Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

write-ac写交流

Agent Skill

write-ac 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。

总安装

247

周安装

10

GitHub Stars

公开资料未说明

下载量

78
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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:write-ac(写交流)
来源仓库:https://github.com/andresnator/agents-orchestrator
仓库路径:skills/write-ac
安装命令:
npx skills add https://github.com/andresnator/agents-orchestrator --skill write-ac
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/andresnator/agents-orchestrator --skill write-ac

简介

该技能用于处理 GitHub 仓库与协作信息,支持交流记录整理。

  • 适用于 Codex、Claude、Cursor、Gemini CLI 中围绕代码变更与 Issue 管理的场景。
  • 可协助跟踪 Pull Request 与协作事项。
  • 通过 GitHub 仓库安装,注意权限与文件操作风险。
  • 建议结合原始 README 确认具体功能与使用限制。

SKILL.md

Building Acceptance Criteria

Generate acceptance criteria for Jira tickets. Output in English, Jira Markdown, inside a code block.

Step 1 — Gather context

Before writing, verify you have the following. If any is missing, ask for it:

  • What the feature or change does (business goal, not implementation detail)
  • Who performs the action (user role or system actor)
  • What the observable outcome is from a user/business perspective
  • Scope restrictions if applicable (e.g., specific environments, feed-handlers, devices)

Ask only what is missing. Do not ask for things already provided.

Step 2 — Write the ACs

Apply these quality rules to every criterion:

  • Binary: Each AC must have a clear pass or fail. Avoid vague outcomes like "works correctly" or "is shown properly".
  • Testable: The outcome must be verifiable through a concrete observable action — not inferred from code behaviour.
  • Implementation-independent: Describe *what* the system does, not *how* it does it internally. Avoid referencing internal flags, class names, or code constructs unless they are part of the user-visible contract.
  • Business language: Write so that any stakeholder (product owner, QA, business analyst) can understand it without technical knowledge.
  • Real scenario: Ground each AC in an authentic business flow (e.g., "a user completes a purchase"), not an abstract system state.

Output Format

Output the criteria in a single code block using this template:

h2. Acceptance Criteria

*AC.1* → Given [initial context / precondition], When [user or system action], Then [observable outcome].

*AC.2* → Given [initial context / precondition], When [user or system action], Then [observable outcome].

Output Rules

  • Each AC must be self-contained and testable.
  • Use the separator between the AC identifier and the Gherkin sentence.
  • Keep each criterion to a single sentence. No bullet sub-lists inside an AC.
  • If scope or feed-handlers apply, append them in parentheses at the end: (DC, LF, BRU).
  • Number sequentially starting at AC.1.
  • No filler text. No preamble outside the code block.

Example Output

h2. Acceptance Criteria

*AC.1* → Given a confirmed event total has been received for the current period, When the system processes the settlement, Then all affected markets are settled and their status is visible to the user as "Settled". (DC, LF, BRU feed-handlers.)

*AC.2* → Given an unconfirmed event total has been received, When the system processes it, Then no markets are settled and their status remains unchanged. (DC, LF, BRU feed-handlers.)

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

33.84%
按下载量换算26

Claude

30.6%
按下载量换算24

Cursor

19.3%
按下载量换算15

Gemini CLI

8.42%
按下载量换算7

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills