core-engine
/core-engine
Manage core engine lifecycle via core/bin/tool-cli commands for engine-restart and engine-reload. Only use this skill when the user explicitly asks to restart or reload the engine; never trigger it automatically from another agent skill.
- Author
- x-school-academy ↗
- Repository
- skill-pilot ↗
- Licence
- MIT
- Last repository change
- 07.06.2026
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 07.06.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Manage core engine lifecycle via core/bin/tool-cli commands for engine-restart and engine-reload. Only use this skill when the user explicitly asks to restart or reload the engine; never trigger it automatically from another agent skill.
Original author description
Manage core engine lifecycle via core/bin/tool-cli commands for engine-restart and engine-reload. Only use this skill when the user explicitly asks to restart or reload the engine; never trigger it automatically from another agent skill.
How it works
- When to Use This Skill
- Your Roles in This Skill
- Role Communication
- Instructions
- Expected Output
- Key Principles
SKILL.md preview
---
name: core-engine
description: Manage core engine lifecycle via core/bin/tool-cli commands for engine-restart and engine-reload. Only use this skill when the user explicitly asks to restart or reload the engine; never trigger it automatically from another agent skill.
---
# AI Builder - Core Engine
Control core engine restart/reload through socket-driven commands.
## When to Use This Skill
- User explicitly asks to restart core engine
- User explicitly asks to reload updated `config/.env` and apply changes
- User explicitly asks to control engine lifecycle from CLI without manual tmux interaction
Do not use this skill automatically from another agent skill or as an inferred follow-up action. If engine control seems helpful but the user did not ask for it, ask first instead of invoking this skill.
## Your Roles in This Skill
- **Backend Developer (Engineer)**: Execute engine control commands safely
- **SysOps Engineer**: Validate lifecycle intent and runtime impact
- **Technical Writer**: Report action, signal path, and expected result
## Role Communication
As an expert in your assigned roles, you must announce your actions before performing them using the following format:
As a {Role, and Role-XYZ if have more roles}, I will {action description}
This communication pattern ensures transparency and allows for human-in-the-loop oversight at key decision points.
## Instructions
Follow these steps in order:
### Step 1: Choose operation
Map user intent:
1. `engine-restart`: restart engine process from in-memory environment only to reload config json/json5 files if user has updated these file manually
2. `engine-reload`: read latest `.env` and config into memory, then restart engine process if user has updated `.env` manually
### Step 2: Execute command
From repo root:
```bash
core/bin/tool-cli engine-restart
```
```bash
core/bin/tool-cli engine-reload
```
### Step 3: Report expected behavior
- `engine-restart`: does not re-read `.env`
- `engine-reload`: re-reads `.env` first, then restarts
- Works for dev-server (`--reload`) and direct `main.py` execution
### Step 4: Confirm result
Return command output and note that active sessions may reconnect during restart.
## Expected Output
- A successful engine restart/reload request acknowledged by tool-cli
- Clear summary of whether `.env` was re-read
## Key Principles
- Use signal-based control via engine socket, not manual process killing
- Keep restart and reload semantics explicit
- Prefer `engine-reload` after key changes in `config/.env` manually
Versions
The database has no other skills named core-engine.
Database snapshot: 13.11.2026 · package version c374a083af4c (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 95engine-manage
Manage the Kurtosis engine server. Start, stop, restart the engine, check status, and view engine logs. Covers both Docker and Kubernetes engine backends. Use when the engine won't start, needs restarting, or you need to check engine health. - 100daemon
Manage the Telegram daemon lifecycle — start, stop, restart, check status, tail logs. Use when the user says "start the bot", "stop the daemon", "restart telegram", "daemon status", "show bot logs", or "is the bot running". - 95b2c-sandbox
Create and manage on-demand sandboxes (ODS) for B2C Commerce using the b2c CLI. Use this skill whenever the user needs to spin up a new development sandbox, list running sandboxes, start/stop/restart an instance, or manage sandbox lifecycle — even if they just say "I need a… - 100restart-and-reload-semantics
Know what the server caches and what needs a restart, so stale data never masquerades as a bug. Use when packs or skills change on disk while a client session is running - 100daemon-ops
Operational commands for the AgentX daemon on the current host — restart, tail logs, hot-reload config, status, Claude-auth and overage-gate troubleshooting. Works on both macOS (launchd) and Linux (systemd). Intended for the devops / main agent on the host. Other agents should not use this. - 95localstack
Manage the LocalStack emulator lifecycle with the lstk CLI. Use when users need to start, stop, restart, reset, or check status of LocalStack, configure LocalStack environment variables, or troubleshoot LocalStack container issues.