lab-itlisted

Investigates and validates how an existing system or capability actually works, from real implementation, tests, and current evidence — never conventions or guesses — producing a verified answer, an architecture decision reached with the user, or an approved `plan.md` handed to `plan-it`. Trigger to investigate or explain how a system works, resolve architecture or design decisions for a proposed feature, or synthesize approved findings into `plan.md`. Not for explaining one function, debugging, reviewing a diff, writing API reference docs, or creating, updating, or reviewing an architecture guide — route guide work to `document-it`.
elieandraos/agentic-engineering · ★ 0 · Code & Development · score 70

Install: claude install-skill elieandraos/agentic-engineering

# lab-it ## What this skill does This skill investigates a real system and turns the resulting understanding into one of the following: | User intention | Result | | -------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------- | | Understand how a system actually works | A verified answer — investigation and recap, no guide required | | Resolve a feature's architecture through conversation, no `plan.md` requested | A verified answer or resolved architecture discussion — no document produced | | Explicitly request `plan.md` synthesis | Approved `plan.md` handed to `plan-it`, via the existing synthesis and approval procedure | | Create, update, or review an architecture guide | Routed to `document-it` | Investigation comes first in every workflow — whether user confirmation follows, and when, is conditional; see "Shared investigation and decision discipline" below. Investigation and recap alone may be the complete result: no `plan.md` gets produced just because an investigation happened. ## Shared inve