Search

By intel

40 skills found.
Search results
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1

Adapt AutoRound to support a new diffusion model architecture (DiT, UNet, hybrid AR+DiT).

intel/auto-round1.6k—~2.8kAutomated safety check: PassApache-2.0yesterday
2
2.Adapt New LLMOfficial

Adapt AutoRound to support a new LLM architecture that doesn't work out-of-the-box.

intel/auto-round1.6k—~2.4kAutomated safety check: PassApache-2.0yesterday
3

Guides perf-based profiling of Linux programs through five flows: quick hardware counters, hotspot profiling, cache contention, core-scaling, and a report.

intel/intel-performance-skills332—~3.1kAutomated safety check: NotesUnknown9 days ago
4

Add a new model export format to AutoRound (e.g., autoround, autogptq, autoawq, gguf, llmcompressor).

intel/auto-round1.6k—~1.9kAutomated safety check: PassApache-2.0yesterday
5
5.Systemc ToolsOfficial

A skill your agent uses when writing, editing, reviewing, or debugging synthesizable SystemC code for Intel SystemC Compiler (ICSC) and SingleSource library.

intel/systemc-compiler320—~4.4kAutomated safety check: PassUnknown11 days ago
6

Add a new hardware inference backend to AutoRound for deploying quantized models (e.g., CUDA/Marlin, Triton, CPU, HPU, ARK).

intel/auto-round1.6k—~2.3kAutomated safety check: PassApache-2.0yesterday
7

Installs, runs, parses and optimizes Phoronix Test Suite benchmarks, saving scores and comparing results before and after code changes.

intel/intel-performance-skills332—~2.4kAutomated safety check: PassUnknown9 days ago
8

Add a new quantization data type to AutoRound (e.g., INT, FP8, MXFP, NVFP, GGUF variants).

intel/auto-round1.6k—~1.5kAutomated safety check: PassApache-2.0yesterday
9

Spots and fixes known x86 C and C++ performance problems from source or profiler output, such as false sharing, missing restrict and narrow SIMD.

intel/intel-performance-skills332—~903Automated safety check: PassUnknown9 days ago
10

Select the Intel GPU device to use when a system has multiple Intel GPU devices.

intel/torch-xpu-ops115—~508Automated safety check: PassMITyesterday
11
11.Add Vlm ModelOfficial

Add support for a new Vision-Language Model (VLM) to AutoRound, including multimodal block handler, calibration dataset template, and special model handling.

intel/auto-round1.6k—~2.4kAutomated safety check: PassApache-2.0yesterday
12

Check PyTorch ciflow/xpu (xpu.yml) on the main branch, collect the failing XPU test cases from the most recent completed run(s), analyze the ROOT CAUSE of each failure with AI, and produce a list…

intel/torch-xpu-ops115—~1.5kAutomated safety check: PassApache-2.0yesterday
13
13.Review PROfficial

Review or prepare a pull request for the AutoRound repository — checks registration points for new data types/backends/VLMs, validates Chinese translation parity for modified markdown files…

intel/auto-round1.6k—~1.7kAutomated safety check: PassApache-2.0yesterday
14
14.At Dispatch V2Official

Convert PyTorch ATDISPATCH macros to ATDISPATCHV2 format in ATen C++ code.

intel/torch-xpu-ops1153 repos~2.2kAutomated safety check: PassApache-2.0yesterday
15
15.PR ReviewOfficial

Review pull requests for XPU operator or backend code. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops115—~4.2kAutomated safety check: PassApache-2.0yesterday
16
16.Skill WriterOfficial

Guide users through creating Agent Skills for Claude Code. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops1153 repos~2.4kAutomated safety check: PassApache-2.0yesterday
17

Read the evidence a nightly UT run produced, decide which failures share a root cause and which are machine breakage rather than product bugs, and write one issue draft per root cause to drafts.json.

intel/torch-xpu-ops115—~2kAutomated safety check: PassApache-2.0yesterday
18

Review PyTorch upstream unit-test (UT) PRs that enable Intel GPU (XPU) on existing tests.

intel/torch-xpu-ops115—~917Automated safety check: PassApache-2.0yesterday
19

Map Intel GPU ISA instruction addresses to precise SYCL/DPC++ source file:line numbers.

