter instead.
- Links suppress reach on X — when a post needs a link, put it in the first reply and say so,
rather than in the main post.
Threads
- The first post must stand on its own and earn the tap — it's a hook, not a table of contents.
- One beat per post; each should be worth reading even out of context.
- Keep them scrolling with small expansion hooks every few posts.
- Number posts (
1/,2/) only for longer threads where it aids the reader; don't force it. - Close with a payoff or a single clear takeaway — not "follow me for more".
Structure
- Hook — the surprising claim or the moment, line one.
- Turn — the tension, or the thing most people get wrong.
- Payoff — what you learned, with a concrete detail.
- Close — one takeaway or a genuine question.
References
references/best-practices.md— sourced checklist of current X tactics (hooks, length,
links, hashtags, threads, cadence).
references/post-specs.md— concrete specs: character limits, hashtag norms, media, links.references/banned-words.json— words to avoid. Read it once for awareness, then run the
lint_against_style tool (surface x) on your draft before proposing it to the writer.
Shared references
Shared global references for all skills in the content agent. These apply regardless of the content type.
references/ai-phrases-to-avoid.md— AI-tell words, phrases, and punctuation to avoid.references/plain-english-alternatives.md— plain-English swaps for bloated or vague wording.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingagent/skills/x-style/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/vercel-labs/eve-content-agent-template/x-style)