agentleFS
VercelKnown publishervercel-labs/eve-content-agent-template/agent/skills/x-style/SKILL.md

x-style

Skill28 starsChanged 21 days agoApache-2.0View on GitHub

Use when drafting or editing a post or thread for X (Twitter) — voice, hooks, length, threads, hashtags, and links.

2 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When writing or editing a post for X:

    line 7
  2. Distinctive:

    No engagement bait ("RT if you agree", "read that again", "let that sink in").

    line 21
  3. Distinctive:

    Keep them scrolling with small expansion hooks every few posts.

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.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

  1. Hook — the surprising claim or the moment, line one.
  2. Turn — the tension, or the thing most people get wrong.
  3. Payoff — what you learned, with a concrete detail.
  4. 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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.