agentleFS
Sign inStart free
sherificansherifican/Agent-FleetOps/skills/fleet-operational-runbook/SKILL.md

fleet-operational-runbook

Skill34 starsChanged 38 days agoMITView on GitHub

Perform routine handoffs and file operations with an explicit destination check after each action.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Use a deployment's documented handoff channel for routine cross-machine or cross-team work.

    line 9
  2. Distinctive:

    Read the destination, naming, and access rules from project documentation.

    line 12
  3. Distinctive:

    Write a self-contained instruction artifact: goal, inputs, ordered steps, expected output, verification method, and requested response.

    line 18
  4. Distinctive:

    Verify that the recipient-side location contains the instruction before reporting the handoff.

    line 20
  5. Distinctive:

    Do not directly control a remote environment when the deployment requires an auditable handoff instead.

    line 24

≈ “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

Fleet Operational Runbook

Overview

Use a deployment's documented handoff channel for routine cross-machine or cross-team work. Prefer the simplest auditable transfer path and verify the destination before considering any operation evidenced.

Procedure: publish a handoff artifact

  1. Read the destination, naming, and access rules from project documentation.
  2. Copy or upload the artifact to the documented handoff location.
  3. Inspect the destination for existence and expected size or checksum.
  4. Report the exact destination and verification evidence; stop on a mismatch.

Procedure: request work on another machine

  1. Write a self-contained instruction artifact: goal, inputs, ordered steps, expected output, verification method, and requested response.
  2. Send it through the documented handoff channel.
  3. Verify that the recipient-side location contains the instruction before reporting the handoff.

Rules

  • Quote paths that can contain spaces or shell-special characters.
  • Do not directly control a remote environment when the deployment requires an auditable handoff instead.
  • Name research legs and artifacts according to the project convention so reconciliation can attribute them.

Verification checklist

  • The destination was inspected after transfer.
  • Naming and destination rules were followed.
  • Any cross-machine work includes self-contained instructions.

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