GitHub collection

kuya-egg/monozukuri

Imported from GitHub — is this yours?

13 skills imported from this repository.

View on GitHub
11 1 MIT
Claude Skill

andon

Make software health, failure, degradation, and recovery visible through useful observability and diagnostics. Use when adding logs, metrics, traces, health checks, alerts, incident signals, or operational feedback.

LLM Mart

Claude Skill

genchi-genbutsu

Inspect the real repository, environment, dependencies, and runtime evidence before designing or changing software. Use for greenfield construction, unfamiliar codebases, uncertain behavior, or any task where assumptions could create rework.

LLM Mart

Claude Skill

hansei

Reflect on failures, incidents, reviews, and completed software work to turn evidence into durable tests, guardrails, documentation, and process improvements.

LLM Mart

Claude Skill

jidoka

Debug software by making failures visible, reproducing them, finding contributing causes, and adding durable regression protection. Use for bugs, failing tests, incidents, regressions, flaky behavior, and unexplained production errors.

LLM Mart

Claude Skill

kaizen

Improve software continuously through small, safe, behavior-preserving changes that reduce maintenance cost. Use for refactoring, cleanup, technical debt, naming, duplication, dead code, or post-change polish.

LLM Mart

Claude Skill

kanso

Choose simple, maintainable software designs by removing speculative complexity, comparing alternatives, and making explicit tradeoffs. Use for architecture, API, data-model, dependency, and scope decisions.

LLM Mart

Claude Skill

kata

Implement software through small, repeatable, integrated vertical slices with clear exit criteria and honest verification. Use when a design is understood and code needs to be built or changed.

LLM Mart

Claude Skill

kodawari

Review software with careful attention to correctness, maintainability, security, operations, and meaningful detail. Use for diffs, branches, pull requests, architecture decisions, or final quality checks.

LLM Mart

Claude Skill

monozukuri-blueprint

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.

LLM Mart

Claude Skill

monozukuri-router

Step 0 of consequential software work under Monozukuri. Classify the task, assess its risk tier, choose execute or sensei mode, and compose the sequence of Monozukuri skills and the Definition of Done for it. Skip for trivial one-line edits, pure questions, and throwaway scripts.

LLM Mart

Claude Skill

nemawashi

Clarify software goals, constraints, stakeholders, and risks before consequential design or implementation work. Use for greenfield ideas, ambiguous requirements, architecture decisions, or changes where misunderstanding would be costly.

LLM Mart

Claude Skill

poka-yoke

Prevent software mistakes through strong boundaries, safe defaults, meaningful tests, and mechanically enforced invariants. Use for TDD, validation, schemas, authorization, edge cases, regression coverage, or reliability-sensitive behavior.

LLM Mart

Claude Skill

shukka

Prepare software for responsible release, migration, deployment, rollback, and handoff with evidence about compatibility, health, ownership, and recovery.

LLM Mart