AI Agent Dynamic Workflows

Use this skill to turn a large task into a supervised AI-agent workflow: draft an orchestration artifact, enter goal mode when sustained execution is requested, delegate disjoint work to subagents when available, integrate results, verify the outcome, and save reusable workflow artifacts.

This skill works in agents that support skills. Do not claim that a local script can call subagent tools unless the current environment exposes such a runner. When no programmable runner exists, create a human-readable orchestration script and operate it through the available agent tools.

Decision Rule

Use this skill when the user requests dynamic orchestration. Task complexity, risk, or parallel tracks alone do not activate it. Within an authorized workflow, choose only delegation that contributes a concrete independent result.

Operating Contract

When using this skill:

1. Restate the goal and success criteria.
2. Create or update a workflow artifact before delegating.
3. Check authorization for consequential actions against the boundaries below; do not ask again for an action already authorized within scope.
4. Create a goal only when explicitly requested by the user or system/developer instructions; ordinary multi-turn work does not authorize goal creation.
5. Split work into disjoint packets with clear ownership.
6. Spawn subagents only when the current environment allows it and the user has authorized delegated or parallel agent work.
7. If no subagent runner is available, perform independent passes locally and label them as parent work, not subagent results.
8. Integrate results explicitly; do not paste raw subagent dumps as the final answer.
9. Verify with checks matched to the task's blast radius.
10. Save reusable artifacts only when they will help future work.

Workflow Artifacts

Prefer creating a local run directory: