agentsclimarketplace

Monorepo bootstrap

Skill prasadmogulothu/agent-skills/monorepo-bootstrap

Reusable, token-optimized agent skills for autonomous development with Hermes, Claude Code & OpenCode. Multi-model orchestration patterns — context-checkpointing, human review gates, RLS security, GDPR consent, AI cost control, and test-fix loops. Framework-agnostic, agentskills.io compatible.

Install
npx -y skills add prasadmogulothu/agent-skills --skill monorepo-bootstrap

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

Scaffold a Turborepo + pnpm monorepo with shared config, a testing harness, and CI in one pass. Use at the start of a new multi-package project. Adaptable to Nx / other tooling.

SKILL.md

1.3 KB, as published. Nobody here has run it

monorepo-bootstrap

Stand up a clean multi-package project foundation so shared code is built once and reused.

Do

  1. Scaffold a Turborepo + pnpm workspace with apps/ (deployables) and packages/ (shared code).
  2. Add a shared config package: TypeScript config, lint/format presets, and any UI/style preset.
  3. Set up a testing harness (unit + e2e + accessibility) with one passing sample test.
  4. Add CI (build + typecheck + lint + test on PR), build caching, and a pre-commit hook.
  5. Establish the rule: apps consume shared packages by workspace name — never copy/fork shared code into an app.

Adapting

The pattern holds for Nx, Lerna, or plain pnpm workspaces — what matters is: shared packages, one config source, a test harness, and CI gating every change. Swap the tool, keep the shape.

Done when

build, test, and lint pass across the empty workspace; CI is green on a trivial PR.

Token tactics

Mechanical — route to a cheap/mid model; verify once. Record the conventions you applied to MEMORY.md so later tasks don't re-explain the project.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.