[Assistant Rules - You MUST follow these instructions]
[Available Skills]
The following skills are available. When you need detailed instructions for a specific skill,
you can request it by outputting: [LOAD_SKILL: skill-name]
- aionui-skills: Access the AionUI Skills registry — discover and download AI agent skills. Use when you need to find a reusable skill for a task or manage your agent credentials on the AionUI Skills platform.
- cron: Scheduled task management - create, query, update scheduled tasks to automatically execute operations at specified times.
- officecli: Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
- skill-creator: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
[Skills Location]
Skills are stored in three locations:
- Builtin skills (auto-enabled): /home/ubuntu/.config/AionUi/config/builtin-skills/_builtin/{skill-name}/SKILL.md
- Bundled skills: /home/ubuntu/.config/AionUi/config/builtin-skills/{skill-name}/SKILL.md
- User custom skills: /home/ubuntu/.config/AionUi/config/skills/{skill-name}/SKILL.md
Each skill has a SKILL.md file containing detailed instructions.
To use a skill, read its SKILL.md file when needed.
For example:
- Builtin "cron" skill: /home/ubuntu/.config/AionUi/config/builtin-skills/_builtin/cron/SKILL.md
- Bundled "pptx" skill: /home/ubuntu/.config/AionUi/config/builtin-skills/pptx/SKILL.md
[User Request]
can you develop a skill where in in case we need to start and stop and restart aionui as service on vps - i just tell you and you are able to do it - i am accessing it via url . pls check latest changes on vps about this service
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Let me first check what's already running on the VPS related to AionUI, then I'll create the skill.
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Good — AionUI is running as a systemd service. Let me read the service file and check how it's configured.
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Now I have the full picture. Let me create the skill and save the details to memory.
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Now let me update memory with the AionUI service details so future sessions have instant context.
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Memory is nearly full — let me combine the Claude API entry with the new AionUI info to make room.
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Done. Here's what I set up:
---
### ✅ Skill created: `aionui-vps-service`
Stored at `~/.hermes/skills/devops/aionui-vps-service/SKILL.md`.
It covers all the operations you asked for:
| Command | What it does |
|---------|-------------|
| `start aionui` | Starts the service |
| `stop aionui` | Stops it cleanly (frees ~8 GB RAM) |
| `restart aionui` | Graceful restart |
| `status` | Shows running/stopped state |
| `logs` | Last 50 lines from journal |
### What I found on the VPS
AionUI is **already running** as a systemd service (`aionui.service`):
- **Status**: Active since 2:42 PM today (just restarted)
- **Binary**: `/opt/AionUi/AionUi` **v1.9.20** (updated May 2 at 2:19 PM — looks like you updated it today)
- **Memory**: ~8.2 GB (normal for a loaded Electron app with Claude agents)
- **Auto-start**: Enabled on boot
- **Virtual display**: Uses `xvfb-run` on display `:99`
The latest change I can see is the `/opt/AionUi/` directory was modified today at 14:19 — so it was updated about 30 minutes before the current session started.
---
Now whenever you say something like *"restart AionUI"* or *"stop the AionUI service"*, I'll load this skill and handle it with the right `systemctl` commands. Want me to do anything with the service right now?
2026-05-02T15:12:15
USER (hermes, deepseek-v4-pro)
[Assistant Rules - You MUST follow these instructions]
[Available Skills]
The following skills are available. When you need detailed instructions for a specific skill,
you can request it by outputting: [LOAD_SKILL: skill-name]
- aionui-skills: Access the AionUI Skills registry — discover and download AI agent skills. Use when you need to find a reusable skill for a task or manage your agent credentials on the AionUI Skills platform.
- cron: Scheduled task management - create, query, update scheduled tasks to automatically execute operations at specified times.
- officecli: Create, analyze, proofread, and modify Office documents (.docx, .xlsx, .pptx) using the officecli CLI tool. Use when the user wants to create, inspect, check formatting, find issues, add charts, or modify Office documents.
- skill-creator: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
[Skills Location]
Skills are stored in three locations:
- Builtin skills (auto-enabled): /home/ubuntu/.config/AionUi/config/builtin-skills/_builtin/{skill-name}/SKILL.md
- Bundled skills: /home/ubuntu/.config/AionUi/config/builtin-skills/{skill-name}/SKILL.md
- User custom skills: /home/ubuntu/.config/AionUi/config/skills/{skill-name}/SKILL.md
Each skill has a SKILL.md file containing detailed instructions.
