agentleFS
belzoralolbtwbelzoralolbtw/x-agent-skill/skills/x-setup/SKILL.md

x-setup

Skill0 starsChanged 34 days agoMITView on GitHub

Set up this X (Twitter) skill pack for a specific account: build the voice profile the other skills read and a starter content base. Use on first run, when the user installs the pack, when a skill says the voice profile is missing, or when onboarding a new account. Produces `templates/voice.md` and a first batch of raw material to post from.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. anotb/x-signal★ 1same name

    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 repository9 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, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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. Distinctive:

    Every skill in this pack writes in one voice.

    line 13
  2. Distinctive:

    Ask in one batch, and accept pasted text for all of it:

    line 18
  3. Very specific:

    4. Point them at the next step: After setup, the order is: x-profile (fix the landing page), then x-reply (start reaching people), then …

    line 41

≈ “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-setup

Every skill in this pack writes in one voice. This skill builds that voice once so the others do not have to guess. Run it before anything else.

What you need

Ask in one batch, and accept pasted text for all of it:

  1. Three of their own posts that sound most like them. Not their best performers, their most them. These define the voice.
  2. What they do, one sentence, and who they are talking to.
  3. What they will not say: topics off limits, claims they cannot make, a tone they refuse.
  4. Proof they can point to: numbers, results, projects, dates.

The loop

1. Write templates/voice.md from the answers. Fill every section. If an answer is missing, leave the field blank and tell the user, rather than inventing a voice. A wrong voice is worse than an empty template.

2. Read the three posts closely. Note sentence length, how they open, how they close, the words they reach for, the punctuation they use, and the words they avoid. Put the specifics in the file, not adjectives about the file.

3. Build the raw material list for later skills to draw from: results, mistakes, opinions, things they explain often, questions they get asked. Aim for at least ten items. This is the fuel for x-plan and x-post.

4. Point them at the next step. After setup, the order is: x-profile (fix the landing page), then x-reply (start reaching people), then x-post and x-plan.

Failure modes

  • Writing a generic voice file ("friendly and professional"). That describes nobody and the skills cannot use it.
  • Guessing the voice from one post, or from the user's job title.
  • Filling the "what they will not say" section with nothing. Every account has something it refuses; find it.
  • Building a content list of topics instead of raw material. "Marketing" is a topic. "I tripled signups with one email" is raw material.

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.