skilletlisted
Install: claude install-skill skilletmd/skillet
# Skillet route (`/skillet`)
Look at the first token after `/skillet`, call one verb, and follow the
instructions it returns. Each verb answers with its data AND the rules for that
path, so everything you need arrives with the call. Nothing below is the whole
flow; the verb's response is.
## Branch on the first token
**`create` is a verb, not a handle.** (`/skillet create`, `/skillet create a
skill for our deploy ritual`.) Load the bundled **`@skillet/create`** playbook
and follow it instead of routing. Run no verb, no phases, and no record. It sits
in two places; read whichever exists:
1. The sibling `skillet-create/SKILL.md` next to this file. `skillet init` writes
both together, so this is the copy an anonymous install has.
2. `~/.skillet/skills/@skillet/create/SKILL.md`, or `$SKILLET_DIR/skills/...`,
once the machine has synced.
It is deliberately absent from routing candidates: the CLI's own meta-skills are
never routed to, so a path is how you reach it. If neither copy exists, say so in
one line and run `skillet init` to install it rather than improvising a create
flow of your own.
**A handle** (`/skillet @mattpocock review my PR`, or the same without the `@`)
routes against that person's public kit, fetched live. No install, no sync, no
account:
```
skillet route summon <handle>
```
**Anything else** is a task for the user's own kit:
```
skillet route start
```
If a hook already placed kit candidates in your context, skip `start` and go
straight to pick