By j5ik2o
Software design skills for DDD, clean architecture, error handling, package design, refactoring, and maintainable domain modeling.
Use when designing or reviewing domain-model accessors that expose internal state for persistence, serialization, tests, or framework integration. Applies the breachEncapsulationOf naming pattern so unavoidable getters are visibly treated as encapsulation breaches, not casual domain APIs. Trigger for getter naming conventions, persistence-only getters, serialization accessors, Tell Don't Ask pressure, or requests to prevent getter misuse.
Use only when the user explicitly asks for Clean Architecture design, implementation, or review. Applies a domain, use case, interface adapter, and infrastructure layer model, with persistence and RPC adapters outside the domain and use-case rules. Do not trigger for generic architecture advice, hexagonal architecture, onion architecture, or ordinary design review unless Clean Architecture is named.
Use when CQRS changes aggregate boundaries or state shape. Helps reduce oversized command aggregates by moving read concerns to read models, keeping only command-decision state in aggregates, and using events for state transitions. Trigger for large aggregates, heavy command updates, aggregates containing query-only data, or boundary redesign during CQRS adoption.
Use when explaining why CQRS often needs event sourcing or durable events for reliable command-to-query synchronization. Covers calculated value sync, database trigger limits, polling scalability, double commits, and making events the source of truth. Trigger for CQRS synchronization, read-model update strategy, CQRS without ES, or double-commit concerns.
Use when evaluating whether CQRS is worth adopting, especially tradeoffs among consistency, availability, scalability, operational complexity, and event sourcing. Trigger for read/write separation decisions, eventual consistency concerns, CQRS architecture review, or choosing between a unified model and CQRS.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A marketplace repository for distributing AI agent skills and plugins for Claude Code and Codex.
.claude-plugin/marketplace.json.agents/plugins/marketplace.jsonmarketplace.yml and generated marketplace.jsonagent-skills, takt, and software-designskills/, .agents/skills/, and .claude/skills/ links for tools that consume plain skill directories directly/plugin marketplace add j5ik2o/ai-tools
/plugin install git@ai-tools
/plugin install github@ai-tools
/plugin install agent-skills@ai-tools
/plugin install takt@ai-tools
/plugin install software-design@ai-tools
Register this repository as a Codex plugin marketplace, then install the plugins you need:
codex plugin marketplace add j5ik2o/ai-tools --ref main
codex plugin add git@ai-tools
codex plugin add github@ai-tools
codex plugin add agent-skills@ai-tools
codex plugin add takt@ai-tools
codex plugin add software-design@ai-tools
Verify the installation, then start a new Codex task so the installed plugins are loaded:
codex plugin list
apm marketplace add j5ik2o/ai-tools --name ai-tools
apm install software-design@ai-tools
Available APM package names are git, github, agent-skills, takt, and software-design.
GitHub CLI provides gh skill for installing agent skills from GitHub repositories. See the gh skill manual for the current preview behavior.
Install a specific skill from this repository:
gh skill install j5ik2o/ai-tools j5ik2o-deep-research-read-me --agent codex --scope user --pin main
Install every skill exposed through the standard skills/ directory:
gh skill install j5ik2o/ai-tools --all --agent codex --scope user --pin main
The skills/ directory is the default discovery entry point. Mirrored links are also kept under .agents/skills/ and .claude/skills/; pass --allow-hidden-dirs only when you intentionally want gh skill to include hidden skill directories during discovery.
npx skills add j5ik2o/ai-tools
| Plugin | Description | Key skills | Details |
|---|---|---|---|
git | Git workflow skills, including staging and committing working-tree changes following Conventional Commits | j5ik2o-git-commit | plugin.json |
github | GitHub workflow skills, including systematic issue triage and GitHub OSS README creation, improvement, and review | j5ik2o-gh-issue-organizer, j5ik2o-deep-research-read-me | plugin.json |
agent-skills | Agent skills demonstrating skill creation, evaluation, and iterative improvement workflows | j5ik2o-skill-forge | README |
takt | TAKT workflow engine skills for multi-agent orchestration, analysis, building, and optimization | j5ik2o-takt-task-builder, j5ik2o-takt-workflow-builder, j5ik2o-takt-facet-builder, j5ik2o-takt-analyzer, j5ik2o-takt-optimizer, j5ik2o-takt-skill-updater | README |
software-design | Software design skills for DDD, clean architecture, error handling, package design, refactoring, and maintainable domain modeling | j5ik2o-ddd-aggregate-design, j5ik2o-clean-architecture, j5ik2o-error-handling, j5ik2o-package-design, j5ik2o-refactoring-packages | plugin.json |
.claude-plugin/
└── marketplace.json
marketplace.yml
marketplace.json
mise.toml
plugins/
├── git/
│ └── skills/
│ └── j5ik2o-git-commit/
├── github/
│ └── skills/
│ ├── j5ik2o-deep-research-read-me/
│ └── j5ik2o-gh-issue-organizer/
├── agent-skills/
│ ├── README.md
│ └── skills/
│ └── j5ik2o-skill-forge/
├── takt/
│ ├── README.md
│ └── skills/
│ ├── j5ik2o-takt-analyzer/
│ ├── j5ik2o-takt-facet-builder/
│ ├── j5ik2o-takt-optimizer/
│ ├── j5ik2o-takt-skill-updater/
│ └── j5ik2o-takt-task-builder/
└── software-design/
└── skills/
├── j5ik2o-clean-architecture/
├── j5ik2o-ddd-aggregate-design/
├── j5ik2o-error-handling/
└── ...
npx claudepluginhub j5ik2o/ai-tools --plugin software-designGitHub workflow skills, including systematic issue triage and GitHub OSS README creation, improvement, and review.
TAKT workflow engine skills for multi-agent orchestration. Includes analyzers, builders, and optimizers for TAKT workflow YAML.
Collection of agent skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling
Git workflow skills, including staging and committing working-tree changes following Conventional Commits.
GitHub workflow skills, including systematic issue triage and GitHub OSS README creation, improvement, and review.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
Utharn Buranasaksee's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
No description provided.
Senior craftsman methodology for AI-assisted development. DDD, Clean Architecture, TDD, and systematic workflows that transform Claude into a disciplined software engineer.
Comprehensive skills library for Claude Code: planning, design, TDD, debugging, collaboration patterns, and proven techniques