| name | task-decomposition |
| description | Turn a vague, oversized, or initiation-resistant outcome into an executable sequence with a visible first action and definition of done. Use when dependencies are hidden, the task spans multiple systems, or the user cannot identify where to begin. |
Task Decomposition
Decompose around execution boundaries, not arbitrary checklist length.
Procedure
- Define the observable outcome and the evidence that proves it.
- Identify hard constraints, dependencies, approvals, and irreversible steps.
- Split the work into independently verifiable units.
- Order units by dependency and feedback speed.
- Choose the smallest reversible first action that produces new information.
- Expose only Now, Next, and Later unless the full plan is requested.
- Re-plan from evidence when a unit fails; do not repeat the same attempt unchanged.
Executive-Skill Check
Use the task itself to find the support need. Check for:
- initiation: first action is unclear or emotionally expensive
- working memory: important state exists only in conversation
- sustained attention: unit is too long to yield feedback
- planning and priority: dependencies or value order are unclear
- time management: duration, checkpoint, or stop condition is absent
- flexibility: the plan has no failure route
- metacognition: done criteria cannot be observed
Modify the environment or task before assuming the user needs more effort.
Output Shape
Outcome: ...
Now: one concrete action
Next: one dependent action
Later: deferred work
Done when: executable evidence
Source Basis
Synthesized from Peg Dawson and Richard Guare's executive-skills taxonomy and intervention pattern: assess fit, modify the environment or task, teach the needed skill, externalize steps, review evidence, and fade scaffolding as it becomes unnecessary.
