Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills › Engineering › Page 423

Claude Engineering Skills (Page 423 of 488)

Code review, refactoring, testing, DevOps, CI/CD, databases, cloud platforms, and full-stack development skills for Claude Code.

29,262 skills · updated 2026-10-25 · showing 25321–25380 of 29,262 by quality score

Sub-topics:Testing (4,356)Devops (3,948)Architecture (3,203)Backend (2,624)Frontend (1,764)Languages (1,535)Code Quality (1,513)Cloud Platforms (1,362)

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Use when designing a system whose past behaviour must be recoverable as a fact — RL training substrates, multi-agent simulations, deterministic game engines, replay-debuggable…
Specialist developer agents for backend (Go/TypeScript), frontend, design, Helm charts, UI implementation, frontend QA, and prompt quality review.
Use when building networks that grow, prune, or adapt topology during training. Routes to continual learning, gradient isolation, modular composition, and lifecycle orchestration…
Use when creating or sending Mailtrap-hosted email templates, Handlebars personalization, template UUID in API payloads, or debugging variables and preview.
Teaches generic constraints, avoiding any in generic defaults, and mapped types in TypeScript. Use when creating reusable functions, components, or types that work with multiple…
Bootstrap skill — establishes how to find and use GodotPrompter skills, with platform-specific tool mapping
Use when starting work on code with non-obvious constraints or history, debugging, making architectural decisions, working with external services, when the user references…
Dual-mode skill for github.com/LerianStudio/lib-streaming, Lerian's producer-only event publication library (Kafka, SQS, RabbitMQ, EventBridge).
Dual-mode skill for github.com/LerianStudio/lib-systemplane, Lerian's dual-backend (Postgres LISTEN/NOTIFY or MongoDB change streams) hot-reload runtime configuration plane.
Use Loom before work. Load this first in Loom workspaces before coding, debugging, design, review, release, record edits, or any nontrivial task unless an adapter already loaded…
Use when mcp-language-server tools are available and you need semantic code intelligence for navigation, refactoring, or type analysis
Manages Medusa Cloud resources through the Cloud CLI (mcloud). Use when deploying, debugging deployments, managing environments, environment variables, or any Medusa Cloud…
Use when starting work in a project that uses minerva (a `.minerva/` directory exists at the project root, or the user has invoked any `minerva:` skill in this session), or when…
Router skill directing to deployment, optimization, MLOps, and monitoring guides.
Neon is a serverless Postgres platform that separates compute and storage to offer autoscaling, branching, instant restore, and scale-to-zero.
The architecture selection router for CNNs, Transformers, RNNs, GANs, GNNs by data modality and constraints
Applies Next.js App Router conventions — Server Components, Server Actions, and fetch-based caching. Use whenever writing or reviewing Next.js code in the app/ directory.
Use automatically before diagnosing or fixing a concrete software engineering failure, including bugs, exceptions, failing tests, build or CI failures, deployment and runtime…
Use at the start of any Odoo PSDU task to know which Odoo-specific skill to reach for. Covers when to invoke odoo-module-development, odoo-code-review, odoo-test-runner,…
Prisma 5+ ORM with schema-first design, type-safe client, migrations, and database integrations (Supabase, PlanetScale, Neon). Use for TypeScript/JavaScript database access.
Routes to appropriate PyTorch specialist skill based on symptoms and problem type — from majiayu000/claude-skill-registry
Dual-mode skill for lib-observability/runtime — the panic observability trident that turns silent goroutine deaths into production signal.
Guidance for using Serena's LSP-powered symbol analysis. Use when you say "how do I find a symbol", "trace references for this method", "explore this file's structure", or when…
Use at session start - establishes Shannon Framework workflows including mandatory 8D analysis before implementation, NO MOCKS testing enforcement, wave-based execution for…
Use before substantial work in a spec-first project, and when users ask what spec-first workflow or command to run next.
Using st.session_state to manage state across Streamlit reruns. Use when persisting data, handling widget state, implementing callbacks, or debugging state issues.
MUST be called first for any QA-shaped request. Triggers — test plan, test strategy, test approach, regression scope, risk-based testing, exploratory testing, code review,…
