What is skill compilation?
Skill compilation is the step where a successful, LLM-planned run is distilled into a durable skill: an ordered set of actions bound to token-efficient DOM indices, minimized to drop the retries and dead ends, with the run-specific values lifted out into late-bound tokens. The expensive reasoning happens once during this cold compile; every later invocation replays the skill or matches it through the semantic cache.
Why it matters
Compilation is the moment cost moves from per-run to one-time. It separates the act of figuring out a workflow (model-heavy) from running it (model-free), which is exactly the boundary RPA-replacement and high-volume agent teams need to make per-1,000-run cost fall.