agentleFS
matthewdonsemail-labmatthewdonsemail-lab/log/.claude/skills/log-twitter-followers/SKILL.md

log-twitter-followers

Skill63 starsChanged 3 days agoMITView on GitHub

Checking who really follows you. A log play (docs/useCases/twitter/followers.md): Before a slide, a page or a message says someone follows you (or that you follow them), check it live on X. Engaging with you isn't following you. This page reads it on the account's own session and sends nothing.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are 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.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before a slide, a page or a message says someone follows you (or that you follow them), check it live on X.

    line 15
  2. Distinctive:

    The full follower list comes from the account's own session,: not from who engaged.

    line 37

≈ “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

Checking who really follows you

This is the log play twitter/followers. Before anything else, call the log MCP tool getGuide({ useCase: "twitter/followers" }): it returns this page and makes it the session's play, so every log tool's answer says which step you are on and a send with no play loaded is refused (rules 157, 158). Then follow the steps in order.

Draft every message from that person's own thread and matt's real replies (voice with no text, search), never from memory, and never send two that read alike (sameAsSent).

Before a slide, a page or a message says someone follows you (or that you follow them), check it live on X. Engaging with you isn't following you. This page reads it on the account's own session and sends nothing.

How the owner asks for it: "does <someone> follow me", "check who really follows me on x", "is <someone> following me on twitter", "check these people follow me before the slide says so".

Run it from a fresh context

Say: "go on docs/useCases/twitter/followers.md for <handles>", or "for everyone named on <page>". The agent then reads this page and README.md and runs the steps.

The steps

#StepToolDone when
0Session checktwitterSessionCheckloggedIn
1For each handle: do they follow the account, does the account follow themtwitterFollows { account, handles: ["a", "b", "c"] }one answer per handle, from X
2Take anyone who doesn't follow off the "followers" line, or reword the linethe page or copyevery name on it is true today

Handles come from research or from the owner, never guessed (rule 53). The read is 1.5 s per handle, so a long list takes a minute.

What the runs taught

  • People who engage aren't always followers. A slide naming the account's "circle" listed people who had only engaged; two of them didn't follow. Every named follower now gets this check first.
  • The full follower list comes from the account's own session, not from who engaged.

Reading the list

log twitter followers --account <a> (MCP twitterFollowers) reads the account's full follower list on its own session, on the direct-API engine.

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.