Most popular Claude skills · page 345

Agent skills for Claude Code, Claude.ai and other agents, ranked by popularity: GitHub stars, forks, and how many curated lists and repos include them.

22,429 skills · showing 16513–16560

  1. 16513Physics Enginej4flmao/agent-skillsUse when the user asks about a physics engine, collision detection, broad phase, narrow phase, GJK, EPA, constraint solvers, rigid bodies, CCD, character controllers or Jolt/PhysX internals. Produces rigid-body physics design and solver code. Not for engine-specific physics settings (use unity, unreal or godot).45
  2. 16514Platform Abstractionj4flmao/agent-skillsUse when the user asks about a platform abstraction layer, cross-platform engine code, windowing, engine filesystem, dynamic library loading, high-resolution timers or platform ifdefs. Produces a PAL for Windows, Linux, macOS and consoles. Not for mobile app platform APIs (use mobile-patterns).45
  3. 16515Preactj4flmao/agent-skillsUse when the user asks about Preact, Preact signals, preact/compat, Preact vs React, Preact SSR or cutting bundle size with a React-compatible library. Produces Preact components, signal-based state and compat aliasing. Not for React-specific architecture (use react-architecture).45
  4. 16516Project Initj4flmao/agent-skillsUse when the user asks to scaffold a project, create the project structure, initialize a new repo from scratch, set up folders and config files or generate AGENTS.md. Scaffolds the directory tree and starter config for the detected or stated stack. Not for onboarding people (use core-onboarding) or dev containers (use dev-loop-dev-container).45
  5. 16517Prometheus Grafanaj4flmao/agent-skillsUse when the user asks about kube-prometheus-stack, ServiceMonitor, exposing /metrics, PromQL queries, Prometheus alert rules, Alertmanager routing, Grafana dashboards as code, or RED and USE metrics. Produces Prometheus, Alertmanager and Grafana configs. Not for TSDB internals and scaling (use sre-observability-scaling) or SLO burn-rate alerts (use sre-sli-slo-management).45
  6. 16518Ptx Assemblyj4flmao/agent-skillsUse when the user asks about PTX, inline asm volatile in CUDA, nvcc -ptx, ptxas -v register spills, state spaces, cp.async, mma.sync or bar.sync. Produces explained PTX listings or inline-asm snippets with constraints and SASS verification steps. Not for native machine code and stall analysis (use sass-machine-code) or kernel design (use cuda-programming).45
  7. 16519Python Django Architecturej4flmao/agent-skillsUse when the user asks about Django, Django ORM queries that are slow, select_related and prefetch_related, Django REST framework (DRF), Django apps structure or migrations. Produces Django code with a service layer and N+1-free queries. Not for FastAPI (use python-fastapi-architecture).45
  8. 16520Python Fastapi Architecturej4flmao/agent-skillsUse when the user asks about FastAPI, setting up a FastAPI project with dependency injection and Pydantic models, Depends(), APIRouter structure, lifespan events or async SQLAlchemy. Produces a layered FastAPI project. Not for Django (use python-django-architecture) or Flask (use flask-backend).45
  9. 16521Quarkus Backendj4flmao/agent-skillsUse when the user asks about Quarkus, Quarkus REST (RESTEasy Reactive), Panache, Dev Services, Quarkus native build, SmallRye Reactive Messaging or continuous testing. Produces Quarkus services with config, health checks and tests. Not for Micronaut (use micronaut) or Spring Boot (use spring-boot-architecture).45
  10. 16522Rate Limitingj4flmao/agent-skillsUse when the user asks about rate limiting, protecting a public API from abuse with request throttling, token bucket, sliding window, 429 Too Many Requests, Retry-After or per-user quotas. Produces an algorithm, key and Redis-backed limiter. Not for circuit breakers and bulkheads (use backend-resilience-patterns).45
  11. 16523Rdma Rocej4flmao/agent-skillsUse when the user asks about RDMA, RoCEv2, InfiniBand, GPUDirect RDMA, ibverbs, PFC, ECN/DCQCN, lossless Ethernet or NCCL falling back to NET/Socket. Produces a fabric checklist, validation commands (perftest, nccl-tests) and NCCL env settings. Not for choosing DDP/FSDP parallelism (use distributed-training).45
