Browse reusable Agent Skills, each with a clear purpose and practical guidance.
ABP MVC and Razor Pages UI - AbpPageModel, abp tag helpers (abp-card, abp-dynamic-form, abp-modal), JavaScript abp.ajax/abp.auth/abp.notify, DataTables integration, bundle/minification. Use when working on MVC or Razor Pages UI in ABP projects.
Bring up and verify the local Logto development environment end to end. Use when a coding agent or developer needs a working localhost stack for feature development, including runtime setup, dependency install, Postgres initialization, database seed/alteration, pnpm start:dev, service health checks, first admin setup, Console/Experience/API smoke tests, Experience /demo-app or first_screen walkthroughs, or screenshots as proof.
Creates Prowler Attack Paths openCypher queries using the Cartography schema as the source of truth for node labels, properties, and relationships. Covers Prowler-specific additions (Internet node, ProwlerFinding, internal isolation labels), $provider_uid scoping, and list-property item nodes with typed `HAS_*` edges that run efficiently on both Neo4j and Amazon Neptune sinks. Trigger: When creating or updating Attack Paths queries.
Creates Pull Requests for Prowler following the project template and conventions. Trigger: When working on pull request requirements or creation (PR template sections, PR title Conventional Commits check, changelog gate/no-changelog label), or when inspecting PR-related GitHub workflows like conventional-commit.yml, pr-check-changelog.yml, pr-conflict-checker.yml, labeler.yml, or CODEOWNERS.
Prowler UI-specific patterns. For generic patterns, see: typescript, react-19, nextjs-16, tailwind-4. Trigger: When working inside ui/ on Prowler-specific conventions (shadcn, folder placement, actions/adapters, shared types/hooks/lib).
Claude Code skill (trtllm-agent-toolkit): implement or extend TensorRT-LLM AutoDeploy fusion transforms under transform/library/ in a TensorRT-LLM checkout. Prefer existing kernels and custom ops; use Triton only when no viable existing-kernel path exists. Use ad-graph-dump for AD_DUMP_GRAPHS_DIR workflows. Covers TRT-LLM paths, registry, default.yaml registration, graph validation, tests, and a review checklist — without prescribing profiling tools or throughput targets.
Write and implement GPU kernels using NVIDIA CuTe DSL (CUTLASS 4.x Python API) — NOT for Triton, CUDA C++, or conceptual explanations. Trigger only when the user wants to write or implement a kernel, not when asking questions about CuTe DSL concepts or layouts. CuTe DSL uses cute.jit/cute.kernel decorators and cutlass.cute imports. Covers element-wise kernels, GEMM patterns, reductions, memory hierarchy (global/shared/register/TMA), MMA tensor core operations, software pipelining, and framework integration.
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA descriptors. Covers kernel classification (dot-related, norm-like, elementwise, reduction), type-specific transformations, and PTX-vs-TileIR benchmarking. Triggered by: "optimize for TileIR", "add TileIR configs", "Blackwell optimization", "TMA descriptors", "2CTA mode", "occupancy tuning". Kernels use standard `import triton`; TileIR activates via ENABLE_TILE=1 when nvtriton is installed.
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must involve Triton explicitly. Covers Triton-specific patterns: fused elementwise, reductions (softmax, LayerNorm, RMSNorm), tiled GEMM with triton.autotune, and flash attention. Workflow: design, write, verify (with fast-path for explicit requests).