OpenAgentSkill
GitHub200+

Skill 审计报告

quark-torch-llm-ptq 审计报告.

Runs an end-to-end AMD Quark post-training quantization workflow for PyTorch / Hugging Face LLMs: inspect a Hub or local model, choose a quantization plan, create reproducible artifacts, request execution approval, and produce a quantized model. Applies to Llama, Qwen, Mistral, and similar transformer LLM requests involving FP8, INT4, or another Quark scheme. Does not handle .onnx model inputs or ONNX PTQ.

实验性 · 审查需审查生成于 2026年10月14日启发式元数据审计
77
审计
73
信任
67
质量
73
安全性
100
维护
92
安装

OpenAgentSkill 信任评分

73
强候选

OpenAgentSkill 信任评分

Trust Score 帮助 Agent 在安装前判断一个 Skill 是否足以进入候选清单。

GitHub 采用度

信息

62

395 个 GitHub Stars

Star/Fork 活跃度

警告

57

395 个 Star，39 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

100

距上次推送 7 天

许可证清晰度

通过

86

MIT

README/SKILL.md 完整度

通过

86

元数据包含足够的用法与工作流上下文

依赖与运行时风险

警告

54

command execution surface, external package install surface

安装可用性

通过

92

npx skills add amd/skills --skill quark-torch-llm-ptq

安装命令安全性

通过

92

标准软件包或运行时安装路径

权限范围

失败

36

shell or command execution, filesystem or document access

仓库证据

通过

86

https://github.com/amd/skills/tree/main/skills/quark-torch-llm-ptq

审查状态

警告

46

缺少 AI 审查批准

Agent 验证结果

信息

54

暂未有 Agent 结果数据

检查项

安装与采用审查

6 通过 · 16 需审查

安装路径

92

通过

npx skills add amd/skills --skill quark-torch-llm-ptq

仓库

88

通过

https://github.com/amd/skills/tree/main/skills/quark-torch-llm-ptq

许可证

86

通过

MIT

维护

100

通过

距上次推送 7 天

AI 审查

55

检查

Review approval is missing

README/SKILL.md 完整度

86

通过

Usable description available

依赖风险

54

修复

command execution surface, external package install surface

安装命令安全性

92

通过

标准软件包或运行时安装路径

权限范围

36

修复

shell or command execution, filesystem or document access

Star/Fork 活跃度

57

修复

395 个 Star，39 个 Fork; 当前元数据中没有议题活跃度信息

采用度

68

信息

395 个 GitHub Stars

Financial decision safety

58

检查

Research-only use: do not treat output as financial advice or execute a position without human approval.

警告

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • Financial research output is not financial advice; require human review before any live investment decision
  • 缺少 AI 审查批准
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Stars/forks activity: 395 stars, 39 forks; issue activity unavailable in current metadata
  • Dependency/runtime risk: command execution surface, external package install surface
  • Permission surface: shell or command execution, filesystem or document access
  • Review status: AI review approval is missing

方法

本报告综合公开元数据、AI 审查输出、仓库活跃度、安装就绪度、OpenAgentSkill 事件、质量评分、信任检查和 Agent 安全门槛；它不是完整的源代码安全审计。

对比相近选项

下一步可审计的相关 Skill

full-output-enforcement

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

96K Stars · 审计报告

distributed-llm-pretraining-torchtitan

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

13K Stars · 审计报告

peft-fine-tuning

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

13K Stars · 审计报告