Waffle init

Skill dustinkeeton/wafflestack/.claude/skills/waffle-init

🧇 One batter, every repo — reusable AI agent & skill definitions rendered into harness-native files (.claude/, .codex/, .agents/)

Install

npx -y skills add dustinkeeton/wafflestack --skill waffle-init

Assembled 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

Scaffold a starter `.waffle/waffle.yaml` so wafflestack can render into this repo. Use in a repo that has never run wafflestack, before picking stacks and running /waffle-render.

SKILL.md

1.7 KB, 380 tokens by cl100k_base, as published. Nobody here has run it

Initialize wafflestack in this repo

Wraps wafflestack init — it writes a starter .waffle/waffle.yaml (a scaffold of targets: / stacks: / include: / config: / eject:) so this repo can be rendered. It errors if a config already exists at any generation, so it is safe to run only once.

Run it

npx --yes github:dustinkeeton/wafflestack init

Pass --gitignore through if $ARGUMENTS asks for it — that also appends .waffle/waffle.local.yaml to .gitignore (nothing else is knowable yet, since no stack is chosen):

npx --yes github:dustinkeeton/wafflestack init --gitignore

After it runs

Report the file it wrote (.waffle/waffle.yaml).
Explain the next two steps and offer to do them:
- Pick stacks + config. Edit .waffle/waffle.yaml — set targets: (usually [claude]), list stacks: (run /waffle-setup to see the full inventory and each stack's required config), and fill config: values. /waffle-install <ref…> can do the stack/config edit and render in one step.
- Render. Run /waffle-render (or /waffle-install) to generate the harness files.
If the command reported that a config already exists, do not overwrite it — point the user at the existing .waffle/waffle.yaml and suggest /waffle-setup (update mode) instead.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most project setup skills give in 380 tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-07

Ask one question at a timein 29 of 999, across 28 files
Detect the package manager from lockfilesin 28 of 999, across 9 files
Present findings to the userin 26 of 999, across 5 files
Explore current repo statein 24 of 999, across 3 files
Update the agent skills block in place if it existsin 24 of 999, across 3 files
Install husky lint-staged and prettierin 23 of 999, across 4 files
Create the lintstagedrc filein 22 of 999, across 3 files
Commit all changed filesin 22 of 999, across 3 files
Run lint-staged to verify it worksin 22 of 999, across 3 files
Create the husky pre-commit filein 21 of 999, across 2 files
Create a prettierrc file if missingin 21 of 999, across 2 files
Initialize huskyin 21 of 999, across 2 files

Said here and by no other author read

Pass the gitignore flag if requested
Explain the next two steps
Offer to perform the next steps
Direct the user to edit the configuration file
Direct the user to run the render command

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.