Claude Skill

docs

Teach your coding agent to use proc: install the proc-cli skill for Claude Code, Codex, Cursor, Gemini CLI and others.

LLM Mart · 0 points · 1 views 151 listing impressions 0 install-command copies
Download yazeed-proc-cli-docs-e3b8074.zip · 516 KB

Install

skills CLI npx skills add https://github.com/yazeed/proc-cli/tree/main/docs
Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install yazeed-proc-cli@llmmart
Git git clone https://github.com/yazeed/proc-cli.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole yazeed/proc-cli collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

The proc-cli skill teaches coding agents (Claude Code, Codex, Cursor, Gemini CLI and others) when to reach for proc and how to use it safely. Instead of lsof -ti :3000 | xargs kill -9, your agent previews with proc free :3000 --dry-run, reads structured JSON, and checks with you before touching a process it didn't start. It adds --yes only for a process it started itself or after you've seen the list and agreed, and never with a name. proc enforces its side too: nothing that stops, kills or pauses a process runs without --yes unless a person confirms at the prompt, --json never counts as a yes, and a name matches only the whole process name.

Install

proc itself has to be installed first (see install). Then add the skill:

npx skills add yazeed/proc-cli

Or with bun:

bunx skills add yazeed/proc-cli

To pick the agent and where it's installed:

npx skills add yazeed/proc-cli --skill proc-cli -a claude-code -y   # one agent, this project
npx skills add yazeed/proc-cli --skill proc-cli -g                   # every project (user-level)

Claude Code plugin

In Claude Code, you can install it as a plugin instead:

/plugin marketplace add yazeed/proc-cli
/plugin install proc-cli@proc-cli

Update

npx skills update

Installs always fetch the current skill from the repository, so a new install is up to date too. The skill is written for proc 2.0 or later. It tells your agent to check proc --version, and to ask you to upgrade rather than run destructive commands on an older proc.

What your agent learns

  • When to use proc: a busy port (EADDRINUSE, "address already in use"), what's listening on a port or running in a directory, stopping or freeing something, a dev server that won't start, a stuck process or a slow machine, and cleaning up the servers and browsers it started. Not containers, system services or remote hosts
  • A safety model on the first screen: which commands only read, which can be undone (freeze, thaw), and which end a process (stop, kill, free); a process is its own only if it started it and recorded the PID; a name is a search, not approval
  • The contract: --json on every command, one JSON document per command (watch streams one per refresh), and fixed exit codes (0 success, 1 error, 2 not found, 3 permission denied, 4 invalid input or confirmation needed). Every error says why in reason, and the agent branches on it, never on the text; exit 4 means nothing changed (invalid_input, needs_confirmation or not_supported); with needs_confirmation it shows you the list, and it doesn't retry with --yes on its own
  • Playbooks: a busy port, stopping its own servers by PID with a guard (--start-time, --in and --by), stopping something it didn't start only after you approve the PIDs, cleaning up only what it recorded, and reading stuck and orphans as leads rather than verdicts
  • Safety: preview with --dry-run, show you the PID, name, directory, command and parent, and wait for a yes; prefer stop over kill; never --kill on orphans or stuck; ask before sudo
  • Gotchas: kill and stop don't signal child processes, :3000 is a port but 3000 is a PID, a port can have several holders, --in narrows a search but doesn't prove a process is the agent's, and an orphaned process isn't necessarily abandoned

Try it

Once it's installed, ask your agent things like:

  • "What's on port 3000?"
  • "Port 3000 is taken, free it"
  • "Why is port 8080 busy?"
  • "What did you leave running in this project?"
  • "My machine is slow, what's using the CPU?"
  • "Wait for the build to finish, then start the server"

