By j0ruge
Automate pre-PR code reviews with severity-graded analysis, detecting hardcoded secrets, TOCTOU race conditions, accessibility issues, and dead code. Resolve AI review comments from CodeRabbit, Copilot, Gemini, and Codex on GitHub PRs.
Resolves AI review comments on a GitHub PR — auto-detects CodeRabbit, Copilot, Gemini, Codex; creates per-reviewer checklists, verifies findings against current code (with byte-exact inspection when reviewers cite invisible/control characters), applies fixes, runs regression tests, resolves GitHub conversations, then cleans up its own checklist files. Triggers — coderabbit, copilot review, gemini review, codex review, fix PR review.
Pre-PR review with severity grading and model routing (haiku/sonnet/opus). Detects TOCTOU races, accessibility gaps, hardcoded secrets (GitGuardian-equivalent regex), docs/OpenAPI sync, contract drift in tests (exported const grew without its assertion updated), and **dead code** via a parallel whole-repo sweep — unused exports, orphaned files, unreachable code (knip/ts-prune/vulture or grep) — with cleanup recs. Final report always includes the Overall Grade table + Recommended Actions. Stack-agnostic with TypeScript/React defaults, dotnet preset. Triggers — code review, pre-PR, secrets scan, accessibility audit, contract drift, dead code, unused exports, cleanup, code health.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Apply non-obvious session lessons to a target skill in two modes — full (marketplace skill: bumps version, updates CHANGELOG/marketplace.json/README, commits and pushes) or lean (local skill in another repo: edits files + CHANGELOG and commits there, no bump or marketplace changes). Triggers — retrofit, skill-maintenance, session-lessons, lean-retrofit, local-skill.
Self-hosted Zitadel v4 OIDC field guide — 43 documented quirks + working docker-compose, idempotent TypeScript bootstrap, and reset script. High-friction traps: FirstInstance env placement, JWT/JWKS over self-signed HTTPS, TLS-terminating reverse proxy (`--tlsMode external`) and the admin-console `Failed to fetch` mixed-content trap, Login UI v1/v2, v2.66→v4 upgrade, API v1→v2 mapping, silent-renew, 401-storm defenses, smoke-e2e CI. Triggers — zitadel, oidc self-hosted, silent-renew, JWKS, masterkey, v2.66→v4, api v1→v2, login-ui-v2, tlsMode external, console Failed to fetch, mixed content, smoke-e2e CI, Playwright self-signed Zitadel.
GitHub Actions / Docker / GHCR pipeline troubleshooting and config — auto-routes by stack: backend Node (Prisma/Biome) or Django (gunicorn), plus frontend Vite. Deep self-hosted runner runbook (containerized myoung34 + systemd): registration-token chicken-and-egg, ACCESS_TOKEN/PAT migration, deprecated-binary & deleted-registration crashloops, stacked failures, silently-queued deploys. Also GHCR auth/TLS-handshake-timeout, reverse-proxy upstream poisoning, Django ALLOWED_HOSTS healthcheck-400. Triggers — CI/CD, GitHub Actions, GHCR auth, self-hosted runner, runner crashloop, registration token expired, runner version deprecated, compose run orphan, deploy queued, Django gunicorn.
Automated GitHub Release creation with categorized release notes from git history. Multi-stack (C#/.NET, Node.js, Go, Rust, Python) with --path filter for monorepo component releases. Contributor resolution via org membership cross-reference.
Complete C#/.NET WPF development toolkit — project setup & audit, Fluent Design guide (90+ controls), WinForms-to-WPF MVVM migration, and FlaUI E2E testing.
npx claudepluginhub j0ruge/skills_commands_manager --plugin codereviewComprehensive 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.
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.
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Consult multiple AI coding agents (Gemini, OpenAI, Grok, Perplexity, plus codex, antigravity, and grok CLIs when installed) to get diverse perspectives on coding problems
UI/UX design intelligence. Searchable local database with 84 styles, 192 palettes, 74 font pairings, 25 charts, and 22 stacks (React, Next.js, Vue, Nuxt.js, Nuxt UI, Svelte, Astro, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, Jetpack Compose, Angular, Laravel, JavaFX, WPF, WinUI, Avalonia, Uno Platform, UWP, Three.js). Use when designing, building, or reviewing UI: pages, components, color schemes, typography, layout, accessibility, animation, or data visualization.