← Back to Skills Marketplace
254
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install musa-torch-coding
Description
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
Usage Guidance
This skill's metadata and description (OpenAI Whisper transcription, OPENAI_API_KEY required) do not match the actual content (MUSA/torch guidance, CUDA->MUSA converter, YOLO template). Before installing or supplying secrets: 1) Do not provide your OPENAI_API_KEY — the code does not use it. 2) Confirm with the publisher what the skill is supposed to do; the mismatch may be a packaging error or mislabeling. 3) Inspect the included scripts locally (scripts/cuda_to_musa.py, assets/yolo8n_template.py, references/reference.md) — they appear to be benign conversion and template code with no network/exfiltration, but they do advise running build/install commands and privileged operations. 4) Do not run sudo commands (e.g., sudo usermod ...) or build/install steps until you trust the source and understand the effect on your system. 5) If you wanted an audio transcription skill, look for a different skill whose files, instructions, and required env vars actually reference the OpenAI transcription API.
Capability Analysis
Type: OpenClaw Skill
Name: musa-torch-coding
Version: 1.0.0
The skill bundle contains a significant discrepancy in `SKILL.md`, where the metadata and description claim the skill is for OpenAI Whisper audio transcription and requires an `OPENAI_API_KEY`, while the actual instructions and code focus entirely on Moore Threads MUSA GPU programming. Requesting sensitive credentials that are unrelated to the functional content is a red flag for potential credential harvesting or poor supply chain hygiene. The provided Python scripts, such as `scripts/cuda_to_musa.py` and `assets/yolo8n_template.py`, appear to be legitimate utility tools for MUSA development.
Capability Assessment
Purpose & Capability
Name/description claim: 'Transcribe audio via OpenAI Audio Transcriptions API (Whisper)'. Actual files and SKILL.md: MUSA (Moore Threads) torch guidance, CUDA-to-MUSA converter, YOLO template, and extensive environment/build instructions. The declared primary credential (OPENAI_API_KEY) and required binary (curl) are unrelated to the skill's true content.
Instruction Scope
The SKILL.md instructs system-level checks and operations appropriate for GPU setup (checking musaInfo, /usr/local/musa, modifying conda envs, build scripts). It also suggests privileged actions (e.g., 'sudo usermod -aG render $(whoami)', editing LD_LIBRARY_PATH, running build.sh). These instructions are coherent with MUSA GPU setup but entirely outside the advertised transcription purpose, and they can require elevated privileges on the host.
Install Mechanism
No install spec is provided (instruction-only), so nothing is automatically downloaded or executed during install. The skill includes code files (converter and templates) that will be present on disk, but there are no external URLs, archive extracts, or package installs declared.
Credentials
requires.env declares OPENAI_API_KEY as required and primaryEnv, but neither SKILL.md nor the included Python files reference OpenAI APIs or use that key. The SKILL.md also lists MUSA-specific environment variables (MUSA_VISIBLE_DEVICES, etc.) in prose but does not declare them as required. The declared required binary 'curl' is not used anywhere in the repository. Requesting an unrelated secret (OPENAI_API_KEY) is disproportionate and suspicious.
Persistence & Privilege
The skill does not set always:true and does not claim to modify other skills or system-wide agent settings. However, the runtime instructions encourage privileged system changes (adding user to 'render' group, running build/install scripts) which could have security implications if executed without review. The skill itself does not request persistent elevated agent privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install musa-torch-coding - After installation, invoke the skill by name or use
/musa-torch-coding - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
musa-torch-coding 1.0.0 – Initial release
- Provides a guide for generating PyTorch code compatible with Moore Threads (MUSA) GPUs using torch_musa.
- Documents key differences between CUDA and MUSA APIs.
- Outlines environment setup, detection, and usage of pre-configured conda environments for MUSA.
- Details code generation rules, including device selection and distributed training with mccl backend.
- Includes model templates, common code patterns, and troubleshooting tips specific to MUSA environments.
Metadata
Frequently Asked Questions
What is musa-torch-coding?
Transcribe audio via OpenAI Audio Transcriptions API (Whisper). It is an AI Agent Skill for Claude Code / OpenClaw, with 254 downloads so far.
How do I install musa-torch-coding?
Run "/install musa-torch-coding" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is musa-torch-coding free?
Yes, musa-torch-coding is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does musa-torch-coding support?
musa-torch-coding is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created musa-torch-coding?
It is built and maintained by peli (@lipeidcc); the current version is v1.0.0.
More Skills