← 返回 Skills 市场

Musify MooreThreads

Name: Musify MooreThreads
Author: dongyang-mt

作者 dongyang-mt · GitHub ↗ · v0.1.0

cross-platform ✓ 安全检测通过

290

总下载

当前安装

版本数

在 OpenClaw 中安装

/install musify

功能描述

Convert CUDA code to MUSA (Moore Threads GPU) using the musify tool. Use when migrating CUDA codebases to MUSA platform, converting CUDA kernels/APIs to MUSA...

使用说明 (SKILL.md)

Musify - CUDA to MUSA Code Conversion

Musify converts CUDA code to MUSA (Moore Threads GPU architecture) using text-based API mapping.

Installation

# Install dependencies
pip install ahocorapy

# musify-text should be available in MUSA toolkit

Basic Usage

# Convert files in-place (CUDA -> MUSA)
musify-text --inplace -- file1.cu file2.cpp

# Convert and create new files (default)
musify-text --create -- a.cu b.cpp

# Print to stdout
musify-text -t -- file.cu

Batch Conversion

# Find and convert all CUDA/C++ files in directory
musify-text --inplace -- $(find /path/to/project -name '*.cu' -o -name '*.cuh' -o -name '*.cpp' -o -name '*.h')

# Using ripgrep (recommended)
musify-text --inplace -- $(rg --files -g '*.cu' -g '*.cuh' -g '*.cpp' -g '*.h' /path/to/project)

Options

Option	Description
`-t, --terminal`	Print output to stdout
`-c, --create`	Create new files with converted code (default)
`-i, --inplace`	Modify files in-place
`-d {c2m,m2c}`	Conversion direction: c2m (CUDA→MUSA, default), m2c (MUSA→CUDA)
`-m \x3Cfile.json>`	Custom API mapping file (can specify multiple)
`--clear-mapping`	Clear default mapping, use only custom mappings
`-l {DEBUG,INFO,WARNING}`	Log level

Exclusion Markers

Prevent specific code sections from being converted:

// MUSIFY_EXCL_LINE - Exclude this line
char *str = "cudaMalloc"; // MUSIFY_EXCL_LINE

// MUSIFY_EXCL_START - Start exclusion block
char *apis[] = {
    "cudaInit",
    "cudaFree"
};
// MUSIFY_EXCL_STOP - End exclusion block

Common CUDA → MUSA Mappings

CUDA	MUSA
`cuda` prefix	`musa` prefix
`CUDA`	`MUSA`
`cu` prefix (driver API)	`mu` prefix
`__cuda`	`__musa`
`cudaMalloc`	`musaMalloc`
`cudaFree`	`musaFree`
`cudaMemcpy`	`musaMemcpy`
`cudaLaunchKernel`	`musaLaunchKernel`
`__global__`	`__global__` (unchanged)
`__device__`	`__device__` (unchanged)
`__shared__`	`__shared__` (unchanged)

Workflow

Backup code before conversion
Run musify on target files
Review changes - text-based conversion may need manual fixes
Compile with MUSA compiler (mcc) to verify
Test on MUSA device

References

安全使用建议

This SKILL.md is coherent with a code-migration tool, but take these precautions before running it: 1) Do a full backup or ensure version control before using --inplace; prefer --create or printing to stdout for an initial pass. 2) Verify the origin of musify-text and the ahocorapy package (install from official MooreThreads releases or the project's GitHub, not a similarly named pip package). 3) Test conversion on a small subset of files and run the MUSA compiler/tests before committing changes. 4) Avoid running automated bulk commands (find/rg piped into --inplace) until you're confident the mappings and exclusion markers behave as expected.

功能分析

Type: OpenClaw Skill Name: musify Version: 0.1.0 The 'musify' skill is a legitimate tool bundle designed to assist in migrating CUDA code to the Moore Threads MUSA platform. The documentation in SKILL.md provides standard instructions for using the 'musify-text' utility, including installation of the 'ahocorapy' dependency and examples of batch processing using common shell commands like 'find' and 'rg'. No malicious patterns, data exfiltration, or prompt injection attempts were identified.

能力评估

✓ Purpose & Capability

Name/description match the instructions: the SKILL.md documents running a musify-text conversion tool over CUDA source files and contains expected options and mappings. There are no unrelated credentials, binaries, or config paths requested.

ℹ Instruction Scope

Instructions remain within the conversion task (running musify-text, finding source files, options, exclusion markers). They explicitly include in-place modification operations and batch file selection (find/rg), which is appropriate for a migration tool but increases risk to source if run without backups or vetting. The doc advises backing up code; it does not instruct reading or exfiltrating unrelated system files or credentials.

ℹ Install Mechanism

There is no automated install spec in the skill (instruction-only), which limits what is written to disk. The doc suggests pip install ahocorapy and that musify-text should come from the MUSA toolkit; pip-installing introduces normal package-source risk (typo-squatting or malicious package) but that is expected for a tool relying on Python packages.

✓ Credentials

No environment variables, credentials, or config paths are requested. The declared requirements map cleanly to the tool's stated functionality.

✓ Persistence & Privilege

Skill is not marked always:true and is user-invocable only. It does not request persistent platform-wide access or modify other skills' configurations.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install musify
安装完成后，直接呼叫该 Skill 的名称或使用 /musify 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v0.1.0

- Initial release of musify skill for CUDA to MUSA code conversion. - Enables batch conversion of CUDA (.cu, .cuh) and C++ files to Moore Threads MUSA equivalents using text-based API mapping. - Supports in-place conversion, new file creation, and printing to stdout. - Offers flexible exclusion markers to prevent conversion of specific code regions. - Includes basic mapping of common CUDA APIs/prefixes to MUSA, and supports custom mapping files. - Designed to streamline migration of CUDA codebases to the MUSA platform.

元数据

Slug musify

版本 0.1.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题