By kolodgeeva
Shared engineering skills: React, Next.js, Fastify, backend/frontend architecture, testing, and security.
Guides development of Fastify Node.js backend servers and REST APIs using TypeScript or JavaScript. Use when building, configuring, or debugging a Fastify application — including defining routes, implementing plugins, setting up JSON Schema validation, handling errors, optimising performance, managing authentication, configuring CORS and security headers, integrating databases, working with WebSockets, and deploying to production. Covers the full Fastify request lifecycle (hooks, serialization, logging with Pino) and TypeScript integration via strip types. Trigger terms: Fastify, Node.js server, REST API, API routes, backend framework, fastify.config, server.ts, app.ts.
Frontend/UI architecture and code organization for a Next.js App Router + React codebase. Use when deciding WHERE code should live — folder structure, where to put a component/constant/util/hook, how to split a component, where business logic belongs, colocation vs shared. Trigger phrases: "where should this go", "folder structure", "how to split this component", "feature folder", "utils vs helpers", "business logic location", "colocation".
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Backend architecture & code organization for a Fastify + DI/ports backend (onion / ports-and-adapters style). Use when deciding WHERE backend code lives and which way dependencies flow — routes vs service vs repository, where business logic / DB access / external calls belong, ports & adapters, module boundaries. Trigger phrases: "where should this go", "onion architecture", "clean architecture", "service vs repository", "layering", "dependency direction", "ports and adapters", "business logic location", "module structure".
Modern React best practices and anti-pattern catalog (2025-26). Use when writing, reviewing, or refactoring React components, hooks, and state management. Covers component design, state patterns, hooks misuse, performance, data fetching, and code organization.
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 Claude Code plugin marketplace: a catalog of plugins (skills, agents, commands, hooks, MCP servers) distributed through a single marketplace.json.
/plugin marketplace add kolodgeeva/dev-digest-ai-marketplace
(or, for local testing before this is pushed: /plugin marketplace add ./)
/plugin install <plugin-name>@dev-digest-ai-marketplace
Browse what's available at the catalog site (search, filters, per-item docs, changelog), in plugins/ in this repo, or via /plugin marketplace list after adding it.
.claude-plugin/marketplace.json # the catalog — lists every plugin and where to find it
plugins/<plugin-name>/ # one directory per plugin
docs/ # contributor-facing guidelines
PLUGIN-GUIDELINES.md # plugin structure, manifest, dependency rules
SECURITY.md # permissions, secrets policy, script review bar
RELEASES.md # SemVer, tagging, update/rollback flow
MARKETPLACE-SITE-SPEC.md # spec for the catalog site below
scripts/
validate-marketplace.mjs # dependency-free structural linter, also run in CI
release.mjs # bump/tag/rollback tooling — see docs/RELEASES.md
build-site-data.mjs # builds site/public/data/*.json from plugins/ for the catalog site
site/ # the catalog site itself (React + Vite; `npm run dev` for local dev)
design/catalog-prototype/ # visual/UX design reference the site is built from
.github/workflows/
validate.yml # CI: linter + `claude plugin validate` + site build on every PR
deploy-pages.yml # builds site data, builds the site (`npm run build`), deploys to GitHub Pages on push to main
CONTRIBUTING.md # how to add or change a plugin
CODEOWNERS # review ownership
MARKETPLACE-RESEARCH.md # background research this setup is based on
See CONTRIBUTING.md. Short version: read docs/PLUGIN-GUIDELINES.md, add your plugin under plugins/, register it in marketplace.json, run node scripts/validate-marketplace.mjs and claude plugin validate ., open a PR.
npx claudepluginhub kolodgeeva/dev-digest-ai-marketplace --plugin engineering-paved-pathRead-only research agent: finds facts in the codebase and on the web, with a structured, source-cited report.
Read-only architecture-review agent: onion-architecture layering (backend) and dependency direction (frontend), scoped to the current diff.
Spec-Driven Development pipeline: spec, plan, implement, review, verify.
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.
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Next.js development expertise with skills for App Router, Server Components, Route Handlers, Server Actions, and authentication patterns
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
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.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.