agentleFS
anotbanotb/x-signal/skills/x-monitoring/SKILL.md

x-monitoring

Skill1 starsChanged 3 months agoMITView on GitHub

Create, run, inspect, pause, resume, and compare durable X Signal monitors. Use when X queries, accounts, or Following should be checked repeatedly or compared over time.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Call x_monitor with list and reuse a monitor when its sources and cadence match.

    line 8
  2. Distinctive:

    Create explicit labeled queries, accounts, optional Following, cadence, filters, and optional webhook or ntfy sink.

    line 9
  3. Very specific:

    When current output is requested, call run immediately.

    line 10
  4. Very specific:

    Run results to compare successive captured samples.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 monitoring

  1. Call x_monitor with list and reuse a monitor when its sources and cadence match.
  2. Create explicit labeled queries, accounts, optional Following, cadence, filters, and optional webhook or ntfy sink. Report it active only after successful creation.
  3. When current output is requested, call run immediately; scheduled activation alone is not a current result.
  4. Run results to compare successive captured samples. Report newly observed and no-longer-observed posts, meaningful metric and author changes, lexical cluster shifts, partial legs, and delivery state. Absence from a sample does not establish deletion.
  5. Preserve direct X links from the stored run. Use pause, resume, update, or delete only when the user asks for that state change.

Collection continues on its configured cadence while notification delivery retries in capture order. Inspect the monitor's delivery health for pending notifications, last captured run, next capture, and next delivery attempt. The delivered baseline advances only after successful delivery; retrying a pending notification before the next capture is due does not repeat X work. Do not recreate a monitor to recover a broken sink.

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.