https://github.com/janmarkuslanger/skills
Claude Code skills for software engineering.
https://github.com/janmarkuslanger/skills
claude-code claude-skills
Last synced: about 1 month ago
JSON representation
Claude Code skills for software engineering.
- Host: GitHub
- URL: https://github.com/janmarkuslanger/skills
- Owner: janmarkuslanger
- License: mit
- Created: 2026-04-26T07:31:45.000Z (about 2 months ago)
- Default Branch: main
- Last Pushed: 2026-05-05T19:11:06.000Z (about 2 months ago)
- Last Synced: 2026-05-05T21:14:00.552Z (about 2 months ago)
- Topics: claude-code, claude-skills
- Homepage:
- Size: 50.8 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# 🧠 janmarkuslanger/skills
Custom skills for [Claude Code](https://claude.ai/code) — reusable instruction units that extend Claude's behavior for specific tasks.
Each skill lives in its own directory with a `SKILL.md` file containing the instructions and metadata Claude uses to determine when and how to apply it.
---
## 📦 Installation
### 1. Register the marketplace
```
/plugin marketplace add janmarkuslanger/skills
```
Registers this collection under the marketplace name `janmarkuslanger-skills`.
### 2. Install the plugin
```
/plugin install janmarkuslanger-skills
```
### 3. Use a skill
```
/create-architecture-docs
```
Replace `create-architecture-docs` with any skill name from the list below.
> **Note:** Requires Claude Code 2.1.119 or later. Update with `npm update -g @anthropic-ai/claude-code`.
---
## 🗂️ Available Skills
| 🔧 Skill | 📝 Description |
|----------|----------------|
| [create-architecture-docs](./skills/create-architecture-docs) | Analyzes the project and generates `ARCHITECTURE.md` covering structure, components, data flow, tech stack, and design decisions |
| [agent-handoff](./skills/agent-handoff) | Writes current agent state to `HANDOFF.md` — completed work, changed files, open tasks, and next steps — for seamless agent handover |
| [create-agents-md](./skills/create-agents-md) | Analyzes the project and generates `AGENTS.md` — architecture, clean code rules, testing strategy, coupling, and conventions — so AI agents have clear guardrails |
### Engineering Cycle
| 🔧 Skill | 📝 Description |
|----------|----------------|
| [architecture-proposal](./skills/architecture-proposal) | Generates `SYSTEM_DESIGN.md` upfront — bounded contexts, layer strategy, architectural patterns, and quality attributes |
| [design-proposal](./skills/design-proposal) | Generates `DESIGN.md` for a feature before implementation — components, interface contracts, coupling decisions, and test approach |
| [adr](./skills/adr) | Creates an Architecture Decision Record at `docs/adr/NNNN-title.md` — context, alternatives considered, and consequences |
| [coupling-review](./skills/coupling-review) | Generates `COUPLING_REVIEW.md` — maps all dependencies, distinguishes intentional from accidental coupling, and flags issues with file-level evidence |
| [testability-review](./skills/testability-review) | Generates `TESTABILITY_REVIEW.md` — identifies hidden dependencies, missing seams, and untestable constructs with concrete fix recommendations |
| [architecture-review](./skills/architecture-review) | Generates `ARCHITECTURE_REVIEW.md` — evaluates code across six dimensions: SRP, dependency direction, layer separation, interface quality, coupling, and testability |
| [diff-commit](./skills/diff-commit) | Validates the current git diff for common issues (debug code, secrets, conflict markers, build artifacts) and generates a Conventional Commits title |
---
## 🏗️ Repository Structure
```
skills/
├── .claude-plugin/
│ └── marketplace.json # Marketplace configuration
├── skills/
│ ├── architecture-proposal/ # Upfront system architecture
│ ├── design-proposal/ # Feature-level design before coding
│ ├── adr/ # Architecture Decision Records
│ ├── coupling-review/ # Coupling quality analysis
│ ├── testability-review/ # Testability analysis
│ ├── architecture-review/ # Full architecture review
│ ├── create-architecture-docs/
│ ├── create-agents-md/
│ ├── diff-commit/
│ └── agent-handoff/
└── README.md
```
---
## 📖 How Skills Work
Claude Code loads each installed skill's `SKILL.md` at startup. The frontmatter (name, description) determines automatic activation; the body contains the instructions Claude executes.
Skills may include supporting files: `references/` for detailed documentation, `scripts/` for executable code.
---
## 🤝 References
- [Claude Code Docs — Skills](https://docs.anthropic.com/en/docs/claude-code/skills)
- [Agent Skills Standard](https://agentskills.io)
- [anthropics/skills](https://github.com/anthropics/skills) — Official skills by Anthropic