技能 webask-benchmark

📦

webask-benchmark

Name: webask-benchmark
Author: webaskio

内容修订 r1 安全 📁 文件系统访问⚙️ 外部命令

Compare WebAsk Survey Results

Survey scores can mislead when questionnaire changes, sample sizes, and seasonal differences are ignored. This skill guides WebAsk comparisons using version history, response distributions, and shared survey metrics.

支持: Claude Codex Code(CC)

🥉 77 青铜

使用我的智能体安装

将此请求复制给你的智能体，其中包含权威 Skill 页面和清单。

智能体请求

Review the Skillstore skill "webask-benchmark" from https://skillstore.io/skills/webaskio-webask-benchmark.md and its manifest at https://skillstore.io/api/skills/webaskio-webask-benchmark/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

你的智能体仍应展示其计划，并按安全策略请求必要确认。

Agent 可读资源

当 AI Agent、爬虫或脚本需要干净上下文，而不是读取完整页面时，请使用这些链接。

Markdown 详情 GET /skills/webaskio-webask-benchmark.md 已签名 manifest GET /api/skills/webaskio-webask-benchmark/manifest 已签名 lockfile GET /api/skills/webaskio-webask-benchmark/lockfile

测试它

正在使用“webask-benchmark”。 Illustrative comparison: spring averaged 4.0 from 286 responses; autumn averaged 4.3 from 318 responses. The questionnaire was unchanged.

预期结果:

The average increased by 0.3 points, from 4.0 to 4.3.
Spring had 286 responses; autumn had 318.
No questionnaire changes were reported, but seasonal and audience differences still need consideration.
These averages and counts alone do not establish statistical significance or explain the cause.

正在使用“webask-benchmark”。 Illustrative comparison: two periods use different wording and response options for the satisfaction question.

预期结果:

The satisfaction answers are not directly comparable because the question and response options changed.
Do not present the score difference as a satisfaction trend.
Review shared operational metrics separately, with clear comparability caveats.

安全审计

安全

v1 • 2026/9/29 打开版本化报告

All four static findings are false positives: documentation navigation links and Markdown formatting around MCP tool names. No evidence found of prompt injection, unauthorized data transfer, or executable shell commands in the reviewed files. The skill describes survey analysis through external MCP tools; their implementations were not included in this review.

已扫描文件

136

分析行数

复核项

已忽略误报

风险因素

📁 文件系统访问 (1)

README.md:1

⚙️ 外部命令 (3)

SKILL.md:23 SKILL.md:25 SKILL.md:27

最新一次完成的静态与语义审计未检测到已确认的安全发现。这并不能证明该 Skill 没有副作用。

审计者: codex

分享与引用此报告

分享版本化评估报告、中性徽章、嵌入卡片和引用。Skillstore 只报告证据，不判断该 Skill 是否安全。

打开版本化报告

复制报告链接

https://skillstore.io/skills/webaskio-webask-benchmark/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/webaskio-webask-benchmark/security.svg)](https://skillstore.io/skills/webaskio-webask-benchmark?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/webaskio-webask-benchmark?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/webaskio-webask-benchmark/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/webaskio-webask-benchmark.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

学术引用 (APA · BibTeX · CFF)

APA 引用

webaskio. (2026). webask-benchmark security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/webaskio-webask-benchmark/audits/1

BibTeX 引用

@techreport{webaskio-webaskio-webask-benchmark-2026,
  author = {webaskio},
  title = {webask-benchmark security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/webaskio-webask-benchmark/audits/1},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "webask-benchmark security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "webaskio"
date-released: "2026-09-29"
url: "https://skillstore.io/skills/webaskio-webask-benchmark/audits/1"
identifiers:
  - type: other
    value: "skillstore:webaskio-webask-benchmark:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore 评分

评分依据证据置信度: 中

架构

可维护性

内容

社区

规范符合性

你能构建什么

Review Customer Satisfaction Changes

Compare repeated survey periods to identify rating and distribution changes while checking questionnaire consistency.

Compare Survey Completion

Compare completion rates and completion times across account surveys without treating answers to different questions as equivalent.

Assess Feedback After a Release

Compare feedback before and after a release while distinguishing observed changes from unproven explanations.

试试这些提示

Compare Two Survey Periods

Compare [survey] during [period A] and [period B]. Check questionnaire versions and report average ratings, changes, and response counts.

Compare Completion Across Surveys

Compare completion rates and completion times for [survey A] and [survey B]. Use only shared metrics and explain any comparability limits.

Investigate Distribution Changes

Compare [survey] across [period A] and [period B]. Check version history, then examine answer distributions, average scores, and sample sizes. Label hypotheses clearly.

Evaluate Comparison Reliability

Evaluate whether [survey] results from [period A] and [period B] support a reliable comparison. Check questionnaire changes, period lengths, seasonality, and sample sizes. Separate observed differences from unsupported significance or causal claims.

最佳实践

Check questionnaire version history before interpreting changes between survey periods.
Use comparable period lengths and consider seasonal or audience differences.
Report distributions and sample sizes alongside averages, and label explanations that remain hypotheses.

避免

Treating answers to different questions as directly comparable.
Presenting small score differences as reliable improvement without sufficient evidence.
Interpreting higher response volume as proof of better product quality.

常见问题

What does this skill compare?

It compares one WebAsk survey across periods or shared operational metrics across different surveys in an account.

Which tools are required?

It depends on get_quiz_list, get_quiz_report, get_quiz_summary, and get_quiz_versions through MCP.

Can it compare surveys with different questions?

It can compare shared metrics such as completion rates and completion times. Answers to different questions are not directly comparable.

Does it provide a formal statistical significance test?

No statistical test is implemented or specified. The instructions call for sample-size caution and an assessment of whether differences are meaningful.

Does it modify surveys or recommend paid upgrades?

The documented workflow uses retrieval tools. It instructs the assistant to report account limits and stop without recommending payment or plan changes.

Which language does it use for responses?

The source instructions are in Russian, but they direct the assistant to respond in the language used by the requester.