Durable CLI task management for long-running or interactive commands.
Install
mkdir -p .claude/skills/oly && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10080" && unzip -o skill.zip -d .claude/skills/oly && rm skill.zipInstalls to .claude/skills/oly
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Use when starting a long-running or interactive CLI command with oly, especially when it may need later input, should be detachable, or should keep durable logs for supervision and resume.Key capabilities
- →Start long-running CLI processes
- →Monitor session logs
- →Send interactive input
- →Update session metadata
- →Notify on task completion
How it works
Oly starts a process in a supervised session that persists across disconnects. It provides structured logging and allows sending input to interactive TUI or CLI prompts.
Inputs & outputs
When to use oly
- →Managing long-running background tasks
- →Supervising interactive sessions
- →Detaching CLI processes
About this skill
When to use
Use oly start instead of a direct terminal invocation when ANY of these apply:
- The command may prompt for input later.
- The session must survive terminal closes, disconnects, or agent handoff.
- Logs, replay, or auditability matter.
- Another human or agent may need to resume or inspect the work.
Do not use oly for short, non-interactive commands — a normal terminal is simpler.
Principles
- Supervisor mindset. Start the job, monitor it, intervene only when needed.
- Small tails first. Use
--tail 40; expand only when context is insufficient. - Fewer polls, longer waits. Set
--timeoutto match the expected next checkpoint — reduces churn and token cost. - Machine-readable listing. Use
oly ls --json --status runningfor scripting or structured decisions.
Workflow
1) Start
oly start --title "task 1" --cwd /path/to/dir --detach the_cmd --arg1 --arg2
| Flag | Purpose |
|---|---|
--detach | Return immediately with the session ID. |
--disable-notifications | Suppress notifications when you will supervise yourself. |
--node <name> | Run on a connected secondary node. |
2) Monitor
oly logs <ID> --tail 40 --no-truncate --wait-for-prompt --timeout 10s
--wait-for-prompt— blocks until the session likely needs input or timeout expires.--timeout— accepts250ms,10s,5m,1h(default5m). Shorten for fast tasks; lengthen for slow ones.- Start with
--tail 40; increase only when recent context is insufficient.
3) Send input
oly send <ID> "hello world!" key:enter
oly send <ID> oly-clipboard
oly send <ID> "cat " oly-file:/path/to/file key:enter
- Arguments are sent left-to-right. Plain text is literal; special keys use
key:prefix. - Keys:
key:enter,key:ctrl+c,key:alt+x,key:shift+tab,key:up,key:down. - Raw hex:
key:hex:.... Piped stdin is supported when no positional chunks are given. - Clipboard content uses
oly-clipboard. Local file upload usesoly-file:<path>. This is normally used for remote node sessions.
Input strategy:
| Scenario | Action |
|---|---|
| Menu / TUI selection | Navigate with key:up / key:down / key:enter. |
| Freeform text prompt | Send text + key:enter. |
| Stuck / needs interrupt | key:ctrl+c (or relevant control sequence like key:esc). |
4) Lifecycle
oly attach <ID> # Detach: Ctrl-], then d
oly update <ID> --title "better name"
oly update <ID> --title ""
oly update <ID> --tag prod --tag release
oly update <ID> --tag ""
oly stop <ID>
oly ls # oly ls --json for agents
oly updatechanges session metadata without restarting the session.--title ""clears the title. If--titleis omitted, the existing title is kept.--tag ""clears all tags. If--tagis omitted, existing tags are kept.- Repeating
--tagreplaces the full tag list with the provided tags.
5) Notify
oly notify <ID> --title "Done" --description "Summary." --body "Details."
<ID>is optional — include it to link the notification to a specific session.- Toggle per-session notifications:
oly notify enable <ID>/oly notify disable <ID>.
Help
oly --help # or: oly <command> --help
When not to use it
- →Short, non-interactive commands
Limitations
- →Requires manual supervision for complex interactive tasks
How it compares
Unlike a standard terminal, oly provides durable logging, session replay, and the ability for agents to resume or supervise tasks after a disconnect.
Compared to similar skills
oly side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| oly (this skill) | 0 | 3mo | Review | Intermediate |
| it-operations | 1 | 7mo | No flags | Advanced |
| pagerduty | 0 | 1mo | No flags | Beginner |
| home-assistant-manager | 9 | 8mo | Review | Advanced |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by slaveOftime
View all by slaveOftime →You might also like
it-operations
davila7
Manages IT infrastructure, monitoring, incident response, and service reliability. Provides frameworks for ITIL service management, observability strategies, automation, backup/recovery, capacity planning, and operational excellence practices.
pagerduty
fisker086
Query PagerDuty incidents, services, and on-call schedules
home-assistant-manager
komal-SkyNET
Expert-level Home Assistant configuration management with efficient deployment workflows (git and rapid scp iteration), remote CLI access via SSH and hass-cli, automation verification protocols, log analysis, reload vs restart optimization, and comprehensive Lovelace dashboard management for tablet-optimized UIs. Includes template patterns, card types, debugging strategies, and real-world examples.
email-systems
davila7
Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders. This skill covers transactional email that works, marketing automation that converts, deliverability that reaches inboxes, and the infrastructure decisions that scale. Use when: keywords, file_patterns, code_patterns.
infra-guardian
diegosouzapw
OpenClaw Agent Infrastructure Guardian — keep your agent's infrastructure alive. Process lifecycle management with detached execution, auto-restart on failure. Cron scheduler health monitoring (per-job detection, auto-recovery). Direct Telegram/messaging alerts independent of OpenClaw. System-level
setup
barefootford
Sets up a Mac for ButterCut. Installs all required dependencies (Homebrew, Ruby, Python, FFmpeg, WhisperX). Use when user says "install buttercut", "set up my mac", "get started", "first time setup", "install dependencies" or "check my installation".