intel/torch-xpu-ops115—~1.8kAutomated safety check: PassApache-2.0yesterday
20

Extract GPU ISA from oneDNN ngen-JIT kernels. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops115—~1kAutomated safety check: PassApache-2.0yesterday
21

Extract GPU ISA from AOT-compiled SYCL binaries using NEO driver runtime dump.

intel/torch-xpu-ops115—~623Automated safety check: PassApache-2.0yesterday
22

Extract GPU ISA from JIT-compiled SYCL kernels. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops115—~823Automated safety check: PassApache-2.0yesterday
23

Extract GPU ISA from Triton kernels on XPU. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops115—~806Automated safety check: PassApache-2.0yesterday
24

Extract Intel GPU ISA (assembly) from any XPU kernel. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops115—~2.9kAutomated safety check: PassApache-2.0yesterday
25
25.Fix ImplementOfficial

A skill your agent uses when asked to implement a fix for a root-caused failure, apply a proposed patch, or produce a staged code change from triage output.

intel/torch-xpu-ops115—~4.2kAutomated safety check: PassApache-2.0yesterday
26
26.Fix VerifyOfficial

A skill your agent uses when asked to verify a fix works, confirm a staged patch resolves a failure, or produce a before/after summary of a fix.

intel/torch-xpu-ops115—~3.3kAutomated safety check: PassApache-2.0yesterday
27
27.Issue HandlerOfficial

A skill your agent uses when asked to fix a GitHub issue end-to-end, run the agent pipeline on an issue, or process an agent:active / batch tracking issue.

intel/torch-xpu-ops115—~8.8kAutomated safety check: PassApache-2.0yesterday
28

A skill your agent uses when setting up a new torch-xpu-ops release branch corresponding to a PyTorch release.

intel/torch-xpu-ops115—~1.4kAutomated safety check: PassApache-2.0yesterday
29
29.SetupOfficial

Set up Intel GPU unitrace profiling tool. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops115—~566Automated safety check: PassMITyesterday
30
30.Source OneapiOfficial

Source the Intel oneAPI environment before running workloads that depend on oneAPI, SYCL, DPC++, or Level Zero.

intel/torch-xpu-ops115—~652Automated safety check: PassMITyesterday
31
31.Tmux Long TasksOfficial

Use tmux to launch and manage long-running jobs that must survive beyond the bash tool timeout.

intel/torch-xpu-ops115—~530Automated safety check: PassMITyesterday
32
32.Ut CheckOfficial

Analyze UT (unit test) results for a torch-xpu-ops PR. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops115—~1.6kAutomated safety check: PassApache-2.0yesterday
33

Build PyTorch from source with Intel XPU (GPU) support. An agent skill from intel/torch-xpu-ops.

intel/torch-xpu-ops115—~939Automated safety check: PassApache-2.0yesterday
34

How to create a pull request for the intel/torch-xpu-ops repository.

intel/torch-xpu-ops115—~1.2kAutomated safety check: PassApache-2.0yesterday
35

Generate PyTorch release notes worksheet for XPU by searching git log between release branches.

intel/torch-xpu-ops115—~1.1kAutomated safety check: PassApache-2.0yesterday
36

Generate and analyze T1/T2/R roofline reports for PyTorch OOB workloads comparing Intel XPU and NVIDIA CUDA.

intel/torch-xpu-ops115—~681Automated safety check: PassApache-2.0yesterday
37
37.Xpu AlignmentOfficial

Find upstream PyTorch behavior or fixes that may require XPU parity work, validate them on XPU, and produce independently reviewed evidence.

intel/torch-xpu-ops115—~2kAutomated safety check: PassApache-2.0yesterday
38
38.Fix ReproduceOfficial

A skill your agent uses when asked to reproduce a bug, verify a nightly CI failure, or confirm a failure still exists on latest source.

intel/torch-xpu-ops115—~7.7kAutomated safety check: PassApache-2.0yesterday
39
39.Auto LabelOfficial

Rules for automatically determining which disable labels to apply to a PR based on the file paths changed.

intel/torch-xpu-ops115—~1.7kAutomated safety check: PassApache-2.0yesterday
40
40.Issue TriageOfficial

Shallow, text-only triage of a GitHub issue on pytorch or torch-xpu-ops.

intel/torch-xpu-ops115—~2.5kAutomated safety check: PassApache-2.0yesterday