Agent skill · vasilyu1983
foundations-theory-of-constraints
Theory of Constraints primitives for focusing steps, drum-buffer-rope, throughput accounting, critical chain, and policy constraints. Use when sequencing by bottleneck.
What it needs
About 11k tokens when loaded.
What this skill does
Theory of Constraints Foundations 11 canonical Theory of Constraints primitives for diagnosing and exploiting system constraints. Primitives are domain-agnostic: the same Five Focusing Steps that fix a production line apply to a software delivery pipeline, a product roadmap, or a consulting engagement. Each primitive solves a specific class of throughput-limiting problem. When to Apply Apply theory-of-constraints when: One bottleneck demonstrably gates total system throughput (the system has a constraint, not many) Roadmap or capacity-allocation under a hard limited resource (eng-weeks, GPU-hours, account-managers) Funnel debug where a single step blocks downstream conversion Policy constraint suspected (a rule, not a physical limit, is what's holding throughput) Subordination question — "should other steps slow down to match the bottleneck?" Post-AI adoption reassessment — when AI coding tools improve individual velocity but delivery metrics (lead time, deployment frequency, change failure rate) stay flat, re-run 5FS; the constraint has likely shifted downstream to code review, verification, or integration (DORA 2025, n≈5,000; corroborated by IT Revolution 2026 and Logilica 2025) LLM / agent-pipeline optimization — when end-to-end latency or task throughput of a multi-step AI pipeline is not meeting targets despite adding models or workers; the constraint is usually a specific stage (LLM decode, serialized tool execution, or a guardrail/eval step), not aggregate capacity — profile per stage before scaling Skip and use simpler alternatives when: System has multiple roughly equal bottlenecks — TOC's "elevate one" model misfires; use queueing networks (foundations-queueing-theory) Throughput question is really a feedback-control question (oscillation, instability) — use foundations-control-theory The "constraint" is actually a strategic choice (we want this to be the limit) — TOC is a diagnostic, not a strategy Bottleneck moves run-to-run (no stable system) — stabilis …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills vasilyu1983/foundations-theory-of-constraints