OpenAgentSkill
GitHub200+

Skill 审计报告

accuracy-safe-quantization 审计报告.

Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.

已阻止 · 阻止高风险生成于 2026年10月13日启发式元数据审计
76
审计
70
信任
68
质量
69
安全性
100
维护
92
安装

OpenAgentSkill 信任评分

70
人工审查

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

459 个 GitHub Stars

Star/Fork 活跃度

信息

62

459 个 Star，122 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 3 天

许可证清晰度

通过

86

Apache-2.0

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

失败

36

command execution surface, credential or environment access

安装可用性

通过

92

npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization

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

22

secrets or environment access, shell or command execution

仓库证据

通过

86

https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization

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 · 14 需审查

安装路径

92

通过

npx skills add google-ai-edge/litert-samples --skill accuracy-safe-quantization

仓库

88

通过

https://github.com/google-ai-edge/litert-samples/tree/main/skills/accuracy-safe-quantization

许可证

86

通过

Apache-2.0

维护

100

通过

距上次推送 3 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

36

修复

command execution surface, credential or environment access

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

22

修复

secrets or environment access, shell or command execution

Star/Fork 活跃度

62

检查

459 个 Star，122 个 Fork; 当前元数据中没有议题活跃度信息

采用度

68

信息

459 个 GitHub Stars

警告

  • Dependency or permission surface needs review
  • Permission surface may require sandboxing
  • Potential broker, wallet, exchange, or real-money execution surface; sandbox and explicit approval are required
  • 缺少 AI 审查批准
  • This skill may touch real-money trading, broker, wallet, or exchange operations; use only in a sandbox with explicit approval.
  • Quality score needs review
  • Permission surface needs review: secrets or environment access, shell or command execution
  • Dependency/runtime risk: command execution surface, credential or environment access
  • Permission surface: secrets or environment access, shell or command execution
  • 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

weather

Current weather and forecasts with web_fetch, falling back to wttr.in curl for locations, rain, temperature, travel planning.

391K Stars · 审计报告

mcporter

List, configure, authenticate, call, and inspect MCP servers/tools with mcporter over HTTP or stdio.

391K Stars · 审计报告

release-openspec

Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is complete, what the next release step is, or to continue a release paused for human approval.

71K Stars · 审计报告