check-workspace

# Skill: check-workspace Read the local `workspace.toml` and surface the current queue state across all active initiatives. Run this at every session start — it replaces reading multiple product docs by hand. ## When to invoke Any time you need to orient: which initiative is active, what specs are ready to start, what is blocked and why, what signals the strategist has flagged. Also the right skill if workspace.toml does not yet exist and you want to initialise it. ## Procedure ### 1. Read workspace.toml Open `workspace.toml` from the repo root. Parse it as TOML (`tomllib.loads()` in Python 3.11+ / `tomli.loads()` backport for earlier). **If absent:** offer to initialise — ask the user whether to create a blank file or bootstrap with their first initiative. A blank file contains only the one-line comment: ```toml # workspace.toml — add ["<initiative-slug>"] sections to declare initiatives ``` **If present and unparseable:** surface the TOML parse error and stop — do not proceed with partial data. ### 2. Resolve the DAG For each initiative's `[work]` and `[shaping_queue]`: - A queue entry is **ready** when all its `needs` entries are satisfied (see below). - A queue entry is **blocked** when one or more `needs` entries are not yet satisfied. - An entry with no `needs` field is unconditionally ready (unless already in `active` or `shipped`). **Needs resolution:** `needs` is a string or list of strings using queue-prefix notation: | Prefix | Resolves against | |--...