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

x-profile

Skill0 starsChanged 35 days agoMITView on GitHub

Audit and rewrite an X (Twitter) profile so a stranger who clicks from a reply or a post decides to follow. Use when the user wants to fix their bio, name, pinned post, or link, asks why their profile does not convert, or says people visit but do not follow. Produces a pass/fail score on seven checks and rewritten name, bio, and pinned post.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. Jakeschincariol/x-agent-skill★ 4same name
    2. lxyang20131208-star/x-algorithm-skills★ 1same name
    3. lloyd3126/chenchungnien-skills★ 0same name
    4. swayamdhawan/x-agent★ 0same 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

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for the current profile: name field, handle, bio, location, link, pinned post, follower and following counts, and the last ten posts.

    line 20
  2. Very specific:

    Read the voice profile (templates/voice.md), or infer the voice from those posts.

    line 22
  3. Very specific:

    Read rubric.json in this folder.

    line 23
  4. Distinctive:

    4. Rewrite or replace the pinned post: If the account has a strong recent post, pin it.

    line 52
  5. Distinctive:

    No hashtags in the bio. No emoji walls.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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-profile

On X, the profile is the landing page. A reply or a good post earns the click; the profile decides whether the click becomes a follower. Most accounts leak followers here and never see it, because they never look at their own profile the way a stranger does.

Before you write

  1. Ask for the current profile: name field, handle, bio, location, link, pinned post, follower and following counts, and the last ten posts.
  2. Read the voice profile (templates/voice.md), or infer the voice from those posts.
  3. Read rubric.json in this folder. Seven checks, each pass or fail, each with the failure it catches and the fix.

The one test that matters

A stranger lands on the profile. Give them three seconds. They are asking two questions, in this order: "what will I get if I follow?" and "is this person real?" Everything on the profile either answers those or wastes the three seconds.

The loop

1. Score the profile against all seven checks in rubric.json. Show it as a table: check, pass or fail, the specific reason. Be blunt. A passing badge on a weak profile helps no one.

2. Fix the fails, in order. Name field first if it fails (it is the search surface), then bio line 1, then the pinned post. Give the rewritten text, not advice about it.

3. Rewrite the bio as one version, not three. A bio is not a place to A/B test; it is a place to say what you do. Format:

Line 1   who you help + do what, or plainly what you post about.
Line 2   proof, or the specific result you produce.
Line 3   optional: a light human detail, or a call to the link/pinned post.

4. Rewrite or replace the pinned post. If the account has a strong recent post, pin it. If not, write a short "start here" post: one line on what the account is about and one line pointing to the best thing they have.

5. Humanize the bio and pinned post (x-human). A bio that reads as AI undoes the trust the rest of the profile is trying to build.

Rules of thumb

  • The name field is search. Put the category in it, e.g. Sam | SEO for SaaS.
  • The bio is for the reader, not the owner. "I help X do Y" beats "passionate about Y".
  • One proof point beats three adjectives. A number, a name, or a link.
  • No hashtags in the bio. No emoji walls. No "DM me to grow your account".
  • The link, if present, should be the most useful single page, not a homepage.

Failure modes

  • Writing a clever bio that sounds great and communicates nothing.
  • Rewriting the bio while the pinned post still shows a dead launch from eight months ago.
  • Adding more claims when the problem was the absence of proof.
  • Changing the name field to a joke and losing the search keyword.
  • Optimizing the profile while the timeline has nothing a new follower wants.

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.