Patch your AI model with pgvector updates from 0.7 to 0.8.2, enabling development of advanced vector search applications in PostgreSQL using halfvec, sparsevec, bit indexing, binary quantization, iterative index scans, subvector extraction, and L1 distance.
npx claudepluginhub nevaberry/nevaberry-plugins --plugin pgvector-knowledge-patchPlugins and knowledge patches for coding agents. Knowledge patches fill gaps left by model training cutoffs.
Install the meta-plugin to auto-detect your project's stack and install matching patches:
/install-plugin nevaberry-plugins/knowledge-patch
Or:
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.
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:
npx skills add https://github.com/nevaberry/nevaberry-plugins --skill dioxus-knowledge-patch
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 This helps prevent outdated APIs, deprecated patterns, and broken implementations.
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
Battle-tested Claude Code plugin for engineering teams — 38 agents, 156 skills, 72 legacy command shims, production-ready hooks, and selective install workflows evolved through continuous real-world use
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
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.
Automates browser interactions for web testing, form filling, screenshots, and data extraction
20 modular skills for idiomatic Go — each under 225 lines, backed by 48 reference files, 8 automation scripts (all with --json, --limit, --force), and 4 asset templates. Covers error handling, naming, testing, concurrency, interfaces, generics, documentation, logging, performance, and more. Activates automatically with progressive disclosure and conditional cross-references.
Create new skills, improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, or benchmark skill performance with variance analysis.