OpenParable
Skip to content

Find the skill for your next task.

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

prowler-ui

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).

14.14k repo stars2.25k repo forks
Development

ad-accuracy-debug

Debug AutoDeploy accuracy regressions vs a reference score (PyTorch backend or published baseline). Use when an AutoDeploy model's eval score is significantly below the reference and the root cause is unknown.

14.13k repo stars2.56k repo forks
Testing & Quality

ad-add-fusion-transformation

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.

14.13k repo stars2.56k repo forks
Development

ad-conf-check

Check whether AutoDeploy YAML configs were actually applied by analyzing server logs and optionally graph dumps (AD_DUMP_GRAPHS_DIR). Use when the user wants to verify config application, debug config issues, or check if AutoDeploy transforms (piecewise CUDA graph, multi-stream, sharding, fusion, etc.) were applied or fell back. Triggers on: "check config", "verify config", "ad-conf-check", "were my configs applied", "config not working", "check if piecewise is enabled", "check log for config", or any request to compare AD YAML settings against runtime behavior.

14.13k repo stars2.56k repo forks
Testing & Quality

ad-graph-dump

Enable and interpret TensorRT-LLM AutoDeploy FX graph text dumps via AD_DUMP_GRAPHS_DIR. Use when you need before/after graphs per transform, to locate subgraphs, or to confirm a rewrite ran. Paths and behavior are grounded in tensorrt_llm/_torch/auto_deploy (GraphWriter, BaseTransform). Complements ad-add-fusion-transformation.

14.13k repo stars2.56k repo forks
Testing & Quality

ad-model-onboard

Translates a HuggingFace model into a prefill-only AutoDeploy custom model using reference custom ops, validates with hierarchical equivalence tests.

14.13k repo stars2.56k repo forks
Development

ad-sharding-ir-port

Adds sharding-aware IR hints (op substitutions, sharding kwargs, all_reduce insertions) directly into an existing AutoDeploy custom model (modeling_*.py). Edits the file in place — no separate _ir.py copy. Validates with apply_sharding_hints and end-to-end multi-GPU runs.

14.13k repo stars2.56k repo forks
Development

kernel-cute-writing

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.

14.13k repo stars2.56k repo forks
Development

kernel-tileir-optimization

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.

14.13k repo stars2.56k repo forks
Development

kernel-triton-writing

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).

14.13k repo stars2.56k repo forks
Development