AB 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.
The skill adds configs to optimize Triton kernels for TileIR on Blackwell GPUs (sm_100+). Promises autotuning of occupancy, num_ctas, TMA descriptors, and kernel classification (dot, norm, elementwise, reduction). Triggers include "optimize for TileIR" or "Blackwell optimization".
Files contain 5 modules and 2 scripts, 2177 tokens total. Scores: safety 100, quality 100, process 66. No critical findings. Kernels use standard `import triton`; TileIR activates via ENABLE_TILE=1 with nvtriton installed. This means the skill wraps existing infrastructure rather than solving the problem standalone. No model runs or sandbox tests.
Install if you work with TensorRT-LLM and need Blackwell tuning. Otherwise skip it.
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm100+).
As a process B 66/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Tools and files. No external tools needed
- 100Steps. 22 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2177 tokens
- 100Progress reporting. Reports progress
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 544: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 22 items
- +3Output format is stated explicitly
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 100.