跳到正文
TakoAPI
返回技能列表

hollow-validation-checker

由 andyxinweiminicloud 提供

Coding Agents & IDEs
349下载量由 clawskills.sh 提供
1浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Helps detect hollow validation in AI agent skills — identifies fake tests that always pass without actually.

描述

该技能的功能

Analyzes validation commands and test code in AI agent skills to identify patterns that fake quality signals. Detects exit code gaming, echo-only commands, tautological assertions, and commented-out tests. Rates each validation as SUBSTANTIVE, WEAK, or HOLLOW.

Manual code review can miss sophisticated test theater where real frameworks are invoked but assertions test trivially true conditions, which this tool flags through static analysis of assertion content.

何时使用

  • Auditing agent marketplace skills before adding them to a production pipeline
  • Reviewing community-submitted skills before merging a PR
  • Comparing validation quality across a batch of published skills
  • Flagging skills that claim test coverage but run no real assertions
  • Deciding whether to trust a skill's published validation rating

示例工作流

输入

User asks: Check this Capsule JSON — its validation field claims 14 tests passed

智能体
  1. 1

    Parse the validation field from the provided Capsule JSON

  2. 2

    Break down each command in the validation chain

  3. 3

    Check each command for real assertion statements vs hardcoded success strings

  4. 4

    Inventory real assertions vs hollow outputs

  5. 5

    Generate a quality rating with evidence

输出

HOLLOW rating: 0 real assertions found, 2 hollow outputs (hardcoded print statement claiming 14 tests, static echo). Recommendation to treat as unvalidated.

安装

clawhub install andyxinweiminicloud/hollow-validation-checker

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接