By bfh-krg1
Stack-agnostic methodology: vision, requirements, data model, feature specs, sprint, ship, deploy
Batch skill: implements, tests, and commits all Approved features in one run. No-arg = all docs/features/*.md with Status Approved. With args = specific FEAT IDs. Creates a branch per feature, implements, tests, auto-commits locally if green, marks Done. Never pushes automatically — offers /ship at the end. Use when the user says "run the sprint", "implement everything", "batch implement", or "process all features".
Reads or creates docs/architecture.md, which declares the tech stack for the project. All dispatcher skills (implement, test, e2e, deploy) read this file to know which stack plugin to invoke. Use when the user asks "what stack are we using", "set up architecture", "choose the stack", or when docs/architecture.md is absent.
FEAT-aware wrapper around the bundled /code-review skill. Maps review findings to FEAT-XXX IDs and prefixes each finding with the relevant feature. Use when the user asks for a "code review", "review my code", or "check the implementation".
Creates or updates docs/data_model.md with entity attribute tables and an optional Mermaid ER diagram. No PlantUML. Use when the user asks to "design the data model", "create the entity model", "define the database schema", "draw an ER diagram", or mentions entities, tables, relationships, or database design.
Dispatcher: reads docs/architecture.md and delegates to the correct stack docker skill to scaffold Dockerfiles and docker-compose.yml. Use when the user says "set up docker", "create docker compose", "scaffold deployment", or "deploy".
External network access
Connects to servers outside your machine
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.
Claude Code plugin marketplace for AI-assisted web app development. Lighter and more batch-friendly than the original AIUP: no UML, no ceremony, generates monorepos.
# 1. Install the marketplace
/plugin marketplace add ./sdd-web-app
/reload-plugins
# 2. In your project directory — start with the vision
/vision
# 3. Define requirements and architecture
/requirements
/architecture # writes FastAPI+Vue3 default if docs/architecture.md is absent
# 4. Design the data model and feature specs
/data-model
/feature-spec # generates all features from requirements at once
# 5. Implement + test everything in one go
/sprint
# 6. Ship
/ship
| Command | Output | Notes |
|---|---|---|
/vision | docs/vision.md | Socratic interview, one-time |
/requirements | docs/requirements.md | FR/NFR/Constraints tables |
/architecture | docs/architecture.md | Writes default if absent |
/data-model | docs/data_model.md | Mermaid ER + attribute tables |
/feature-spec [FR-001 ...] | docs/features/*.md | All FRs by default |
/implement [FEAT-001 ...] | code | All open features by default |
/migration | DB migration files | Alembic or Drizzle Kit |
/test [FEAT-001 ...] | test results | All features by default |
/e2e [FEAT-001 ...] | Playwright results | App must be running |
/sprint [FEAT-001 ...] | branches + commits | Full cycle: implement→test→commit |
/ship [FEAT-001] | push + PR | Always asks before pushing |
/deploy | docker-compose files | Docker only |
/init-secrets | .env | Generates from .env.example |
/code-review | findings | FEAT-aware wrapper |
/refactor | refactored code | Preserves ACs, re-runs tests |
/reverse-engineer | feature specs + data model | Reads existing code |
your-project/
├── backend/ # API + data layer
├── frontend/ # Vue3 + Vite SPA
├── docker-compose.yml
├── .env.example
└── docs/
├── vision.md
├── requirements.md
├── architecture.md
├── data_model.md
└── features/
Python 3.14 · FastAPI · SQLAlchemy 2.0 Mapped[] · Alembic · pgvector · Vue3 · Vite · Pinia · TailwindCSS · Docker
TypeScript · Node 22 · Fastify 5 · Drizzle ORM v1 · pgvector · Vue3 · Vite · Pinia · TailwindCSS · Docker
/plugin install pyright-lsp@claude-plugins-official # Python type-checking
/plugin install typescript-lsp@claude-plugins-official # TypeScript type-checking
/plugin install commit-commands@claude-plugins-official # git commit helpers
/plugin install security-guidance@claude-plugins-official
/plugin install pr-review-toolkit@claude-plugins-official
Also install gh (GitHub) or glab (GitLab) CLI and authenticate it — required for /ship PR creation.
typescript-lsp covers .ts files)npx claudepluginhub bfh-krg1/sdd-web-app --plugin coreFastAPI + SQLAlchemy 2.0 + Alembic + pgvector + Vue3 + Vite monorepo stack plugin
Fastify 5 + Drizzle ORM + pgvector + Vue3 + Vite monorepo stack plugin
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.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.