OpenAgentSkill
GitHub200+

Skill 审计报告

ab-testing 审计报告.

Use when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go significant. NOT recurring metric tracking (that is `analytics`), NOT north-star/KPI trees (that is `kpi-framework`), NOT projecting metrics forward (that is `forecasting`).

已审查 · 审查需审查生成于 2026年10月12日启发式元数据审计
78
审计
75
信任
66
质量
84
安全性
88
维护
92
安装

OpenAgentSkill 信任评分

75
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

警告

48

66 个 GitHub Stars

Star/Fork 活跃度

警告

43

66 个 Star，0 个 Fork; 当前元数据中没有议题活跃度信息

近期维护

通过

88

距上次推送 1 个月

许可证清晰度

通过

86

MIT

README/SKILL.md 完整度

通过

94

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

通过

90

公开元数据中未发现主要依赖风险提示

安装可用性

通过

92

npx skills add ericrisco/rsc-harness --skill ab-testing

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

通过

100

公开元数据中未发现高风险权限范围

仓库证据

通过

86

https://github.com/ericrisco/rsc-harness/tree/main/skills/ab-testing

审查状态

信息

66

可用 AI 审查数据

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

8 通过 · 9 需审查

安装路径

92

通过

npx skills add ericrisco/rsc-harness --skill ab-testing

仓库

88

通过

https://github.com/ericrisco/rsc-harness/tree/main/skills/ab-testing

许可证

86

通过

MIT

维护

88

通过

距上次推送 1 个月

AI 审查

55

检查

The verify.sh script executes arbitrary Python files discovered in the project. While it is a local, read-only tool, it could be a risk if run on untrusted code. This is not a critical issue for the skill itself, but it is worth noting.

README/SKILL.md 完整度

94

通过

Usable description available

依赖风险

90

通过

公开元数据中未发现主要依赖风险提示

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

100

通过

公开元数据中未发现高风险权限范围

Star/Fork 活跃度

43

修复

66 个 Star，0 个 Fork; 当前元数据中没有议题活跃度信息

采用度

68

信息

66 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

  • Financial research output is not financial advice; require human review before any live investment decision
  • The verify.sh script executes arbitrary Python files discovered in the project. While it is a local, read-only tool, it could be a risk if run on untrusted code. This is not a critical issue for the skill itself, but it is worth noting.
  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • GitHub adoption: 66 GitHub stars
  • Stars/forks activity: 66 stars, 0 forks; issue activity unavailable in current metadata

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

Frontend Design

Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.

180K Stars · 审计报告

Taste Skill: Anti-Slop Frontend

Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.

94K Stars · 审计报告

Canvas Design

Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

180K Stars · 审计报告