agentleFS
itentialitential/infra-agent-skills/skills/network-health-verification/SKILL.md

network-health-verification

Skill1 starsChanged 32 days agoApache-2.0View on GitHub

Screen network devices for health problems (CPU, memory, logs, core files, crashinfo) after a change or while troubleshooting. Use to run documented health checks as part of a job run and read each check's result. Covers Cisco pyATS Health Check in integrated job mode; assumes pyATS, a testbed, authenticated device access, and an existing pyATS job. Thresholds are inputs; this does not decide what "healthy" means for a network.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run health checks against network devices and report what each check observed.

    line 8
  2. Very specific:

    Use to confirm devices are healthy after a change, or to screen for resource, log, or crash problems while troubleshooting, by running …

    line 12

≈ “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

Network Health Verification

Run health checks against network devices and report what each check observed.

When to use this skill

Use to confirm devices are healthy after a change, or to screen for resource, log, or crash problems while troubleshooting, by running health checks with a job. Capturing state snapshots to compare yourself belongs to network-state-collection. Applying the change itself is outside this skill.

Universal concepts

  • A health result reflects only the checks, thresholds, and device coverage actually run; unsupported or skipped checks are unknown, not healthy.
  • Some checks have side effects (clearing logs, copying or deleting crash files) and need explicit approval before the run.
  • Thresholds and criteria are caller inputs, not defaults this skill defines.

Procedure

  1. Identify the requested tool in references/INDEX.md.
  2. Open the linked procedure and follow it exactly, including its confirmation gates.
  3. Report results using that procedure's own status vocabulary.

Known limitations

The tool's side-effect options are flagged in its procedure. Coverage is limited to the implementation in the index.

Contributing to this skill

Change this router only to correct its shared concepts/routing or add a supported tool pointer. Tool details belong in that tool's references. Recheck the universal concepts before adding a tool.

Tools

A local pyATS job/CLI session with device transport; the mode procedure lists the specifics.

Verification checklist

  • Tool matches an entry in the index.
  • The selected procedure's checks and confirmation gates were followed.
  • Results and documented failures are reported without replacing their status vocabulary.

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.