agentsclimarketplace

Bootstrap

Skill ngocsangyem/MeowKit/.claude/skills/bootstrap

Use when creating a new project from scratch — orchestrates the full journey from idea to running code. Research → design → plan → scaffold → implement → docs. Explicit invocation only — never auto-activates. CLI = project infrastructure (.claude/), bootstrap = application code + full pipeline. NOT for autonomous multi-hour builds of specified products (see mk:autobuild); NOT for single-task feature work on existing projects (see mk:cook).From its SKILL.md

Install
npx -y skills add ngocsangyem/MeowKit --skill bootstrap

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 14 stars14 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.
  • runs commandsInstructs the agent to run 2 commands, including `scripts/detect-stack.sh` and 1 more.

SKILL.md

3.7 KB, 662 tokens by cl100k_base, as published. Nobody here has run it

Bootstrap

End-to-end project orchestrator: research → design → plan → scaffold → implement → docs.

CLI boundary: the installer = project infrastructure. mk:bootstrap = application code + full pipeline. Zero overlap. Never touch .claude/.

When to Use

Explicit only — never auto-activate.

mk:bootstrap [requirements]
mk:bootstrap [requirements] --full
mk:bootstrap [requirements] --fast
mk:bootstrap [requirements] --parallel

Do NOT invoke when: project already has source code, or you only need kit setup (use CLI).

Modes

ModeFlagGatesResearchDesignPlan flagCook flag
Auto(default)Design onlyParallel researchersUI/UX if frontend--auto--auto
Full--fullEvery stepParallel researchersUI/UX if frontend--hard(interactive)
Fast--fastNone6 parallel batchSkip--fast--auto
Parallel--parallelDesign onlyParallel researchersUI/UX if frontend--parallel--parallel

Routing

Parse first flag from arguments:

  • --full → load references/workflow-full.md
  • --fast → load references/workflow-fast.md
  • --parallel → load references/workflow-parallel.md
  • default → load references/workflow-auto.md

Each workflow file defines the exact steps for that mode. After plan + scaffold, all modes load references/shared-phases.md for implementation → docs → final report.

Planning BEFORE Scaffolding

Plan first, scaffold second. The plan tells us WHAT to scaffold.

  1. Plan — invoke mk:plan-creator with mode-matched flag. Plan defines: architecture, modules, file structure, acceptance criteria.
  2. Scaffold — generate files following the plan's architecture + references/scaffolding-principles.md. Detect stack via scripts/detect-stack.sh. Validate with scripts/validate-bootstrap.sh.

Optional: invoke mk:plan-ceo-review on the plan (Full mode).

Planning is NOT optional. Every bootstrap creates a plan before generating any source files.

Gotchas (top 3)

  • Scaffolding before planning: generating files without a plan → plan first, scaffold second
  • Skipping research on "simple" projects: hidden complexity → always research unless --fast
  • Duplicating CLI init: never generate .claude/ files — CLI handles that

Full list: references/gotchas.md

Workflow Integration

Pre-workflow. Bootstrap IS the full workflow for new projects:

mk:bootstrap → [research → design → plan → scaffold → cook → docs] → done

For subsequent features on the same project: use mk:plan-creator → mk:cook directly.

What ships with it: 10 files

25.5 KB alongside SKILL.md, 2 of them executable

scripts/

Keep looking

Skills are one crate of 325,949. 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.