Token导航 LogoToken导航

Agent Skill · 待分类

domain-glossary(领域术语表)

domain-glossary 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

domain-glossary 是待分类类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在待分类类的 11,209 个 Skill 里排第 10,165。

总安装 212周安装 9GitHub Stars 6下载 74核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:domain-glossary(领域术语表)
来源仓库:https://github.com/kambleakash0/agent-skills
仓库路径:skills/domain-glossary
安装命令:
npx skills add https://github.com/kambleakash0/agent-skills --skill domain-glossary
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/kambleakash0/agent-skills --skill domain-glossary

这个 Skill 是做什么的

这个 Skill 的分类还没最终确定,用法以来源仓库的说明为准。

domain-glossary 将对话中的领域术语转化为统一的 Ubiquitous Language 文档。适用于消除“account”“user”“customer”等词汇歧义,建立共享语言。自动扫描术语、解析冲突并写入 DOMAIN_GLOSSARY.md 持续演进。支持多次调用以随对话深化术语定义与关系梳理。

建议团队定期回顾 glossary 确保所有成员使用一致术语。

来源仓库内路径:skills/domain-glossary

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/kambleakash0/agent-skills --skill domain-gloss…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

domain-glossary 怎么安装?

在终端执行 npx skills add https://github.com/kambleakash0/agent-skills --skill domain-glossary。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

domain-glossary 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

domain-glossary 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

domain-glossary 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

domain-glossary 用的人多吗?

公开数据是累计安装 212 次,近一周安装 9 次,下载 74 次,GitHub 6 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

domain-glossary 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理待分类类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

待分类类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
infsh-cli

infsh CLI · Codex、Claude

4,374,576382权限未标注未明确未收录
ai-video-generation

AI 视频生成 · Codex、Claude

4,313,376382调用外部服务未明确有提醒
lark-openapi-explorer

云雀 OpenAPI 浏览器 · Codex、Claude

2,064,1209,011需要联网未明确有提醒
lark-workflow-standup-report

Lark 工作流程站立报告 · Codex、Claude

2,041,6328,978需要联网未明确通过
use-my-browser

使用我的浏览器 · Codex、Claude

1,848,49140操作浏览器未明确未通过
domain-glossary

领域术语表 · 本页

2126只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Ubiquitous Language Glossary

This skill turns an ongoing conversation into a DDD-style ubiquitous language document. It scans for domain terms, resolves ambiguities, proposes canonical names, and writes a living glossary to DOMAIN_GLOSSARY.md in the working directory.

When to Use

Use this skill when:

  • You’re discussing a domain, feature, product, or system and want shared language.
  • You mention “ubiquitous language”, “domain model”, or “DDD”.
  • You keep tripping over overloaded terms (“account”, “user”, “customer”) and want them nailed down.

You can re-run this skill as the conversation evolves to keep the glossary up to date.

Process

  1. Scan the conversation and context

- Read the current conversation, plus any attached docs or PRDs, for domain-relevant nouns, verbs, and concepts. - Ignore generic technical terms (array, function, endpoint) unless they carry domain meaning here.

  1. Detect language problems Identify and note where:

- The same word is used for different concepts (ambiguity). - Different words are used for the same concept (synonyms). - Terms are vague, overloaded, or inconsistently applied.

  1. Propose a canonical glossary

- Choose one canonical term per concept and be opinionated about names. - For each term, write a tight, one‑sentence definition that says what it *is*, not how it’s implemented. - List “aliases to avoid” so everyone sees which terms should be retired in this context.

  1. Group terms into sections

- Group related terms under headings (e.g. “Order lifecycle”, “People”, “Billing”, “Content model”). - Each group gets its own Markdown table with columns: Term, Definition, Aliases to avoid. - If everything belongs to a single cohesive cluster, one table is fine—don’t force fake groupings.

  1. Describe relationships

- Add a “Relationships” section that describes how the key terms relate to each other in plain language. - Use bold term names and, where obvious, simple cardinalities (e.g. “An Order has many Line items”).

  1. Write an example dialogue

- Add a short example conversation (3–5 exchanges) between a developer and a domain expert. - Use the canonical terms consistently and show how they interact in a realistic scenario. - Use this dialogue to clarify boundaries between easily-confused terms.

  1. Write or update DOMAIN_GLOSSARY.md

- If the file does not exist, create it with the structure described above. - If it exists, read it first, merge in new understanding, and update it in place.

Re-running

When invoked again in the same repo or conversation:

  1. Read the existing DOMAIN_GLOSSARY.md.
  2. Merge in new terms introduced since the last run.
  3. Update definitions where understanding has clearly evolved.
  4. Mark changed entries with “(updated)” and new entries with “(new)”.
  5. Add any new ambiguities you’ve observed to “Flagged ambiguities”.
  6. Refresh the example dialogue so it reflects the latest terms and relationships.

Output format

DOMAIN_GLOSSARY.md should roughly follow this pattern (adapt as needed):

# Ubiquitous Language

## <Domain cluster 1>

| Term | Definition | Aliases to avoid |
|------|------------|------------------|
| **Order** | A customer's request to purchase one or more items | Purchase, transaction |
| **Invoice** | A request for payment sent to a customer after delivery | Bill, payment request |

## <Domain cluster 2>

| Term | Definition | Aliases to avoid |
|------|------------|------------------|
| **Customer** | A person or organization that places orders | Client, buyer, account |
| **User** | An authentication identity in the system | Login, account |

## Relationships

- An **Invoice** belongs to exactly one **Customer**.
- An **Order** produces one or more **Invoices**.

## Example dialogue

> **Dev:** "When a **Customer** places an **Order**, do we create the **Invoice** immediately?"
> **Domain expert:** "No — an **Invoice** is generated only once a **Shipment** is fulfilled."
> ...

## Flagged ambiguities

- "account" is being used to mean both **Customer** and **User**. Prefer **Customer** for the business entity and **User** for authentication.

(Use actual terms from the current domain, not these placeholders.)

Behavior and Rules

  1. Be opinionated. When multiple terms exist for the same concept, pick one canonical word and move others into “aliases to avoid”.
  2. Keep definitions tight. One sentence, focused on identity (“what it is”), not procedure (“what it does”).
  3. Only include domain terms. Skip generic infrastructure vocabulary unless it has a special meaning here.
  4. Call out conflicts. Ambiguous or overloaded terms go into “Flagged ambiguities” with a clear recommendation.
  5. Use the glossary going forward. After writing/updating the file, stick to the canonical terms in subsequent conversation.

平台分布

Codex

38.81%
按下载量换算29

Claude

27.38%
按下载量换算20

Cursor

17.27%
按下载量换算13

Gemini CLI

10.2%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills