agentleFS
brandonjjonbrandonjjon/solo-skill/SKILL.md

solo

Skill2 starsChanged 8 months agoMITView on GitHub

Manages local development processes (Vite, Horizon, Reverb, Pail, etc.) via the Solo MCP server. Use this skill when the user wants to start, stop, restart, or check the status of local dev services; read or search process output/logs from running services; check which ports processes are using; investigate CPU or memory usage of dev processes; or mentions Solo, SoloTerm, or solo.yml. Also activate when diagnosing local build failures (e.g. "CSS not updating", "Vite manifest error"), local WebSocket connection drops (checking Reverb output), stuck local queue workers (checking Horizon output), or any problem where reading a running dev process's stdout/stderr would help — even if the user doesn't mention Solo by name. Do NOT use for: configuring or installing Horizon/Reverb/Pulse (use those dedicated skills instead), reading Laravel log files (laravel.log), production server issues, or application code changes.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. anthropics/claude-plugins-official★ 46ksame name
    2. simoncorry/foundry★ 39same name
    3. Rhovian/niles★ 4same name
    4. ORBWEVA/solo-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    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. Distinctive:

    Before using any process tools, you need an active project selected:

    line 26
  2. Very specific:

    Call list_projects — if only one project exists, it auto-selects

    line 28
  3. Very specific:

    If multiple projects exist, call select_project with the correct project_id

    line 29
  4. Distinctive:

    When the user reports a frontend issue or you see a Vite manifest error:

    line 56
  5. Very specific:

    Check for connection errors, auth failures, or port conflicts with get_process_ports

    line 67
  6. Distinctive:

    If a process shows as stopped unexpectedly, read its output for crash details before restarting

    line 71

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “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

Solo Dev Process Management

Solo (SoloTerm) is a desktop app that manages development processes like asset bundlers, queue workers, and WebSocket servers. It exposes MCP tools (prefixed mcp__solo__) that let you control and inspect these processes without the user needing to switch to a terminal.

Getting Started

Before using any process tools, you need an active project selected:

  1. Call list_projects — if only one project exists, it auto-selects
  2. If multiple projects exist, call select_project with the correct project_id

You only need to do this once per session. All subsequent calls operate on the selected project.

Choosing the Right Tool

To understand what's running:

  • get_project_status — overview of all processes and their states (start here)
  • list_processes — list process names and configurations
  • get_project_stats — CPU and memory usage, sorted by memory (use when investigating performance)

To control processes:

  • start_process / stop_process / restart_process — act on a single process by name
  • start_all_processes / stop_all_processes / restart_all_processes — act on everything at once

To read output:

  • get_process_output — recent stdout/stderr (default 50 lines; pass lines param for more)
  • search_output — find lines matching a pattern (case-insensitive substring; pass max_results to control volume)
  • clear_output — flush a process's output buffer

Other:

  • get_process_ports — which TCP ports a process is listening on
  • setup_agent_integration — add Solo docs to the project's CLAUDE.md

Common Workflows

Debugging build errors

When the user reports a frontend issue or you see a Vite manifest error:

  1. get_process_output on the bundler process (usually "Vite")
  2. search_output for "error", "failed", or "warning" if the output is long
  3. Fix the issue, then restart_process to pick up changes

Debugging queue / job failures

  1. get_process_output on the queue worker (usually "Horizon")
  2. search_output for "fail", "exception", or the specific job class name

Debugging WebSocket issues

  1. get_process_output on the WebSocket server (usually "Reverb")
  2. Check for connection errors, auth failures, or port conflicts with get_process_ports

Checking if services are healthy

  1. get_project_status for a quick overview
  2. If a process shows as stopped unexpectedly, read its output for crash details before restarting

Important Constraints

  • Processes must be trusted in the Solo UI before they can be started via MCP. If start_process fails, tell the user to trust the process in Solo first.
  • Solo can read output but cannot send interactive input to processes.
  • Process names are defined in the project's solo.yml — read it if you need the exact names.

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.