Skip to main content
Run any Skill in Manus
with one click
$pwd:
intel
GitHub creator profile

intel

Repository-level view of 20 collected skills across 7 GitHub repositories, including approximate occupation coverage.

skills collected
20
repositories
7
occupation fields
1
updated
2026-05-29
occupation focus
Major fields detected across this creator.
repository explorer

Repositories and representative skills

#001
auto-round
7 skills1.4k134updated 2026-05-14
35% of creator
adapt-new-diffusion-model
Software Developers

Adapt AutoRound to support a new diffusion model architecture (DiT, UNet, hybrid AR+DiT). Use when a new diffusion model fails quantization, needs custom output configs, requires a custom pipeline function, or is a hybrid architecture with both autoregressive and diffusion components.

2026-05-14
adapt-new-llm
Software Developers

Adapt AutoRound to support a new LLM architecture that doesn't work out-of-the-box. Use when quantization fails for a new model type, block detection doesn't find layers, MoE models need unfusing, custom forward passes are needed, or non-standard linear layer types need handling.

2026-05-14
add-vlm-model
Software Developers

Add support for a new Vision-Language Model (VLM) to AutoRound, including multimodal block handler, calibration dataset template, and special model handling. Use when integrating a new VLM like LLaVA, Qwen2-VL, GLM-Image, Phi-Vision, or similar multi-modal models for quantization.

2026-05-14
add-inference-backend
Software Developers

Add a new hardware inference backend to AutoRound for deploying quantized models (e.g., CUDA/Marlin, Triton, CPU, HPU, ARK). Use when implementing QuantLinear kernels, registering backend capabilities, or enabling quantized model inference on a new hardware platform.

2026-05-11
add-export-format
Software Developers

Add a new model export format to AutoRound (e.g., auto_round, auto_gptq, auto_awq, gguf, llm_compressor). Use when implementing a new quantized model serialization format, adding a new packing method, or extending export compatibility for deployment frameworks like vLLM, SGLang, or llama.cpp.

2026-04-17
add-quantization-datatype
Software Developers

Add a new quantization data type to AutoRound (e.g., INT, FP8, MXFP, NVFP, GGUF variants). Use when implementing a new weight/activation quantization scheme, registering a new quant function, or extending the data_type registry.

2026-04-17
review-pr
Software Quality Assurance Analysts & Testers

Review a pull request for the AutoRound repository with a structured checklist covering code quality, test coverage, documentation, Chinese translations, and quantization-specific concerns. Use when reviewing or preparing to submit a PR.

2026-04-17
#002
torch-xpu-ops
4 skills94107updated 2026-05-22
20% of creator
#004
intel-performance-skills
3 skills42updated 2026-05-29
15% of creator
performance-patterns
Software Developers

Detect and fix x86/C/C++ performance patterns from source code or profiling output (perf, VTune, flamegraphs). Invoke when the user asks to optimize, review for performance, or write new SIMD/vectorized code — even without profiling data. Trigger on: serial accumulator loops, narrow SIMD (xmm/ymm that could be ymm/zmm), _mm* intrinsics, HITM/cmpxchg clusters, false sharing, missing restrict or vzeroupper, hot symbol inside a system library (.so) that may have a version gap, or any request to write a fast reduction, dot product, or CPU-dispatched function. Patterns: serial accumulator, TTAS spinlock, SIMD upconversion (zipper), false sharing, per-CPU stats, missing vzeroupper, missing restrict, CPU dispatch, library version upgrade, fast CRC32C (crc32c function name trigger, single-accumulator _mm_crc32 loop, table-lookup CRC32C), known algorithms (Cosine Similarity, Hamming Distance, Jaccard Distance), SIMD sort for numeric primitives (float/double/int32_t/uint32_t/int64_t/uint64_t via x86-simd-sort).

2026-05-29
linux-perf
Network & Computer Systems Administrators

Profile and fix Linux performance problems using `perf`. Workflows: (A) hardware counters -- IPC, cache-miss, branch mispredictions; (B) hotspot profiling -- which functions and source lines consume CPU, with SIMD and accumulator detection; (C) cache-line contention -- false sharing, HITM, `perf c2c`; (D) core-count scaling -- dual-profile comparison, bottleneck categorization; (E) structured hotspot report with annotated source and pattern observations. Resolution strategies: TTAS spinlock, SIMD upconversion, parallel accumulator, structured false-sharing fix, per-CPU stats. Trigger on: perf, profiling, profile, hotspot, hotspots, cache miss, IPC, false sharing, HITM, scaling, core count, thread scaling, bottleneck, slow code, CPU bound, why is this slow, where does time go, does not scale. When in doubt, invoke this skill -- better to use it unnecessarily than to miss a performance opportunity.

2026-05-22
phoronix-test-suite
Software Quality Assurance Analysts & Testers

Install, run, parse, and optimize benchmarks from the Phoronix Test Suite (PTS). Use this skill whenever the user mentions "phoronix", "pts/", or "phoronix-test-suite", or asks to run, measure, improve, or optimize a PTS test — e.g., "run pts/mt-dgemm", "optimize pts/compress-zstd", "what score does pts/x265 get". Trigger immediately on any `pts/<testname>` reference, even if the user doesn't explicitly say "phoronix". Also trigger when the user asks to find or edit the source code of a PTS test.

2026-05-19
#006
systemc-compiler
1 skills30744updated 2026-05-15
5.0% of creator
#007
linux-kernel-oops
1 skills113updated 2026-05-01
5.0% of creator
Showing 7 of 7 repositories
All repositories loaded