create-team-skilllisted

# Creating a new Team skill This is the dev-workspace guide for authoring a skill in this plugin. Follow it so a new skill matches the conventions the existing skills already use. A skill is a document the agent reads, not a function it calls. Before writing one, classify it — principle skill or not (Part 0) — then make three decisions in order. Each has a wrong-by-default failure mode, so decide deliberately rather than copying another skill's wiring. 1. **Invocation** — is this an entry point (user/model triggers it) or a building block (another skill composes it)? This defines what the skill *is*. 2. **Input** — how does it get the thing it operates on? Discover it. Do not demand it. 3. **Context** — how does it stay inside the window while it runs? Offload, delegate, search. ## Shared convention: the artifacts directory Every skill that hands off uses one durable, repo-local directory for what it would otherwise "keep in the conversation". That covers inputs passed between skills, checkpoints, and findings. In this repo that directory is **`docs/plans/<id>/`**, where `<id>` is `<TICKET>-<topic>` or `<YYYY-MM-DD>-<topic>`. This guide calls it `<ARTIFACTS>`. Producers write there. Consumers discover and read from there. The agreement matters more than the path: every handoff uses the same convention so skills stay decoupled. --- ## Part 0 — Principle skill or not Decide this before Part 1: the verdict fixes the name, the shape, and the frontmatter. A `princip