  12. 16524React Architecturej4flmao/agent-skillsUse when the user asks about React project structure, feature-based folders, a React component that re-renders too often, how to structure state and custom hooks, error boundaries or the React Compiler. Produces a React 19 app architecture with component and hook conventions. Not for Next.js App Router (use react-nextjs) or picking a state library (use frontend-state-management).45
  13. 16525React Fiber Architecturej4flmao/agent-skillsUse when the user asks about React Fiber, reconciliation, render vs commit phase, lanes, concurrent rendering, time slicing, the React scheduler or why a component rendered twice. Produces an explanation of reconciler internals to debug render behaviour. Not for app architecture (use react-architecture) or React Three Fiber (use web3d-webgl).45
  14. 16526React Nextjsj4flmao/agent-skillsUse when the user asks about Next.js, App Router, Server and Client Components, 'use client', Server Actions, layouts, loading.tsx/error.tsx, caching and revalidation, proxy/middleware or Next.js data fetching. Produces Next.js 15/16 App Router code and route structure. Not for render/caching internals or why a route is dynamic (use nextjs-internals).45
  15. 16527React Server Componentsj4flmao/agent-skillsUse when the user asks about React Server Components, RSC, 'use client' / 'use server' boundaries, Server Functions (server actions), serializable props or the RSC payload in React 19. Produces boundary placement and data/mutation patterns that work in any RSC framework. Not for Next.js routing and caching specifics (use react-nextjs).45
  16. 16528Red Team Pentest Methodologyj4flmao/agent-skillsUnderstand the theoretical frameworks of offensive security, OSINT, and attack lifecycles.45
  17. 16529Render Graphj4flmao/agent-skillsUse when the user asks about a render graph, frame graph, transient resource aliasing, automatic barriers, async compute, GPU-driven rendering or command list recording. Produces render graph design with pass and resource lifetimes. Not for raw Vulkan API usage (use vulkan).45
  18. 16530Rtosj4flmao/agent-skillsUse when the user asks about FreeRTOS, task priorities, xTaskCreate, ISR-safe queues, mutex vs semaphore, priority inversion, task notifications, task stack overflow or Zephyr threads. Produces RTOS task design, ISR deferral and timing analysis. Not for bare-metal superloops (use c-cpp-patterns or bare-metal-rust).45
  19. 16531Ruby Railsj4flmao/agent-skillsUse when the user asks about Ruby on Rails, ActiveRecord callbacks getting out of hand, service objects, Rails API mode, Active Job / Solid Queue, N+1 with includes or RSpec. Produces Rails 8 code with thin models and controllers. Not for Ruby outside Rails or Phoenix (use backend-elixir).45
  20. 16532Rust Architecturej4flmao/agent-skillsUse when the user asks about Rust backend structure, Cargo workspace layout, crate boundaries, hexagonal Rust, trait-based DI or choosing axum vs actix-web. Produces a Rust service layout with error architecture. Not for tokio, serde or ownership recipes (use rust-patterns) or language basics (use lang-rust).45
  21. 16533Rust Patternsj4flmao/agent-skillsUse when the user asks about tokio patterns, axum extractors, thiserror vs anyhow, serde, Arc<Mutex> vs RwLock, tower-http middleware or sqlx queries. Produces idiomatic async Rust backend code. Not for workspace layout (use rust-architecture).45
  22. 16534Sandbox Executionj4flmao/agent-skillsUse when the user asks to sandbox agent code, run untrusted code from an LLM, gVisor (runsc), Firecracker microVMs, Kata Containers, durable execution with Temporal, or sandbox snapshot and fork. Produces a sandbox config with isolation level, network and resource limits, plus a durable-execution design. Not for container image hardening (use security-container-security).45
  23. 16535Sass Machine Codej4flmao/agent-skillsUse when the user asks about SASS, cuobjdump -sass, nvdisasm, warp stall reasons, long scoreboard, HMMA/HGMMA, FFMA or instruction mix in Nsight Compute. Produces annotated SASS with root cause and a source-level fix. Not for writing PTX or inline asm (use ptx-assembly) or general kernel design (use cuda-programming).45
  24. 16536Scala Playj4flmao/agent-skillsUse when the user asks about Play Framework, Scala Play controllers, Play JSON Reads/Writes, Slick, Guice DI in Play or Pekko streams in Play 3. Produces Play 3 services with async actions and tests. Not for Scala language basics (use lang-scala).45
  25. 16537Scaling Architecturej4flmao/agent-skillsUse when the user asks about game server scaling, shards, zone servers, Agones, game server fleet autoscaling or game backend capacity. Produces fleet, persistence and region design with capacity math. Not for a single server tick loop (use authoritative-server) or generic web autoscaling (use devops-kubernetes-autoscaling).45
  26. 16538Spring Boot Architecturej4flmao/agent-skillsUse when the user asks about Spring Boot project structure, package-by-feature, hexagonal Spring, Spring WebFlux vs MVC, Spring Data repositories or Spring profiles. Produces a Spring Boot 3/4 service layout. Not for @Transactional, AOP, security or testing recipes (use spring-boot-patterns).45
  27. 16539Spring Boot Patternsj4flmao/agent-skillsUse when the user asks about Spring Boot service layer and transaction boundaries, @Transactional, constructor injection, Spring AOP, Spring Security filter chain or @DataJpaTest/@WebMvcTest. Produces Spring Boot pattern code. Not for package layout (use spring-boot-architecture).45
  28. 16540Statistical Mechanicsj4flmao/agent-skillsUse this skill when the user says 'diffusion model math', 'score matching', 'DDPM', 'Langevin dynamics', 'reverse SDE', 'probability flow ODE', 'Boltzmann distribution', 'energy-based model', 'classifier-free guidance', 'flow matching', 'noise schedule'. Explains the statistical-mechanics view of generative modeling (Boltzmann distributions, Langevin dynamics, forward/reverse diffusion SDEs, score functions) and implements a correct DDPM training and sampling loop. Do NOT use for: using pretrained image generators (ai/genai-vision), information-theoretic losses (fundamental-truths/information-45
  29. 16541Stencilj4flmao/agent-skillsUse when the user asks about Stencil, @stencil/core, @Component/@Prop/@State/@Event decorators, a web component compiler, framework output targets or a Stencil design system. Produces lazy-loaded, framework-agnostic Stencil components and build config. Not for Lit (use frontend-lit) or hand-written custom elements (use frontend-web-components).45
  30. 16542Storage Infrastructurej4flmao/agent-skillsUse when the user asks about SAN, NAS, iSCSI, Fibre Channel, NVMe-oF, Ceph, MinIO, ZFS, RAID levels, block vs file vs object storage, SSD endurance, thin provisioning, or fio benchmarks. Produces storage architecture and benchmarking plans. Not for Longhorn on Kubernetes (use longhorn) or backup policy (use backup-dr).45
  31. 16543Supabasej4flmao/agent-skillsUse when the user asks about Supabase, setting row level security policies in Supabase, Supabase Auth, Realtime, Storage policies, Edge Functions or supabase CLI migrations. Produces Supabase schema, RLS and function code. Not for Firebase (use firebase) or general multi-tenancy (use backend-multi-tenancy).45
  32. 16544Sveltekitj4flmao/agent-skillsUse when the user asks about SvelteKit load functions and form actions, +page.server.ts, +server.ts endpoints, hooks, use:enhance, adapters, SSR/prerendering or SvelteKit deployment. Produces SvelteKit routes, server loads, validated actions and adapter config. Not for Svelte component and rune design (use frontend-svelte-architecture).45
  33. 16545Symfony Backendj4flmao/agent-skillsUse when the user asks about Symfony, Doctrine ORM entities, Symfony Messenger, autowiring, security voters, Flex recipes or WebTestCase. Produces Symfony 7 services, entities and tests. Not for Laravel (use php-laravel) or Laminas (use php-zend).45
  34. 16546Tensorrt Optimizationj4flmao/agent-skillsUse when the user asks about TensorRT, trtexec, ONNX to TensorRT engines, optimization profiles for dynamic shapes, FP8/INT8 engines, Polygraphy or TensorRT-LLM / trtllm-serve. Produces build commands, precision plan and benchmark plan. Not for choosing GPTQ/AWQ in depth (use extreme-quantization-mastery) or serving platforms (use ml-model-serving).45
  35. 16547Terraformj4flmao/agent-skillsUse when the user asks for a Terraform module (for example a VPC with remote state), state backends and locking, workspaces, terraform plan in CI, module versioning, import and moved blocks, or OpenTofu. Produces module layouts, backend configs and CI review flows. Not for Pulumi (use devops-pulumi) or configuration management (use ansible).45
  36. 16548Tool Calling Principlesj4flmao/agent-skillsUse when the user asks about tool calling, function calling, tool schemas, tool_use / tool_result, strict structured outputs, an agent picking the wrong tool or tool error handling. Produces JSON Schema tool definitions, validated handlers with teaching errors, idempotency and a permission matrix. Not for the agent loop (use ai-agent-core-loop) or REST API design (use backend-api-design).45
  37. 16549Tpu Systolic Arraysj4flmao/agent-skillsUse when the user asks about TPUs, systolic arrays, the MXU, XLA on TPU, JAX TPU performance, Pallas kernels, TPU padding or recompilation. Produces shape, dtype and sharding rules plus JAX code and profiling steps. Not for NVIDIA GPU kernels (use cuda-programming) or GPU multi-node training (use distributed-training).45
  38. 16550Triton Kernelsj4flmao/agent-skillsUse when the user asks about OpenAI Triton kernels, @triton.jit, tl.load, tl.dot, triton.autotune, fused kernels in Python or torch.compile Inductor kernels. Produces a kernel, PyTorch wrapper, correctness test and do_bench benchmark. Not for Triton Inference Server (use ml-model-serving) or CUDA C++ (use cuda-programming).45
  39. 16551Unityj4flmao/agent-skillsUse when the user asks about Unity 6, MonoBehaviour, the player loop, URP, HDRP, Addressables, Netcode for GameObjects, Unity physics or Unity Profiler. Produces Unity project architecture, gameplay code and performance fixes. Not for DOTS, Entities and Burst in depth (use unity-csharp) or Unreal (use unreal).45
  40. 16552Unity Csharpj4flmao/agent-skillsUse when the user asks about Unity DOTS, Unity ECS with Entities, ISystem, IJobEntity, Burst jobs, the C# Job System, NativeArray or GC-free Unity C#. Produces Entities, Jobs and Burst code with correct safety rules. Not for general Unity project architecture (use unity) or engine-agnostic ECS design (use ecs-pattern).45
  41. 16553Unrealj4flmao/agent-skillsUse when the user asks about Unreal Engine 5, UE5 C++, Blueprints, UObject and Actor lifecycle, Gameplay Ability System, Nanite, Lumen, Chaos physics or Unreal replication. Produces Unreal project architecture and C++/Blueprint guidance. Not for Unity (use unity) or custom engine rendering (use render-graph).45
  42. 16554Vapor Backendj4flmao/agent-skillsUse when the user asks about Vapor, server-side Swift, Fluent ORM and migrations, Vapor middleware, Vapor WebSocket or Vapor Queues. Produces async/await Vapor 4 services with tests. Not for iOS apps (use ios).45
  43. 16555Vaultj4flmao/agent-skillsUse when the user asks to store database credentials in HashiCorp Vault, dynamic secrets, KV v2, Transit encryption, the PKI engine, Vault policies, auth methods (Kubernetes, OIDC, AppRole), Vault Agent or the injector. Produces Vault configs and policies. Not for cloud secret stores or overall secrets strategy (use security-secrets-management).45
  44. 16556Vue Architecturej4flmao/agent-skillsUse when the user asks about Vue 3 project structure, Vue 3 composables for shared logic, script setup, Composition API architecture, feature folders, Pinia store layout or migrating from the Options API or Vuex. Produces a Vue 3 app structure and conventions. Not for Nuxt (use vue-nuxt) or specific router/directive patterns (use frontend-vue-patterns).45
  45. 16557Vue Nuxtj4flmao/agent-skillsUse when the user asks about Nuxt 4 or Nuxt 3, useFetch and useAsyncData, server routes in server/api, Nitro, Nuxt layers, route rules, the app/ directory, auto-imports or upgrading Nuxt 3 to 4. Produces Nuxt app structure, data fetching and server code. Not for plain Vue 3 SPA structure (use vue-architecture).45
  46. 16558Vulkanj4flmao/agent-skillsUse when the user asks about Vulkan, swapchain recreation on window resize, vkQueueSubmit, dynamic rendering, pipeline barriers, synchronization2, descriptor sets, VMA or validation layer errors. Produces explicit Vulkan setup, sync and memory code. Not for engine-agnostic frame graph design (use render-graph).45
  47. 16559Webgpu Webgl Renderingj4flmao/agent-skillsUse when the user asks about WebGPU, WGSL, WebGL2, GLSL shaders, bind groups, render pipelines, GPU buffers or compute shaders in the browser. Produces low-level browser GPU pipeline setup, buffer alignment, WebGL2 fallback and per-frame performance rules. Not for Three.js or React Three Fiber scenes (use web3d-webgl).45
  48. 16560Zero Trust Identityj4flmao/agent-skillsAdvanced Zero Trust Identity, OIDC/SAML Mechanics, and JWT Validation45