
Agent Zero Profiles
Creates Agent Zero profiles with agent config, prompt overrides, tools, and extensions.
Install
npx skills add agent0ai/agent-zero --skill a0-create-agent -g -a claude-code -y- Repository
- agent0ai/agent-zero19.6k
- Category
- AI and agents
- Updated
- 3d ago
- License
- See repository
- Context cost
- Mediumabout 3,000 tokens
- Runs scripts
- No, instructions only
What it does
Create Agent Zero profiles with agent.yaml, prompt overrides, tools and extensions.
Create an Agent Zero Agent Profile
[!IMPORTANT] Do not create new profiles in
/a0/agents/, that directory is reserved for core framework profiles (default,agent0,developer,hacker,researcher,_example). User profiles belong in/a0/usr/agents/<profile_name>/.
Related skills: /a0/skills/a0-development/SKILL.md (broader framework guide) | /a0/skills/a0-create-plugin/SKILL.md (bundle a profile inside a plugin).
Primary references:
/a0/agents/_example/, the canonical reference profile (tool + extension + prompt overrides)/a0/agents/default/, the base profile every other profile inherits from/a0/plugins/AGENTS.md, plugin-distributed profiles + per-profile config
Existing Profile Pattern
The built-in profiles are intentionally split into two layers:
agent.yamlis tiny metadata for discovery and delegation:titledescriptioncontext
- The actual profile behavior usually lives in
prompts/agent.system.main.specifics.md.
Use the shipped profiles as calibration:
| Profile | Pattern to copy |
|---|---|
agent0 | Minimal top-level assistant identity |
developer | Rich capabilities, methodology, output requirements |
researcher | Rich capabilities, methodology, evidence standards |
hacker | Short, direct operational identity plus optional environment override |
_example | Minimal demo of prompt/tool/extension override surfaces |
For most new profiles, create agent.yaml plus one strong agent.system.main.specifics.md. Add other prompt overrides, tools, or extensions only when the blueprint explicitly needs them.
Step 0: Progressive Intake
Do not ask the user a long form. New users are easily overwhelmed. Guide them with lossy compression: ask only the next highest-value question, one or two questions per turn maximum.
Default assumptions unless the user says otherwise:

