By elct9620
Guides large-scale feature implementation and codebase maintenance by applying systematic software design (DDD, Clean Architecture, GoF patterns), safe refactoring, test-driven development, security threat modeling, and a spec-to-implementation roadmap tracker.
Fix bugs by diagnosing root cause, reproducing with tests, and applying minimal fixes.
Clean up legacy code issues by identifying code smells and applying safe refactoring techniques.
The `<execute name="main">ARGUMENTS</execute>` is entry point for this command.
The `<execute name="main">ARGUMENTS</execute>` is entry point for this command.
Implement features based on the agent skills.
Plan how a system is structured — which layers, modules, or contexts exist and how code is laid out — driven by the forces at play, not by a fixed pattern. The default is to add no extra structure; structure is introduced only when complexity calls for it, and the chosen shape (Clean Architecture, DDD, DCI, or another) is judged in the moment. Use this skill when following a recorded structure in docs/architecture.md, or when deciding the structural shape for a non-trivial feature, a new module, or a restructuring — especially after a design-forces memo recommends a layered or partitioned structure.
Surface design forces and lay out the option space — including framework defaults, scaffolds, and deferring — before committing to Clean Architecture, DDD, or any heavier pattern. Produces a Design Analysis Memo at the start of /write, /refactor, or non-trivial /fix. Make sure to use this skill whenever the user starts a non-trivial feature, restructures code, or asks "do we really need Clean Architecture / DDD / pattern X here".
Select and apply GoF design patterns: Factory, Builder, Strategy, Observer, Adapter, Decorator. Use when solving recurring design problems or structuring multi-component changes. Make sure to use this skill whenever the user needs to decouple components, wrap legacy APIs, handle multiple algorithm variants, build complex objects step by step, or asks which pattern fits their situation.
Model business domains using DDD patterns: Entity, Value Object, Aggregate, Domain Event. Use when implementing business logic, defining domain concepts, or designing aggregate boundaries. Make sure to use this skill whenever the user works on business rules, creates domain objects, discusses bounded contexts, models workflows or processes, or asks about entity vs value object distinctions — even for simple CRUD features that involve domain invariants.
Apply SOLID, KISS, DRY, YAGNI principles to code design decisions. Use when building new features from scratch and need to decide on class structure, interface boundaries, or dependency direction. Make sure to use this skill when the user faces design trade-offs, asks about SOLID principles, debates whether to abstract or keep things simple, or needs to evaluate competing design approaches — but not for code smell detection (use refactoring skill instead).
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.
This is personalized agent skills for coding tasks. Mainly designed to Claude Code but fit for other LLMs as well.
Each team or individual has their own coding style, preferences, and best practices. In my opinion, each one or team should have their own coding skills to better fit their needs.
I use Ruby, TypeScript/JavaScript, and Golang the most. And love Clean Architecture, Domain-Driven Design, and Test-Driven Development. This skill set is build around these preferences.
| Type | Selection |
|---|---|
| Architecture | Clean Architecture |
| Design | Domain-Driven Design |
| Workflow | Test-Driven Development |
| Principles | SOLID, KISS, DRY |
| Coding | Design Patterns |
| Coding | Refactoring |
| Coding | Security |
This repository is designed as Claude Code Plugin which contains following components:
|- /coding-skills
|- commands/ # Workflow commands (entry points)
|- write.md # Implement new features with TDD
|- fix.md # Diagnose and fix bugs
|- refactor.md # Clean up legacy code
|- review.md # Post-implementation quality checks
|- roadmap.md # Spec-to-implementation tracking
|- skills/ # Individual skills with specific knowledge
|- design-forces/
|- testing/
|- architecture/
|- domain-modeling/
|- design-patterns/
|- refactoring/
|- principles/
|- schema/
|- security/
The command as entry which defines the workflow, then adaptively select necessary skills to complete the task.
For example, the /write command uses architecture to follow a structure already recorded in docs/architecture.md, or — when the design forces call for it — to decide a structural shape (Clean Architecture, DDD, DCI, or another). It defaults to adding no extra structure when the forces are quiet.
Choose the appropriate command based on your task:
| Command | Purpose | Arguments |
|---|---|---|
/write | Implement features | feature|id [--skip-tests] |
/refactor | Clean up code | [path|module] |
/fix | Fix bugs | bug|issue|error |
/review | Review changes | [path|module|--staged] |
/roadmap | Track implementation | [init|update|status] [feature] |
| Skill | /write | /refactor | /fix | /review |
|---|---|---|---|---|
| coding:design-forces | ✓† | ✓† | ✓‡ | ✓§ |
| coding:testing | ✓ | ✓ | ✓* | ✓* |
| coding:refactoring | ✓ | ✓* | ✓ | ✓ |
| coding:architecture | ✓ | ✓ | ✓ | ✓ |
| coding:principles | ✓ | ✓ | ✓ | ✓* |
| coding:design-patterns | ✓ | ✓ | ✓ | ✓ |
| coding:domain-modeling | ✓ | - | ✓ | - |
| coding:schema | ✓ | ✓ | ✓ | ✓ |
| coding:security | ✓ | ✓ | ✓ | ✓ |
*Core skill for this command (always activated)
†Runs before active-skills selection to frame the direction
‡Runs only when the bug crosses layers or involves a design decision
§Used to check changes against patterns recorded in docs/architecture.md
/roadmapis a standalone tracking command and does not use coding skills.
/write: Starting a new feature or adding new functionality/refactor: Improving code quality without changing behavior/fix: Diagnosing and fixing bugs with test verification/review: Reviewing recent changes for style consistency, test quality, and architecture alignment after /write or /fix/roadmap: Tracking spec-to-implementation progress, initializing a roadmap from specs, or checking feature status/write or /fix → /review → /refactor (if needed)
After implementing features (/write) or fixing bugs (/fix), run /review to check quality. If the review report contains findings, use /refactor to address them.
Use /roadmap init to create a tracking index from your SPEC.md, then /roadmap status to check progress as you implement.
To use this coding skills, install from the marketplace or use claude plugin add in Claude Code. Then choose the command which most fits the task.
Apache-2.0 License. See LICENSE for details.
npx claudepluginhub elct9620/claudekit --plugin codingCommands to create and manage GitHub Actions workflows.
Enhanced /loop with structured Plan → Execute → Review → Sample phases for stable long-running tasks
A plugin for maintaining project specifications
Provides helpful Ruby extensions for varios scenarios.
Provides Hono CLI skill to make agent know how to use Hono framework.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Access thousands of AI prompts and skills directly in your AI coding assistant. Search prompts, discover skills, save your own, and improve prompts with AI.
Complete developer toolkit for Claude Code
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Orchestrate multi-agent teams for parallel code review, hypothesis-driven debugging, and coordinated feature development using Claude Code's Agent Teams