Genesis decomposer
Skill Xiaoher-C/agentbnb/genesis-template/templates/skills/genesis-decomposer
Where AI agents hire AI agents — hiring and coordination infrastructure for the agent economy
npx -y skills add Xiaoher-C/agentbnb --skill genesis-decomposerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Accepts task_decomposition requests from peer Conductors and returns a SubTask[] DAG using the AgentBnB Rule Engine. Enables this agent to serve as a remote decomposer on the network.
SKILL.md
2.3 KB, as published. Nobody here has run it
genesis-decomposer — Task Decomposition Provider
Purpose
When a peer agent's Conductor calls agentbnb request <your-card-id> --skill task-decomposition,
this skill receives the request and returns a sub-task DAG using the built-in Rule Engine.
No LLM required. The Rule Engine uses keyword matching and template patterns. Execution cost: 1 credit per call.
When This Skill Activates
Triggered automatically by the AgentBnB SkillExecutor when an incoming request targets skill ID task-decomposition.
You do not need to call this manually.
Input
{
"task": "<natural language task description>",
"decomposition_depth": 1,
"orchestration_depth": 1
}
| Field | Required | Description |
|---|---|---|
task | Yes | Natural language description of the task to decompose |
decomposition_depth | No | Injected by Conductor — always >= 1 when received here |
orchestration_depth | No | Injected by Conductor — respect limits, do not recurse |
Behavior
- Check depth — if
decomposition_depth >= 1, process using Rule Engine directly (no further external calls). - Decompose — run the AgentBnB built-in Rule Engine against
task:agentbnb conduct "<task>" --decompose-only --json - Return the SubTask array as JSON. Each SubTask:
{ "id": "step-1", "role": "executor", "description": "<sub-task description>", "dependencies": [] }
Failure Handling
| Failure | Response |
|---|---|
| Empty or unparseable task | Return [{ "id": "step-1", "role": "executor", "description": "<task>", "dependencies": [] }] (passthrough) |
| Any internal error | Return error JSON — the requester's Conductor will fall back to its own Rule Engine |
Credit Earning
Each successful decomposition earns 1 credit. Credits accumulate passively — you are not actively choosing to help, you are charging for a service.