Monorepo init

Skill dkotama/skills/skills/monorepo-init

Curated Agents skills handcrafted by I Nyoman Darma Kotama.

Install

npx -y skills add dkotama/skills --skill monorepo-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

0 stars0 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

Bootstrap a new project with full scaffold — CLAUDE.md, DECISIONS.md, .memory/, docs/, PRD.md, Hello World per platform with tests. Run once at project creation. Idempotent — safe to re-run. Activates on: "init this monorepo", "set up project structure", "bootstrap project", "create CLAUDE.md and memory", "init project scaffold".

SKILL.md

2.7 KB, 629 tokens by cl100k_base, as published. Nobody here has run it

Monorepo Init

Bootstraps a new project in 3 phases: Plan → Review → Generate.

Minimal interview (3 questions max). Smart defaults inferred from stack. User reviews full plan before any file is written.

Core Rules — Never Break

Self-contained — never invoke superpowers:brainstorming, superpowers:writing-plans, or any other skill. This skill owns its entire flow.
Minimal questions — ask only: project name, platforms, stack per platform. Infer everything else.
Review before write — always show the full scaffold plan and get user approval before generating any file.
Platform isolation — each platform is fully independent: own deps, own tooling, own scripts. Sharing is opt-in.
Hello World required — every platform ends with Hello World running, unit tests ≥ 80% coverage, e2e framework with ≥ 1 passing test.
Idempotent — skip .memory/000 silently if exists; prompt before overwriting CLAUDE.md, PRD.md, TASK.md.
Canonical names — enforce web not fe, api not backend, cms not strapi.

Definition of Done

For each platform:

Check	Requirement
Hello World runs	dev/start command exits 0
Unit tests pass	test runner exits 0
Coverage ≥ 80%	reported by test runner
E2E configured	≥ 1 e2e test passes

3-Phase Flow

Phase 1 — Plan
  AskUserQuestion: name + platforms (1 call)
  AskUserQuestion: stack per platform (1 call each)
  Infer all defaults → show summary
  Multi-turn: user corrects defaults via free text
  Loop until user says "looks good" / "proceed" / "go"

Phase 2 — Review
  Print full scaffold plan (files, stacks, tools, defaults)
  Wait for explicit approval: "go" / "generate" / "yes"
  "Change X" → back to Phase 1

Phase 3 — Generate
  Write all files
  Scaffold Hello World + tests per platform
  Run tests, verify ≥ 80% coverage
  Output commit command

Companion Files

Need	File
Phase 1 questions + inference table + Phase 2 review format	`skills/monorepo-init/recipes/interview.md`
Phase 3 generation steps	`skills/monorepo-init/recipes/execution.md`
File templates (CLAUDE.md, PRD.md, DECISIONS.md, TASK.md, SPEC, memory, docs)	`skills/monorepo-init/config/templates.md`
Hello World code + unit test + e2e per stack	`skills/monorepo-init/recipes/hello-world.md`

Gives 0 of the 12 instructions most project setup skills give in 629 tokens

Counted across 999 of the 1,637 authors here whose files we hold, read 2026-08-06

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 25 of 999, across 4 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
initialize huskyin 21 of 999, across 2 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

Said here and by no other author read

Ask only for project name, platforms, and stack
Infer all other defaults from stack
Make each platform fully independent
Enforce canonical platform names
Scaffold Hello World with tests per platform
Verify unit test coverage is at least eighty percent

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.