A suite of architectural-decision skills for Claude Code: decide-architecture (software architecture stack), design-patterns (GoF + Python-idiomatic patterns), and agentic-patterns (LLM-agent control-flow design). Each skill branches on project status — greenfield runs a short selection interview and recommends a composed design; refactoring reviews existing code against the catalog and proposes targeted moves.
Use when designing or assessing an LLM-agent system — 'how should I build this agent', 'do I need multiple agents or one', 'should this be a workflow or an agent', 'how do I add memory/tools/human approval', 'is my ReAct loop / multi-agent setup right', or any agent-architecture code review. Branches automatically: greenfield → a layered design interview (autonomy → reasoning loop → topology → memory → reliability → governance → integration); existing agent code → a review against the catalog's seven recurring defects. Pushes toward the least autonomy that works. Reach for this whenever agents, tools, multi-agent, RAG-agents, orchestration, or LLM control flow come up, even if no pattern is named.
Use when choosing or assessing software architecture — picking a structure/topology for a new system, or reviewing whether an existing codebase's architecture fits. Triggers on questions like 'how should I structure this service', 'should this be microservices or a monolith', 'is our layering right', 'we're adding events/CQRS/a queue — does it fit', or any greenfield architecture decision or architecture-focused code review. Branches automatically: greenfield → a short selection interview that composes a stack; existing code → a review against the pattern catalog with targeted moves. Reach for this even when the user hasn't named a specific pattern.
Use when choosing or assessing object-level design patterns (GoF and Python-idiomatic) — 'which pattern fits here', 'how should I structure this class', 'is this the right use of a factory/strategy/observer', 'how do I make these algorithms swappable', or any design-pattern code review. Branches automatically: greenfield → a short interview that returns one recommended pattern (with its Pythonic form); existing code → a review that maps smells to the patterns that fix them. Strongly prefers the language feature over the ceremony — reach for this whenever pattern/class-design questions come up, even if no pattern is named, and especially in Python.
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 suite of architectural-decision skills for Claude Code. Three skills help you choose an architecture for new work, or audit the architecture of code you already have — each branching automatically on whether you're greenfield or refactoring.
Validated across 20 real-world cases (both modes, real repositories): zero wrong recommendations, and it recommends doing less — no agent, no microservices, no pattern — as readily as doing more. Full docs → · Examples →
| Skill | Use it to… | Greenfield mode | Refactoring mode |
|---|---|---|---|
arch-crew:decide-architecture | Pick or assess software architecture (structure, topology, data, overlays) | Selection interview → composed stack | Review code → targeted moves |
arch-crew:design-patterns | Pick or assess GoF / Python-idiomatic design patterns | Which-pattern interview → one recommendation (+ Pythonic form) | Smell → pattern review |
arch-crew:agentic-patterns | Design or assess an LLM-agent system | Layered design interview (autonomy → … → integration) | Seven-defect agent review |
Each skill first works out where you are — greenfield (a new design) or refactoring (existing code) — then either runs a short selection interview or reviews your code against the catalog. The through-line in all three: recommend the least architecture that meets the requirement, and name the cost of every pick.
Add the marketplace and install the plugin:
/plugin marketplace add AdamKrysztopa/architectural-decisions
/plugin install arch-crew
Then invoke a skill directly (e.g. arch-crew:decide-architecture) or just describe an architecture
decision and the right skill triggers.
The decision logic and pattern catalogs are distilled from three single-file HTML references
(html/, kept locally as the source of truth, not shipped) into each skill's references/:
references/decision-tree.md — the selection interview / decision tree.references/catalog.md — the patterns with when-to-use, cost, and code-review cues.SKILL.md stays a lean workflow and reads those references on demand (progressive disclosure).
.claude-plugin/
plugin.json
marketplace.json
skills/
decide-architecture/ SKILL.md + references/{decision-tree,catalog}.md
design-patterns/ SKILL.md + references/{decision-tree,catalog}.md
agentic-patterns/ SKILL.md + references/{decision-tree,catalog}.md
MIT
npx claudepluginhub adamkrysztopa/architectural-decisions --plugin arch-crewA suite of recent data-science skills for Claude Code: ds-star & ds-star-plus (iterative plan→implement→execute→verify→route solving with a rubric-graded LLM-as-judge), ds-clarify (human-in-the-loop spec), ds-spike (multi-data-scientist ensemble with debate), ds-model (AIDE solution-tree + leaderboard), ds-conduct (data-aware orchestrator), ds-memory (cross-session memory), ds-verify/ds-reconcile/ds-vote/ds-search (standalone primitives), data-profile, and eda-narrative. Grounded in DS-STAR (Nam et al., 2025) and follow-on work.
UI/UX design intelligence. 67 styles, 161 palettes, 57 font pairings, 25 charts, 15 stacks (React, Next.js, Vue, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Nuxt, Jetpack Compose). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient.
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.
This skill should be used when users need to generate ideas, explore creative solutions, or systematically brainstorm approaches to problems. Use when users request help with ideation, content planning, product features, marketing campaigns, strategic planning, creative writing, or any task requiring structured idea generation. The skill provides 30+ research-validated prompt patterns across 14 categories with exact templates, success metrics, and domain-specific applications.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
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.
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.