Menu
Breaking complex user goals into subtasks that agents can handle.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Proactively identifying failure modes, misuse, and unintended consequences.
Managing shared context, memory, and state across multiple agents.
Coordinating text, image, voice, and tool-use modalities in a single interaction.
Helping users form warranted trust in the AI — neither overtrust nor undertrust — through deliberate confidence and source signalling.
Reading user emotional state from text signals — caps, punctuation density, repetition, latency — and adapting before the user disengages.
Designing review workflows to surface and mitigate bias in AI outputs.
| name | task-decomposition |
| description | Breaking complex user goals into subtasks that agents can handle. |
Users come with goals, not subtasks. Task decomposition is how a multi-agent system breaks a complex user goal into pieces that individual agents can handle — and then reassembles the results into something coherent.
For each type of user goal the system handles:
How finely to decompose matters:
User goals are often ambiguous. The system needs to:
