yogsoth-ai Tactic: Task Decomposition
Orchestration Pattern
FUNCTION task_decomposition(experiment_design):
// Phase 1: Enumerate
activities = SPAWN activity-listing(experiment_design)
VALIDATE activities.count > 0
// Phase 2: Sequence
sequenced = SPAWN dependency-sequencing(activities)
VALIDATE no_circular_dependencies(sequenced)
// Phase 3: Estimate
estimated = SPAWN duration-estimation(sequenced)
VALIDATE all_tasks_have_estimates(estimated)
// Phase 4: Format
plan = SPAWN plan-formatting(estimated)
VALIDATE no_placeholders(plan)
VALIDATE all_paths_absolute(plan)
RETURN plan
END
Decision Criteria
| Condition | Action |
|---|---|
| Activity list is empty | ABORT — experiment design is incomplete |
| Circular dependency detected | Return to dependency-sequencing with conflict details |
| Duration estimate has high variance (σ > tM) | Flag as risky, add extra buffer |
| Plan contains TBD/TODO | REJECT — return to plan-formatting |
| Task count > 50 | Consider grouping into phases |
| Task count < 3 | Verify decomposition isn't too coarse |
Error Recovery
- If activity-listing fails: check experiment design completeness, escalate to Campaign 3
- If dependency-sequencing finds cycles: present cycle to user, ask for resolution
- If duration-estimation lacks data: use conservative estimates (pessimistic × 1.5)
- If plan-formatting produces placeholders: iterate with specific missing information
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| activity-listing | Enumerate all implementation activities from an experiment design |
| dependency-sequencing | Determine task dependencies and execution order |
| duration-estimation | Three-point PERT estimation for implementation activities |
| plan-formatting | Format task plan as bite-sized executable tasks following superpowers:writing-plans conventions |