a0 create agent

AI Community v1.0.0

Skill notes

Existing Profile Pattern

The built-in profiles are intentionally split into two layers: agent.yaml is tiny metadata for discovery and delegation: title description context

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: Scope: user profile in /a0/usr/agents/<name>. Models: inherit global/project _model_config. Response contract: keep the standard Agent Zero JSON tool-call contract.

Step 1: Create an AgentProfileBlueprint JSON

Before writing files, produce exactly one valid JSON object in a fenced json block using this schema. This blueprint is the source of truth. Do not require a utility model or prose post-processing to extract fields. Rules for the blueprint: Output strict JSON: no comments, no trailing commas, no markdown inside string values except the intended file content. profile.name must be lowercase letters, numbers, hyphens, or underscores only.

Step 2: Required Fields

The blueprint must contain these required profile inputs: Input · Rule · Example name (directory name) · lowercase letters, numbers, hyphens or underscores; must be unique across profile search paths · data-analyst title · human-readable display name shown in the UI · Data Analyst description · one-line specialization summary · Agent specialized in data analysis, visualization, and statistical modeling.

Step 3: Write Files from the Blueprint

After the user confirms the blueprint, create exactly the paths listed in files. agent.yaml: A profile with only agent.yaml is valid — it inherits everything from default/. Add the sections below only when you need to change something.

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
AI
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
98 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@agent0ai · v1.0.0 · no license declared
Token usage
Heavy
Setup complexity
Manual integration
External API key
Not required
Operating systems
Docker
Runtime requirements
Python · Docker
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
Network behavior
Local-only
Install commands
None (reference only)
Output preview a0-create-agent.preview
# Reference: Complete example profile layout

/a0/agents/_example/
├── agent.yaml
├── prompts/
│   ├── agent.system.main.specifics.md     # role override
│   └── agent.system.tool.example_tool.md  # tool usage prompt
├── tools/
│   ├── example_tool.py                    # new tool
│   └── response.py                        # redefines core response tool
└── extensions/
    └── agent_init/
        └── _10_example_extension.py       # init-time hook

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.