Where it lives

Files (proc-cli)
  • assets
    • css
      • style.css 22.7 KB · in bundle
    • js
      • site.js 8.3 KB
        Loading…
    • demo.mp4 377.2 KB · in bundle
    • social-card.png 45.3 KB · in bundle
  • commands
    • by.md 2.4 KB
      Loading…
    • for.md 2.3 KB
      Loading…
    • free.md 1.5 KB
      Loading…
    • freeze.md 1.9 KB
      Loading…
    • in.md 2.2 KB
      Loading…
    • index.md 4.7 KB
      Loading…
    • info.md 3.1 KB
      Loading…
    • kill.md 2.9 KB
      Loading…
    • list.md 3.2 KB
      Loading…
    • on.md 4.2 KB
      Loading…
    • orphans.md 1.8 KB
      Loading…
    • ports.md 1.4 KB
      Loading…
    • stop.md 2.3 KB
      Loading…
    • stuck.md 2 KB
      Loading…
    • thaw.md 1.7 KB
      Loading…
    • tree.md 2.2 KB
      Loading…
    • unstick.md 1.9 KB
      Loading…
    • wait.md 2.5 KB
      Loading…
    • watch.md 3.2 KB
      Loading…
    • why.md 1.7 KB
      Loading…
  • _data
    • faq.yml 7 KB
      Loading…
    • reader.yml 11.1 KB
      Loading…
    • release.yml 140 B
      Loading…
  • _includes
    • changelog-nav.html 1.5 KB · in bundle
    • commands-nav.html 823 B · in bundle
    • reader-chips.html 492 B · in bundle
    • reader-explain.html 190 B · in bundle
    • schema.html 2.3 KB · in bundle
  • _layouts
    • default.html 3.8 KB · in bundle
    • page.html 676 B · in bundle
    • post.html 1.1 KB · in bundle
  • _posts
    • 2026-01-15-why-i-built-proc.md 4.4 KB
      Loading…
    • 2026-03-06-automating-process-management-shell-scripts.md 14 KB
      Loading…
    • 2026-03-06-find-kill-process-on-port-macos-linux.md 14.5 KB
      Loading…
    • 2026-03-06-proc-vs-lsof-fuser-killport-fkill.md 7.1 KB
      Loading…
    • 2026-03-06-ps-grep-awk-kill-pipeline-explained.md 9.3 KB
      Loading…
    • 2026-03-06-ss-vs-netstat-vs-lsof.md 12.2 KB
      Loading…
    • 2026-03-06-zombie-orphan-stuck-processes-guide.md 13.6 KB
      Loading…
    • 2026-03-10-eaddrinuse-address-already-in-use-fix.md 5.4 KB
      Loading…
    • 2026-03-10-kill-vs-pkill-vs-killall.md 6 KB
      Loading…
    • 2026-03-10-nodejs-child-process-management.md 7.6 KB
      Loading…
    • 2026-03-10-nohup-vs-disown-vs-background.md 6.4 KB
      Loading…
    • 2026-03-10-unix-signals-complete-reference.md 9.3 KB
      Loading…
    • 2026-10-25-whats-new-in-proc.md 5 KB
      Loading…
    • 2026-10-31-whats-new-in-proc-2.md 5.6 KB
      Loading…
  • apple-touch-icon.png 3.8 KB · in bundle
  • apt.md 1.4 KB
    Loading…
  • changelog.md 68.7 KB
    Loading…
  • CNAME 12 B · in bundle
  • faq.md 606 B
    Loading…
  • favicon.ico 4.1 KB · in bundle
  • favicon.svg 369 B · in bundle
  • index.html 10.3 KB · in bundle
  • install.md 4.1 KB
    Loading…
  • posts.html 767 B · in bundle
  • skill.md 4.6 KB
    ---
    layout: page
    title: Agent skill
    description: "Teach your coding agent to use proc: install the proc-cli skill for Claude Code, Codex, Cursor, Gemini CLI and others."
    permalink: /skill
    ---
    
    The proc-cli skill teaches coding agents (Claude Code, Codex, Cursor, Gemini CLI and others) when to reach for proc and how to use it safely. Instead of `lsof -ti :3000 | xargs kill -9`, your agent previews with `proc free :3000 --dry-run`, reads structured JSON, and checks with you before touching a process it didn't start. It adds `--yes` only for a process it started itself or after you've seen the list and agreed, and never with a name. proc enforces its side too: nothing that stops, kills or pauses a process runs without `--yes` unless a person confirms at the prompt, `--json` never counts as a yes, and a name matches only the whole process name.
    
    ## Install
    
    proc itself has to be installed first (see [install](install)). Then add the skill:
    
    ```bash
    npx skills add yazeed/proc-cli
    ```
    
    Or with bun:
    
    ```bash
    bunx skills add yazeed/proc-cli
    ```
    
    To pick the agent and where it's installed:
    
    ```bash
    npx skills add yazeed/proc-cli --skill proc-cli -a claude-code -y   # one agent, this project
    npx skills add yazeed/proc-cli --skill proc-cli -g                   # every project (user-level)
    ```
    
    ### Claude Code plugin
    
    In Claude Code, you can install it as a plugin instead:
    
    ```text
    /plugin marketplace add yazeed/proc-cli
    /plugin install proc-cli@proc-cli
    ```
    
    ## Update
    
    ```bash
    npx skills update
    ```
    
    Installs always fetch the current skill from the repository, so a new install is up to date too. The skill is written for proc 2.0 or later. It tells your agent to check `proc --version`, and to ask you to upgrade rather than run destructive commands on an older proc.
    
    ## What your agent learns
    
    - **When to use proc**: a busy port (`EADDRINUSE`, "address already in use"), what's listening on a port or running in a directory, stopping or freeing something, a dev server that won't start, a stuck process or a slow machine, and cleaning up the servers and browsers it started. Not containers, system services or remote hosts
    - **A safety model on the first screen**: which commands only read, which can be undone (`freeze`, `thaw`), and which end a process (`stop`, `kill`, `free`); a process is its own only if it started it and recorded the PID; a name is a search, not approval
    - **The contract**: `--json` on every command, one JSON document per command (`watch` streams one per refresh), and fixed exit codes (0 success, 1 error, 2 not found, 3 permission denied, 4 invalid input or confirmation needed). Every error says why in `reason`, and the agent branches on it, never on the text; exit 4 means nothing changed (`invalid_input`, `needs_confirmation` or `not_supported`); with `needs_confirmation` it shows you the list, and it doesn't retry with `--yes` on its own
    - **Playbooks**: a busy port, stopping its own servers by PID with a guard (`--start-time`, `--in` and `--by`), stopping something it didn't start only after you approve the PIDs, cleaning up only what it recorded, and reading `stuck` and `orphans` as leads rather than verdicts
    - **Safety**: preview with `--dry-run`, show you the PID, name, directory, command and parent, and wait for a yes; prefer `stop` over `kill`; never `--kill` on `orphans` or `stuck`; ask before `sudo`
    - **Gotchas**: `kill` and `stop` don't signal child processes, `:3000` is a port but `3000` is a PID, a port can have several holders, `--in` narrows a search but doesn't prove a process is the agent's, and an orphaned process isn't necessarily abandoned
    
    ## Try it
    
    Once it's installed, ask your agent things like:
    
    - "What's on port 3000?"
    - "Port 3000 is taken, free it"
    - "Why is port 8080 busy?"
    - "What did you leave running in this project?"
    - "My machine is slow, what's using the CPU?"
    - "Wait for the build to finish, then start the server"
    
    ## Where it lives
    
    - Source: [`skills/proc-cli/`](https://github.com/yazeed/proc-cli/tree/main/skills/proc-cli) in the repository ([`SKILL.md`](https://github.com/yazeed/proc-cli/blob/main/skills/proc-cli/SKILL.md), and [`reference.md`](https://github.com/yazeed/proc-cli/blob/main/skills/proc-cli/reference.md) for every JSON output)
    - Listing: [skills.sh/yazeed/proc-cli/proc-cli](https://www.skills.sh/yazeed/proc-cli/proc-cli), where it passes the security audits from Gen Agent Trust Hub, Socket and Snyk
    - Evals: [`evals.md`](https://github.com/yazeed/proc-cli/blob/main/skills/proc-cli/evals.md) lists the tasks the skill is checked against, each with what the agent must and must never do
    - Format: the [Agent Skills](https://agentskills.io) standard, so any agent that supports skills can use it
    
  • _config.yml 836 B
    Loading…

Comments (0)

Sign in to join the conversation.

No comments yet.

Reviews (0)

No reviews yet.