dag-pattern-learner

This skill monitors iteration progress by tracking quality trends and detecting plateaus to recommend optimal stopping points. Use it when you need to determine when further iterations won't improve task outcomes. It pairs with other DAG skills like the iteration detector and feedback synthesizer for comprehensive workflow monitoring.

This skill executes scheduled DAG workflows in parallel waves using the Task tool, managing concurrent agent spawning within set resource limits. It coordinates task execution and agent handoffs for workflow runs when triggered by commands like 'execute dag' or 'run workflow'. Use this specifically for parallel execution, not for building DAGs or scheduling them.

This skill validates DAG structures, detects cycles, and resolves dependency ordering using Kahn's algorithm for topological sorting. Use it when you need to compute an optimal execution sequence or verify a graph is acyclic after construction. It pairs with dag-graph-builder for validation and dag-task-scheduler for execution planning.

This skill traces complete execution paths in DAG workflows, recording node timing, inputs, outputs, and state transitions for debugging. Use it for execution tracing, path analysis, and logging when you need to understand workflow flow. It is specifically for execution path tracing, not for performance profiling or failure investigation.