xiaohei-info/oh-my-multica

Production-grade software delivery for coding-agent teams on Multica — dynamic planning, deterministic execution, verifiable delivery.

This repository also configures its own agents. See what oh-my-multica tells them →

26Stars on the repository
46Mods indexed here, across every type
5d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

A method for creating or reviewing a detailed technical architecture diagram: a concrete description of how an approved system design will be built. It covers technical components, their connections, runtime collaboration, stability, operations, and security.

not rated 26 +2 5d ago A SkillSpector: pass 50 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

A method for creating or reviewing a system functional architecture diagram: a high-level picture of what the system does and how its capabilities are grouped. It focuses on user and business capabilities, not code, deployment, or step-by-step runtime behavior.

not rated 26 +2 5d ago A SkillSpector: pass 50 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Use when an architect must run the overview-design portion of technical design, preserve the full lifecycle-stage doctrine for shared technical-design entry and overview design, and define goals, alternatives, functional layering, system structure, risk, and overview-level design boundaries before detailed design…

not rated 26 +2 5d ago A SkillSpector: warn 63 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Grill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.

not rated 26 +2 5d ago A 44 tokens copy · 86% MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Use when architecture or backend work needs pre-code structural guidance from design patterns, or post-code cleanup guidance from refactoring and code-smell-driven improvement.

not rated 26 +2 5d ago A SkillSpector: pass 38 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Manage software complexity through deep modules, information hiding, and strategic programming. Use when the user mentions "module design", "API too complex", "shallow class", "complexity budget", "strategic vs tactical", "deep module", "information leakage", or "pass-through method". Also trigger when reviewing…

not rated 26 +2 5d ago A SkillSpector: pass 125 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Design scalable distributed systems using structured approaches for load balancing, caching, database scaling, and message queues. Use when the user mentions "system design", "scale this", "high availability", "rate limiter", "design a URL shortener", "system design interview", "capacity planning", or "distributed…

not rated 26 +2 5d ago A SkillSpector: pass 119 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

not rated 26 +2 5d ago A 40 tokens copy · 75% MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup.

not rated 26 +2 5d ago A 46 tokens copy · 98% MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.

not rated 26 +2 5d ago A 41 tokens copy · 97% MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.

not rated 26 +2 5d ago A 46 tokens copy · 84% MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

not rated 26 +2 5d ago A SkillSpector: pass 48 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Use when writing, reviewing, or refactoring code in any language to apply industrial-grade development norms abstracted from the Alibaba Java Development Handbook. Covers naming, type safety, exceptions, logging, concurrency, databases, project structure, testing, and security with language-agnostic principles and…

not rated 26 +2 5d ago A SkillSpector: pass 66 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Apply meta-principles of software craftsmanship: DRY, orthogonality, tracer bullets, and design by contract. Use when the user mentions "best practices", "pragmatic approach", "broken windows", "tracer bullet", "software craftsmanship", "technical debt prevention", "prototype vs tracer bullet", or "code ownership".…

not rated 26 +2 5d ago A SkillSpector: pass 129 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Top-level entry point for the software development skill family. Routes to the right sub-skill for design patterns, refactoring, DDD, worktree governance, kanban splitting, container supervision, project governance, runtime ops, and web routing.

not rated 26 +2 5d ago A SkillSpector: pass 52 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: