菜单
Conducts and records a verifiable GPT-RAG UI architectural decision. Use when a choice alters boundaries, contracts, identity, sessions, persistence, accessibility, deployment, or operation with meaningful reversal cost.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Azure/gpt-rag-ui --skill architecture-decision命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | architecture-decision |
| description | Conducts and records a verifiable GPT-RAG UI architectural decision. Use when a choice alters boundaries, contracts, identity, sessions, persistence, accessibility, deployment, or operation with meaningful reversal cost. |
engineering-principles references.docs/adr/ using
the ADR template.Do not turn a tool or framework preference into an architectural requirement. When evidence is missing, record a time-bounded investigation and its decision criterion instead of guessing.
Prepare and reconcile gpt-rag-ui releases. Use for release preparation, release branches, semantic versioning, VERSION or changelog updates, release notes, tags, GitHub Releases, packages, container images, or deployment publication; require explicit human approval before publishing anything.
Prepares a verifiable GPT-RAG UI release. Use for release branches, VERSION, changelog entries, tags, release notes, and compatibility evidence; never publish without explicit human approval.
Keeps GPT-RAG UI developer, user, and operator documentation aligned with shipped behavior. Use for features, configuration keys, security policy, deployment parameters, defaults, UI behavior, or breaking changes.
基于 SOC 职业分类
