[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.
- vps-database: Interact with the central SQLite database (chat_archive.db) containing chronological conversation history and permanent operational milestones across all AI agents on this VPS (Antigravity, Claude, Deepseek). Use when the user asks to: (1) query past chat logs, conversations, or messages, (2) search or look up agent memories, resolutions, or facts, (3) record or update operational milestones, (4) inspect the database schema or sync status.
[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]
hi
2026-05-27 18:20:25
ASSISTANT (antigravity, gemini-3.5-flash)
Hello! I am Antigravity, your AI coding assistant. How can I help you with your coding tasks, project ideas, or questions today?
2026-05-27 18:20:31
USER (antigravity, gemini-3.5-flash)
which llm
2026-05-27 18:20:43
ASSISTANT (antigravity, gemini-3.5-flash)
I am Antigravity, an agentic AI coding assistant developed by the Google DeepMind team. Under the hood, I am powered by Google's Gemini models.
2026-05-27 18:20:48
USER (antigravity, gemini-3.5-flash)
which model
2026-05-27 18:20:59
ASSISTANT (antigravity, gemini-3.5-flash)
I am **Antigravity**, powered by **Gemini 3.5 Flash**, a large language model built by Google.
2026-05-27 18:21:04
USER (antigravity, gemini-3.5-flash)
do you wait for instructions or autonomously work
2026-05-27 18:21:24
ASSISTANT (antigravity, gemini-3.5-flash)
I operate as an interactive, human-in-the-loop agentic coding assistant. Here is how my workflow balances autonomous action with your control:
1. **Triggered by You**: I wait for your explicit instructions, requests, or questions before initiating any task.
2. **Autonomous Problem Solving**: Once you give me a task, I can autonomously explore the codebase, plan the implementation, draft files, write code, and even delegate complex sub-tasks to specialized background subagents.
3. **Safety and Approval**:
* **Terminal Commands**: I will propose bash commands to run, but they **will not execute** until you explicitly review and approve them in the terminal interface.
* **Implementation Plans**: For complex or architectural changes, I enter **Planning Mode**, where I draft a detailed implementation plan and wait for your approval before writing any code.
4. **Asynchronous Background Execution**: If a task or build takes time, I can run it in the background. The system will automatically wake me up once the task finishes or if I receive a status update, so you do not need to wait around or prompt me to keep checking.
You can also use slash commands like `/goal` to let me work autonomously on long-running objectives, `/schedule` for recurring tasks, or `/grill-me` to help us align on a design plan together.