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

x-audit

Skill0 starsChanged 34 days agoMITView on GitHub

Audit an X (Twitter) account from pasted analytics and a sample of posts, and say what is working, what is not, and what to change first. Use when the user wants an account review, "why am I not growing", a content audit, feedback on their posts, or help reading their analytics. Produces a ranked diagnosis and a short list of changes in priority order.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. Jakeschincariol/x-agent-skill★ 4same name
    2. lxyang20131208-star/x-algorithm-skills★ 1same name
    3. 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, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Ask for, in one batch:

    line 18
  2. Distinctive:

    If analytics are unavailable, say so and audit the posts alone.

    line 26
  3. Distinctive:

    1. Name the one bottleneck: Not five problems. The single constraint that, if fixed, moves everything else.

    line 46
  4. Distinctive:

    If one post format outperformed, the answer is often "do more of this one".

    line 57
  5. Very specific:

    If the account has fewer than about 20 posts, there is not enough to audit.

    line 70

“Common” is measured: kept by at least 6 in 10 of the 3 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-audit

Most growth advice fails because it is generic. This skill works from the account's own numbers and posts to find the specific leak.

Before you write

Ask for, in one batch:

  1. Analytics for 30 days: impressions, engagement rate, profile clicks, follows, and the top 5 and bottom 5 posts by impressions.
  2. Ten recent posts pasted as text, with their numbers if available.
  3. The goal: followers, leads, authority, or a launch. Growth without a goal is just a bigger number.

If analytics are unavailable, say so and audit the posts alone. Do not invent numbers to have something to analyze.

How to read the numbers

High impressions, low follows    Reach is fine, the profile or niche is the leak.
                                 Fix: x-profile, or narrow the lane.
Low impressions, high follows    Content is strong, distribution is weak.
                                 Fix: x-reply, more replies, more reach posts.
High views, no replies           The posts do not invite a response. The close
                                 is weak, or the posts are all statements.
Engagement but no profile clicks Readable but not distinctive. No reason to
                                 want more from this specific person.
Great one week, dead the next    Cadence problem, not a content problem.
                                 Fix: x-plan, a size they can keep.

The loop

1. Name the one bottleneck. Not five problems. The single constraint that, if fixed, moves everything else. Most accounts have exactly one.

2. Rank the diagnoses. What the numbers support, strongest first, each tied to a specific post or number. "Your top post got 40k impressions and 12 follows, so the reach is there and the profile is where they leave."

3. Give changes in priority order, three at most. Each one: what to do, which skill does it, and how they will know in a week whether it worked.

4. Point at the wins to repeat. The audit is not only about what is broken. If one post format outperformed, the answer is often "do more of this one".

Failure modes

  • A list of generic tips. Every line has to point at this account's own data.
  • Blaming the algorithm. The algorithm rewards replies and dwell; if those are low, that is a content fact, not a mystery.
  • Recommending "post more" when the real problem is the profile or the lane.
  • Auditing vanity metrics. Follows and profile clicks are the ones that matter.
  • Fixing everything at once, so nothing can be measured.

When not to act

If the account has fewer than about 20 posts, there is not enough to audit. Say so plainly and point them at x-plan and x-reply instead of pretending to find a pattern in noise.

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.