Author: Haider Lasani

An AI skill packages reusable expertise for a task. An AI coding workflow for teams controls how a feature moves through planning, specification, development, review, checks, documentation, and delivery.

AI slop in software development is low-quality, error-prone output that is cheap to mass-produce. It is best treated as a workflow symptom.

AI coding productivity is conditional, not one number. Field experiments report more completed tasks, a bounded Copilot experiment reported faster completion, and METR observed experienced maintainers taking longer on familiar-repository tasks.

Almost right AI code creates a lifecycle cost that starts after generation. Price discovery, reproduction, context recovery, correction, retesting, rereview, and documentation as one verification workload.

AI can increase pull request arrival without increasing safe delivery. Use a queue model to expose review capacity, work in progress, and risk.

A realistic large-repo failure: the AI edits plausible files, review looks busy, and the relevant module is discovered too late.