Menu
SkillsMP has collected 15 skills from qualcomm/EasyWoS. Open a skill to review its source and details.
Showing 15 of 15 collected skills.
Top-level loop-engineering orchestrator for x64-to-ARM64 porting of any open source project. Drives the whole pipeline end to end — scan, OpenSpec propose, easywos-spec task generation, OpenSpec apply (per-kernel port + verify/retry), wiring the ported…
Bridges EasyWoS scan output with OpenSpec task generation for x64-to-ARM64 porting. MUST be invoked when OpenSpec generates tasks.md for changes involving porting_items. Parses EasyWoS YAML, runs hybrid spec matching (script initial screening + LLM semantic…
Fallback skill for porting x64 code to ARM64 when no specific spec matches. Provides mandatory architectural constraints that ALL ARM64 migrations must respect regardless of code pattern — covering both hand-written assembly and C/intrinsics output. Use when…
Convert ARM64 NEON inline assembly written in Clang/GCC-style `asm volatile(...)` blocks into maintainable C/C++ intrinsics, and must build a Verification project that compares the original asm against the translated intrinsics for semantic equivalence. Use…
Convert x64 assembly to AArch64 arm64 — both inline asm (asm volatile / __asm__) and standalone MASM .asm files (PROC/ENDP, equ, macro/endm) translated to GAS .S form. Use when porting x64-specific asm to arm64, adding arm64 support alongside an existing x64…
Expert skilltree layer-1 dispatcher. Receives porting task commands from tasks.md, parses arguments, loads porting_item data and spec descriptions, then routes to the appropriate leaf skill for actual migration execution. Invoked as: /dispatcher-skill…
Detect a project's build system and modify its build files to add a Windows ARM64 build configuration. Use when the user wants to "enable ARM64", "add ARM64 support", "support Windows on ARM"/"Windows on ARM64"/"WoA", "build for ARM64", "make project ARM64…
Expert guidance for porting x86/x64 SSE/AVX vectorized C++ to ARM64 NEON, grounded in the Microsoft STL's two real backends (vector_algorithms.cpp). Use this skill when: translating __m128i/__m256i intrinsics to NEON (uint8x16_t/uint16x8_t/etc.), replacing…
Creates new leaf skills for the expert skilltree, or adds missing spec.yaml files to existing leaf skills. Enforces the standard directory structure (SKILL.md + references/specs/*.md + *.yaml) and guides LLM to auto-generate structured spec.yaml files from…
Run a target program under a CPU-sampling profiler and produce an ETL trace file for later performance analysis. Keywords - collect ETL, profile a program, generate etl, capture CPU trace, record ETL.
Performance bottleneck root-cause analysis tool. Parses SpeedScope JSON flame graphs, traces back the call chain to the true root-cause module (not just the most expensive leaf), then combines that with user-provided source paths to pinpoint hotspots, and…
Analyze per-process CPU usage from ETL log files and export SpeedScope flame graphs. Keywords - ETL, flame graph, CPU usage, speedscope.
Port x86 SSE/AVX intrinsics to ARM NEON, including CRC32 PCLMULQDQ → PMULL. Use when translating x86/x64 intrinsic code to NEON equivalents, adding ARM paths alongside existing x86 code, writing ARM NEON compute kernels from SSE/AVX specifications, or porting…
Generate an x64-to-ARM64 porting report in YAML format. Triggers when the user asks to generate/create/write an ARM64 porting report or migration analysis. Trigger phrases include: generate arm64 porting report, create porting report, write porting report,…
Analyze ARM64EC JIT executable memory allocation bugs where JIT-generated ARM64 or ARM64EC code is allocated with VirtualAlloc/VirtualAllocEx and then misclassified or treated as X64 code. Use this skill whenever the user mentions ARM64EC, JIT code pages,…