Waffle setup
🧇 One batter, every repo — reusable AI agent & skill definitions rendered into harness-native files (.claude/, .codex/, .agents/)
npx -y skills add dustinkeeton/wafflestack --skill waffle-setupAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Print the wafflestack setup playbook and full stack/skill/agent inventory for this repo, then help pick stacks and config. Use to plan an install or audit what the toolkit offers.
SKILL.md
1.7 KB, 367 tokens by cl100k_base, as published. Nobody here has run it
Setup playbook + inventory
Wraps wafflestack setup — it prints the agent-driven install playbook (schema/SETUP.md)
followed by a generated inventory of every stack: its items, config schema (required vs.
defaulted keys), env prerequisites, opt-in syrup items, and any setup: notes. It reads
current config when one exists, adding a "Current configuration — update mode" section
(live targets/stacks/includes/ejects/effective config/unset required keys/opt-in syrup state),
so a re-run curates an update pass.
Run it
npx --yes github:dustinkeeton/wafflestack setup
Interpret it for the user
Do not just dump the output — read it and help the user decide:
- Recommend a starting selection. From the inventory, name the stacks that fit this repo
and the required config keys each would demand. Flag any opt-in syrup items (sensitive
files/payloads, marked "do NOT install by default") and explain what enabling one implies. - Point at the next command. Turning the plan into files is
/waffle-install <ref…>(persists the choice, then renders) — or, on a repo with no config yet,/waffle-initfirst./waffle-renderre-renders an existing selection. - Surface prerequisites. If a stack lists
env:or asetup:block (e.g.gh auth, labels, a Projects v2 board, secrets), call those out before rendering — the render will warn on missing env, but service-side setup is on the user.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.