Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Monozukuri Blueprint

ASecurity

Author a greenfield build blueprint in four gated stages — business logic, tech stack, logic-to-stack mapping, and a phase plan — each requiring explicit user approval before the next. Use when building a new project or a substantial new subsystem from scratch; run by monozukuri-core for greenfield tasks.

11 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add kuya-egg/Monozukuri --skill monozukuri-blueprint --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Monozukuri Blueprint?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Monozukuri Blueprint
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kuya-egg-monozukuri-blueprint/badge)](https://www.skillsdirectory.com/skills/kuya-egg-monozukuri-blueprint)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: monozukuri-blueprint
description: "Author a greenfield build blueprint in four gated stages — business logic, tech stack, logic-to-stack mapping, and a phase plan — each requiring explicit user approval before the next. Use when building a new project or a substantial new subsystem from scratch; run by monozukuri-core for greenfield tasks."
user-invocable: false
---

# Monozukuri blueprint

This skill turns a framed idea into four approved artifacts and an ordered
phase plan. It does no implementation — it sets direction and order so each
phase can then be built under its own playbook.

## Use this skill when

- building a new project from scratch;
- adding a substantial standalone subsystem;
- the router selected the `greenfield` playbook; or
- the user asks for a build plan or blueprint.

## Do not use when

- the work changes an existing flow — that is `feature`;
- the work is a one-off script; or
- the request is a pure question.

## Prerequisite

`nemawashi` has run, or its output already exists. Blueprint consumes the
framed intent, users, and constraints; it does not re-ask them.

## The gate

After producing each stage's artifact, stop. Present it, say what the next
stage will do, and wait for explicit approval. A later stage may send you
back to revise an earlier artifact; re-approve the changed artifact before
resuming. Never begin a stage while the previous one is unapproved.

See `monozukuri-core/references/blueprint.md` for the full gate protocol and
for what a strong artifact at each stage looks like.

## Stages

### Stage 1 — business logic

- produces: `.monozukuri/blueprint/01-business-logic.md`
- contains: domains, actors and roles, entities and their relationships,
  business rules, primary flows, state transitions, invariants, and notable
  edge cases — in plain language.
- refuses: any technology, framework, or datastore choice; naming a library.
- template: `monozukuri-core/references/templates/blueprint/business-logic.md`

### Stage 2 — tech stack

- produces: `.monozukuri/blueprint/02-tech-stack.md`
- contains: language and runtime, framework(s), datastore(s), infra and
  deploy target, and key libraries — each with a one-line "why this — over
  what", derived from a stage-1 need, `kanso` applied.
- refuses: a choice stage 1 does not justify; components added "for later".
- template: `monozukuri-core/references/templates/blueprint/tech-stack.md`

Significant choices — those whose later reversal would touch many modules or
the data model — also become ADRs under `.monozukuri/decisions/`.

### Stage 3 — logic to stack map

- produces: `.monozukuri/blueprint/03-logic-to-stack-map.md`
- contains: one row per stage-1 element (actor, domain, entity, rule, flow,
  state) mapped to exactly one home in the stack; orphans and unused
  components listed explicitly.
- refuses: leaving any stage-1 element unmapped.
- template: `monozukuri-core/references/templates/blueprint/logic-to-stack-map.md`

### Stage 4 — phase plan

- produces: `.monozukuri/blueprint/04-phase-plan.md`
- contains: ordered phases, each with `intent` (one line), `affected`
  (areas or files), `prereqs` (earlier phase ids and named external
  dependencies, or "none"), `playbook`, and `risk`. Phase 1 is a vertical
  slice through real boundaries; later phases run smallest first within
  prereq order (`monozukuri-core/references/checkpoints.md`).
- refuses: step-by-step task lists; a phase whose prereqs are not satisfiable
  by earlier phases.
- template: `monozukuri-core/references/templates/blueprint/phase-plan.md`

## Outcome

Four approved artifacts in `.monozukuri/blueprint/`, and a phase plan whose
phases each name a `playbook` (`feature | refactor | migration | release`)
and a `risk` tier (`low | medium | high | critical`).

## Handoff

After stage 4 approval, start phase 1. Its `playbook` and `risk` are already
set, so the router's classify step is already answered: go straight to that
playbook, render its Definition of Done from `definition-of-done.md` for the
stated risk tier, and execute. The detailed task list for the phase comes
from `spec-driven-implementation` / `writing-plans` at that point, not from
blueprint. Re-run `monozukuri-router` only if a phase proves misclassified.

If a referenced skill is not installed, apply its named lens inline instead
of trying to invoke it.

Attribution

kuya-eggkuya-egg
View sourceMore from kuya-egg →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →