agentleFS
Sign inStart free
CsHengCsHeng/agent-skills/skills/routeros-scripting-guidelines/SKILL.md

routeros-scripting-guidelines

Skill3 starsChanged 8 days agoMITView on GitHub

Apply RouterOS v7 scripting language guidance when writing, reviewing, or diagnosing persisted .rsc files, script repository sources, scheduler, Netwatch, PPP or DHCP event bodies, imports, error handling, permissions, or external I/O. Use as a conditional language overlay; the primary workflow retains repository ownership and live-device authority.

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:

    Read only the references needed for the current task:

    line 12
  2. Distinctive:

    Keep secrets in the repository or runtime secret mechanism, and diagnose permission errors by caller, invocation form and policy sets first.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

RouterOS Scripting Guidelines

Apply RouterOS language and execution semantics inside the active primary workflow. Verify syntax and version-specific behavior against the current MikroTik Scripting manual and the target version's actual execution context; repository examples show patterns and defer to the manual.

References

Read only the references needed for the current task:

  • For declarations, scopes, variable names, values, arrays, substitutions, functions, and object selection, read language-and-values.md.
  • For script repository, CLI/import, scheduler, Netwatch, PPP, DHCP, caller permissions, and background execution, read execution-contexts-and-permissions.md.
  • For convergence, runtime errors, retries, imports, external I/O, logging, and validation, read convergence-and-external-io.md.

Working Method

  1. Identify the RouterOS version and exact execution context before choosing syntax, built-in variables, or permission assumptions.
  2. Separate expected absence or no-op state from a runtime failure, then make the caller-owned failure policy explicit.
  3. Validate with the narrowest safe oracle available, escalating from source inspection to import dry-run or live execution when the primary workflow authorizes it. Take the live-device apply path, backup and rollback policy from the primary workflow and repository owner.
  4. Keep secrets in the repository or runtime secret mechanism, and diagnose permission errors by caller, invocation form and policy sets first.

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.

Check your setup, free