跳到技能内容
词映 AI导航
发现工具选型指南Skills 技能AI 快讯AI图片AI视频AI文档AI办公AI助手AI搜索AI编程AI音频AI设计AI智能体模型与开发AI学习模型评测AI提示词内容检测AI金融AI 3D扫描与识别其他工具跨境电商 AI
词映 AI导航
工具库Skills 技能
我的收藏
词映 AI导航
发现工具选型指南Skills 技能AI 快讯AI图片AI视频AI文档AI办公AI助手AI搜索AI编程AI音频AI设计AI智能体模型与开发AI学习模型评测AI提示词内容检测AI金融AI 3D扫描与识别其他工具跨境电商 AI
Skills directory/brianwestphal/gitgist/check-requirements-against-code

Requirements Against Code Skill for ChatGPT: Check CLI, Behavior and Documentation Gaps

Compare supplied requirements with code, CLI help, scripts, and summaries. Report implementation, divergences, and evidence gaps using traceable IDs.

中文

Install in ChatGPT

Requires a ChatGPT workspace where you can create skills. This is a text adaptation of the pinned GitHub source.

  1. Review the inputs and outputs in the pinned .claude/skills/check-requirements-against-code/SKILL.md.
  2. In ChatGPT, open Plugins, Skills, Create, and Create with editor.
  3. Write the skill rules using the workflow described here. Provide requirement IDs, code excerpts, CLI help, summaries, and actual test results.
  4. Save the skill and check the fictional example in a new chat.

Example task

Fictional FR-7 says --format json is available, but help lists text only and no test output is supplied. Another implemented flag lacks docs. Draft findings.

What to check

Record the FR-7 discrepancy and the undocumented option separately with locations and versions. Keep runtime behavior unverified and request a matching check.

Original SKILL.md on GitHub · Updated 2026-11-13

Frequently asked question

Does inconsistent documentation prove the implementation is broken?

Confirm the help source and code version. Record the static difference and use relevant runtime evidence to establish behavior.

Browse ChatGPT skills in the Chinese directory
词映 AI 导航Skills 技能
工具分类全部工具已本地化技能选型指南AI 快讯