https://github.com/nevaberry/nevaberry-plugins
Plugins and Knowledge Patches for AI - filling gaps in Claude's knowledge about language and framework features released after training cutoff
https://github.com/nevaberry/nevaberry-plugins
ai-tools claude-code claude-code-plugins developer-tools developer-tools-ai-agent knowledge-base knowledge-patch plugins
Last synced: about 21 hours ago
JSON representation
Plugins and Knowledge Patches for AI - filling gaps in Claude's knowledge about language and framework features released after training cutoff
- Host: GitHub
- URL: https://github.com/nevaberry/nevaberry-plugins
- Owner: Nevaberry
- License: mit
- Created: 2026-01-22T14:04:37.000Z (5 months ago)
- Default Branch: master
- Last Pushed: 2026-04-06T13:57:49.000Z (3 months ago)
- Last Synced: 2026-04-06T15:40:23.580Z (3 months ago)
- Topics: ai-tools, claude-code, claude-code-plugins, developer-tools, developer-tools-ai-agent, knowledge-base, knowledge-patch, plugins
- Language: Shell
- Homepage: https://nevaberry.com/ai-plugins
- Size: 875 KB
- Stars: 14
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Nevaberry Plugins
Plugins and knowledge patches for coding agents. Knowledge patches fill gaps left by model training cutoffs.
## Install
Install the meta-plugin to auto-detect your project's stack and install matching patches:
```
/install-plugin nevaberry-plugins/knowledge-patch
```
Or:
```sh
npx skills add https://github.com/nevaberry/nevaberry-plugins --skill knowledge-patch
```
Then run `/knowledge-patch-setup` to scan your project (package.json, Cargo.toml, go.mod, etc.) and install matching patches automatically.
### Manual install
Install individual patches directly — useful before rewriting to a new technology:
```
/install-plugin nevaberry-plugins/rust-knowledge-patch
/install-plugin nevaberry-plugins/dioxus-knowledge-patch
```
Or:
```sh
npx skills add https://github.com/nevaberry/nevaberry-plugins --skill dioxus-knowledge-patch
```
## How it works
AI models have training cutoffs. After that, APIs change, functions get deprecated, and new features ship. Knowledge patches contain only what changed: curated, verified diffs against baseline model knowledge.
When loaded, the patch is checked **before** writing code for that technology. This helps prevent outdated APIs, deprecated patterns, and broken implementations.
## Coverage
**Languages & runtimes:** Bun, Deno, Elixir, Gleam, Go, Kotlin, Node.js, Python, Rust, Swift, TypeScript, Zig
**Frontend & app frameworks:** Angular, Astro, Dioxus, Flutter, Leptos, Next.js, Nuxt, React, React Router, SolidJS, Svelte, Tauri, Vite, Vue
**Backend & server frameworks:** Axum, Django, FastAPI, Hono, Rails, Spring Boot, tRPC
**Data & persistence:** Drizzle, pgvector, PostGIS, PostgreSQL, Prisma, SQLite, SQLx
**Auth & identity:** Auth.js, Better Auth, Clerk, Supabase, WorkOS, ZITADEL
**AI, cloud & APIs:** AWS SDK, GCP, LangChain, PyTorch, Stripe, Vercel AI SDK
**Tooling & infrastructure:** Biome, Caddy, Docker, Kubernetes, Nginx, Playwright, Podman, Tailwind CSS, Terraform, Tokio, Traefik, Vitest
**Linux distros:** AlmaLinux, Arch, CentOS Stream, Debian, Fedora, openSUSE/SLES, RHEL, Rocky, Ubuntu