Design or debug Swift concurrency, isolation, Sendable, actors, tasks, and cancellation. Use proactively for async behavior, concurrency migrations, or compiler diagnostics.
Use when analyzing existing codebases to generate architecture documentation - coordinates subagent-driven exploration with mandatory workspace structure, validation gates, and…
Use when you have architecture documentation from system-archaeologist and need critical assessment, refactoring recommendations, or improvement prioritization - routes to…
Use when programmatically creating or managing agent trajectories in TypeScript - provides TrajectoryClient for persistent storage and TrajectoryBuilder for in-memory construction
Use when managing multi-document sets as wikis - manifest-driven architecture, reading paths, derivation discipline, terminology/claim consistency, change evolution, and…
Receive and verify USPS webhooks (Subscriptions - Tracking API v3.2). Use when setting up USPS tracking webhook handlers, debugging X-HMAC signature verification, creating…
One-shot helper for registering a utels.dev project and writing the returned ingest token straight into a wrangler secret.
Receive and verify Utila webhooks. Use when setting up Utila webhook handlers, debugging x-utila-signature RSA/PSS verification, or handling Utila digital-asset events like…
Reference card for the smaller utility packages Remix v3 bundles — `remix/mime` (`detectContentType` from filename, `isCompressibleMimeType`, `defineMimeType`), `remix/lazy-file`…
Build, develop, and publish uTools plugins. Use when the user asks to create a uTools plugin, add features to an existing uTools plugin, query uTools APIs (utools.db,…
Translate the UTS pseudocode test specs in a whole module directory into runnable Kotlin tests in the ably-java uts module. Takes a UTS module directory (e.g.
ASGI server for Python web applications - Fast, production-ready server for async frameworks — from engineering/engineering-misc
ASGI server for Python web applications - Fast, production-ready server for async frameworks — from majiayu000/claude-skill-registry
UX Vern - Cool architecture, but can the user find the button? Empathy-driven design thinking.
Generate high-quality Vela-compatible slide deck JSON from topics, outlines, documents, or existing slide content.
Generate high-quality Vela-compatible slide deck JSON from topics, outlines, documents, or existing slide content.
Generate high-quality Vela-compatible slide deck JSON from topics, outlines, documents, or existing slide content.
Refactor existing V2 code to follow ideal SOLID pattern. Use when user says "refactor", "fix violations", "cleanup V2", or "/v2-refactor ".
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive…
Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.
Implement or review a Remotion 5 breaking change while the v4 and v5 release lines still share code. Use when v4 behavior and public types must remain compatible on main, but…
Key commands for building, debugging, and testing in V8. Use when needing command syntax for gm.py, d8 flags, or run-tests.py. Do not use for environment setup.
Maps the V8 dir/folder structure, component locations, and local documentation. Use when locating specific subsystems, mapping src/ code to docs/ design files, or understanding…
Executes and interprets V8 tests. Use when running unittests, cctest, or mjsunit, or when debugging test failures. Do not use for building.
\"Use this agent when you need to design, build, or optimize data pipelines, ETL/ELT processes, and data infrastructure.
\"Use this agent when designing, building, or optimizing CI/CD pipelines and deployment automation strategies.\".
\"Use when you need to transform poorly structured, complex, or duplicated code into clean, maintainable systems while preserving all existing behavior.\".
PostgreSQL's VACUUM machinery — heap scanning, dead-tuple collection, index cleanup, HOT pruning, freezing, VM/FSM updates, truncation — plus the autovacuum launcher/worker…
Comprehensive guide for developing with Vagrant, including Vagrantfile configuration, custom boxes, providers (VirtualBox, VMware, Hyper-V, libvirt, AWS), provisioners (Ansible,…
Use when the user wants to manage Valet agents, channels, connectors, organizations, or environment variables (secrets and plain config) via the valet CLI.
Run comprehensive validation on all site content. Use for daily health checks or before deployment.
Use check-jsonschema when an agent needs to catch broken GitHub Actions, Renovate, Azure Pipelines, and other schema-backed config files before they hit CI.
Hướng dẫn kiểm tra chéo mã nguồn để đảm bảo quá trình tự động build IPA trên GitHub Actions không bị lỗi.
Search all 29,262 Engineering skills →