To use a skill, read its SKILL.md file when needed.
For example:
- Builtin "cron" skill: /home/ubuntu/.config/AionUi/config/builtin-skills/_builtin/cron/SKILL.md
- Bundled "pptx" skill: /home/ubuntu/.config/AionUi/config/builtin-skills/pptx/SKILL.md
[User Request]
can i use the natural language with you
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Yes, absolutely — that's the whole point of the skill I just created. You can talk to me naturally:
| You say | I do |
|---------|------|
| *"restart AionUI"* | `sudo systemctl restart aionui` |
| *"stop AionUI"* / *"shut it down"* | `sudo systemctl stop aionui` |
| *"start AionUI"* / *"bring it back up"* | `sudo systemctl start aionui` |
| *"is AionUI running?"* / *"status?"* | `sudo systemctl status aionui` |
| *"show me AionUI logs"* | `sudo journalctl -u aionui -n 50` |
You don't need to remember any `systemctl` commands, service names, or flags. Just tell me what you want in plain English and I'll handle the rest.
This applies to everything else too — trading bots, the Claude API wrapper, file operations, etc. Natural language is how you're meant to interact here.
2026-05-02T15:12:15
USER (hermes, deepseek-v4-pro)
but we have one challenge - although i can access you from my mobile too bec it is url based - but what happens to the commands yes allow etc
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Great question — this is about **command approval prompts** when you're on mobile and can't easily type `/approve` or `/yolo`.
Let me check your current approval config:
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Here's the situation:
**Your current setting:** `approvals.mode: manual` with a 60-second timeout. When Hermes wants to run a command flagged as risky (like `rm`, `systemctl stop`, etc.), it pops up an approval prompt and waits 60 seconds. If you don't respond, it gets **denied**.
This is indeed a problem on mobile — you'd need to type `/approve` or `/yolo` and there's no easy button for it.
---
### Three options to fix this:
| Mode | Behavior | Safety | Best for |
|------|----------|--------|----------|
| **`smart`** ✅ | AI auto-approves low-risk commands, only prompts on high-risk | Medium | **Mobile — recommended** |
| **`off`** (yolo) | Never asks, everything auto-runs | Low | Full trust, unattended bots |
| **`manual`** (current) | Always asks, 60s timeout | High | Desktop CLI only |
---
**I'd recommend `smart`** — it uses a small auxiliary model to judge risk. Commands like `systemctl restart aionui` or `git status` auto-approve. Only genuinely destructive things (`rm -rf /`, `DROP TABLE`) still ask.
Want me to switch you to `smart` mode? Just say yes and I'll do it — one command, no code changes.
2026-05-02T15:12:15
USER (hermes, deepseek-v4-pro)
lets work without it during markets and then check
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Makes total sense — during market hours you can't be baby-sitting approval prompts on mobile. Let me switch you to **`smart` mode** now. It'll auto-approve routine operations (service restarts, bot commands, file edits) and only stop for truly catastrophic things.
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Done. One note — this change takes effect on your **next session** (`/reset` or reconnect). Your current session is still in `manual`.
Here's what `smart` does for you:
| Example command | Smart mode | Manual mode |
|----------------|-----------|-------------|
| `systemctl restart aionui` | ✅ Auto-approved | ❌ Prompts |
| `git status` | ✅ Auto-approved | ❌ Prompts |
| `python bot.py` | ✅ Auto-approved | ❌ Prompts |
| `rm -rf /home/ubuntu/bots/` | ⚠️ Still prompts | ❌ Prompts |
| `sudo rm -rf /` | ⛔ Still prompts | ❌ Prompts |
After market hours today, we can review the session logs if you want to see what auto-executed. Want me to `/reset` now so it activates, or wait for your next message?
2026-05-02T15:12:15
USER (hermes, deepseek-v4-pro)
can we not have commands for allow allow for this session yes no etc
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
Yep — we can toggle it right now for this session. Let me enable it:
2026-05-02T15:12:15
ASSISTANT (hermes, deepseek-v4-pro)
You're right — for **this current session**, the `manual` mode is baked in from when it started. There's no `/yolo` available mid-session through AionUI.
But the fix is one click away: **reconnect / refresh AionUI** and you'll get a fresh session with `smart` mode active. No more approve/deny prompts for routine commands.
I've already saved the `smart` config permanently, so every session from now on will use it — including market hours, mobile, anytime.
Want me to confirm the config stuck before you reconnect?