agentleFS
Sign inStart free
coolxeocoolxeo/grok-bot-skills/skills/writing/x-article/SKILL.md

x-article

Skill7 starsChanged 17 days agoMITView on GitHub

Use this when writing or rewriting an X Article (long-form on x.com/i/article), with images between sections, a first-line hook, and no invented numbers.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use for X Articles (x.com/i/articles or compose/articles), not tweets or 1/2/3/4 threads.

    line 10
  2. Distinctive:

    No invented token counts, dollar figures, or quotes.

    line 22
  3. Distinctive:

    Do not recap ranking cards as the article.

    line 24
  4. Distinctive:

    No AI slop (edit, minimum change).

    line 32

≈ “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 Article

Use for X Articles (x.com/i/articles or compose/articles), not tweets or 1/2/3/4 threads.

Form

  • Title is short and concrete.
  • First line of the body is the hook. If it is weak, change the entry point before polishing.
  • Research body: question → what you looked at → what you could measure → what you could not.
  • Images sit between sections, not as a dump at the end. Diagrams that explain the next paragraph. No decoration. Cover is type-only, no product mascot on a founder/research piece.
  • Closer is one usable line. Hashtags only at the end, 0–2 (#buildinpublic when it is actually build-in-public).

Research rules

  • No invented token counts, dollar figures, or quotes.
  • Named instruments only (disk, chat volume, subagents, ad spend, HTTP bytes, git blobs).
  • Do not recap ranking cards as the article. Cards support a finding.
  • Source-check every claim. Unverified numbers come out.

Pipeline

  1. Outline (hook options, mechanism, evidence gaps).
  2. Draft section by section.
  3. Source-check.
  4. No AI slop (edit, minimum change).
  5. Hand a draft to whoever holds the account. Do not post.

Voice

First person, specific, short sentences mixed with longer ones. No unrelated product-promo CTA on a founder/research Article. No press-release tone.

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.

Check your setup, free