Use when drafting or editing a post or thread for X (Twitter) — voice, hooks, length, threads, hashtags, and links.
npx skills add https://github.com/vercel-labs/eve-content-agent-template --skill x-style
When writing or editing a post for X:
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.
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.
~240–259 characters tends to travel well. Lowercase openers are fine when they read naturally.
own sake. Prefer native video over a link out.
rewards genuine replies, so end on an open question or a real conversation starter instead.
rather than in the main post.
1/, 2/) only for longer threads where it aids the reader; don't force it.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 thelint_against_style tool (surface x) on your draft before proposing it to the writer.
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.Take vercel-labs/eve-content-agent-template-x-style from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.