agentleFS
tang-vutang-vu/social-posting-skills/skills/post-x/SKILL.md

post-x

Skill9 starsChanged 2 months agoMITView on GitHub

Adapt and publish campaign items on X (Twitter) — single posts and threads

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Do NOT mass-like, mass-follow, or recycle identical replies.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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) Adapter

Machine-checkable facts (char limits, media bounds, publish modes) live in platforms/x.json — the CLI validates against them. Do not hardcode numbers here; they go stale.

What X rewards (culture, not algorithm folklore)

  • One sharp claim per post. The hook decides whether a thread gets read.
  • Threads that teach: numbered steps, one idea per post, 5–10 posts.
  • Build-in-public: real numbers, real decisions, real failures.
  • Conversation over broadcasting — replies are where accounts grow.

Drafting from the content graph

  • core-claim → post 1 (hook). Cut adjectives; keep the strongest noun/verb.
  • proof/technical nodes → thread posts 2..n, one per post.
  • cta + link → last post, or a self-reply (see link note).
  • Disclosures belong IN the content: "I built this" reads natively on X.

Link note (heuristic, labeled)

Widely held community practice: put the external link in a self-reply rather than the main post, to keep the post clean. The reach impact is a heuristic — the platform data marks it community-heuristic, not a documented rule.

Publishing

  • agent-browser → execute playbook.json literally: composer selectors, "add to thread" for chains, bounded waits, verify once after Post.
  • api → official X API exists but is paid-tier; adapter not implemented.
  • manual → draft package with the full thread laid out.

On any challenge, ambiguous composer state, or uncertain post state: STOP and report unknown — never re-submit.

Genuine engagement (human participation)

  • Reply substantively to comments on your post — add information, not "thanks!".
  • Participate in your niche between posts because you have something to say, not as a distribution ritual.
  • Do NOT mass-like, mass-follow, or recycle identical replies. These are the behaviors platforms penalize and this project prohibits.

Pitfalls

  • Typing via automation: chunk long text; emoji/unicode may not type.
  • Rate limits are real — campaign volume should stay far below caps.
  • Identical text cross-posted verbatim reads as spam; adapt per platform.

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.