agentleFS
dmzoneilldmzoneill/skills/manage-local-services/SKILL.md

manage-local-services

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Manage workflow daemon services - MCP, SLOP, Slack, Ollama, Scheduler. Start, stop, restart, status. Use when user says "start MCP", "restart slack daemon", "service status".

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    If action in [start, restart]: systemctl_daemon_reload() first

    line 47
  2. Very specific:

    If target includes mcp: journalctl_unit(unit="aa-workflow-mcp.service", lines=10) — recent logs

    line 57

≈ “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

Manage Local Services

Manage workflow daemon services (MCP, SLOP, Slack, Ollama, Scheduler).

Inputs

InputTypeDefaultPurpose
actionstringrequiredstart, stop, restart, status
servicestring"all"all, mcp, slop, slack, ollama, scheduler

Service Unit Mapping

Servicesystemd unit
mcpaa-workflow-mcp.service
slopaa-workflow-slop.service
slackaa-workflow-slack.service
ollamaollama.service
scheduleraa-workflow-scheduler.service

Persona

Load infra persona (systemd, journalctl tools).

Workflow

1. Bootstrap

  • persona_load("infra")
  • Resolve service: if service="all", target all units; else target single unit

2. Current Status

  • systemctl_list_units(pattern="aa-workflow-*") — workflow units
  • systemctl_is_active(unit="aa-workflow-mcp.service") — MCP
  • systemctl_is_active(unit="aa-workflow-slop.service") — SLOP
  • systemctl_is_active(unit="aa-workflow-slack.service") — Slack
  • ollama_status() — Ollama
  • cron_status() — scheduler
  • cron_list() — cron jobs

3. Perform Action

  • If action in [start, restart]: systemctl_daemon_reload() first
  • For each target unit:
    • start: systemctl_start(unit=...)
    • stop: systemctl_stop(unit=...)
    • restart: systemctl_restart(unit=...)

4. Post-Action Status

  • systemctl_status(unit="aa-workflow-mcp.service") — MCP status
  • systemctl_status(unit="aa-workflow-slop.service") — SLOP status
  • systemctl_status(unit="aa-workflow-slack.service") — Slack status
  • If target includes mcp: journalctl_unit(unit="aa-workflow-mcp.service", lines=10) — recent logs

5. Error Handling

  • On "failed" or "error": learn_tool_fix("systemctl_{action}", "service failed", "Service failed to {action}", "Check journalctl_unit for logs")

6. Session Log

  • memory_session_log("Managed local services: {action} {service}", "Running: X/Y")

Quick Actions

  • Check logs: journalctl_unit(unit="aa-workflow-mcp.service", lines=50)
  • Restart all: skill_run("manage_local_services", '{"action": "restart", "service": "all"}')
  • Investigate: skill_run("investigate_service_issues", '{"service_name": "aa-workflow-mcp"}')

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.