pr-description

A guide for writing Pull Request descriptions, which explain proposed code changes before teammates review them.

In plain words
What is it for?
Use it when opening or updating a Pull Request, linking it to an issue, describing breaking changes, or documenting how the change was tested.
Why use it?
It gives reviewers the context, reason, risks, and verification steps they need without forcing them to reconstruct the story from the code.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/wade-devcode/awesome-coding-skills-cn/pr-description
Any agent
npx skills add Wade-DevCode/awesome-coding-skills-cn --skill pr-description
Clone the repo
git clone --depth 1 https://github.com/Wade-DevCode/awesome-coding-skills-cn

Made for: Claude Code, Codex.

Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.02051
Opus 5 $0.00010 $0.01026
Sonnet 5 $0.00004 $0.00410
Haiku 4.5 $0.00002 $0.00205

Measured 2d ago against content hash 6aebd2692b27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pr-description scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/pr-description/SKILL.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR 描述

何时用

  • 创建 Pull Request 之前,需要填写描述。
  • 更新已有 PR,需要补充说明测试方法或设计变更。
  • 接到 reviewer 反馈"看不懂这个 PR 在做什么"时,说明描述不够。
  • AI 辅助完成了实现,需要人工补充上下文和验证步骤。

核心规则

1. 讲清"做了什么、为什么、怎么验证",不让 reviewer 猜

规则: PR 描述必须包含三部分:改了什么(变更摘要)、为什么改(背景/动机)、怎么验证(测试方法)——缺一不可。

为什么: AI 辅助写代码时,描述最常见的问题是只写"做了什么"而完全不写"为什么"和"怎么验证"。reviewer 看到一堆代码改动不知道背景是什么、这个方案是否是最优选择,也不知道怎么本地复现来验证。结果要么盲目通过,要么来回追问浪费时间。典型事故:PR 描述写"修复 bug",reviewer 花 20 分钟读代码才弄清楚是哪个 bug、怎么触发、为什么这样修。

怎么做:

  • 用固定结构写描述:背景→改动摘要→验证步骤,三段清晰分隔。
  • 背景可以一两句话说清楚:是 issue 触发、是需求变更、还是性能优化?
  • 验证步骤要具体到"执行什么命令/点击什么按钮/看到什么输出"。

2. 关联 issue/需求;破坏性变更与迁移步骤显著标注

规则: 关联对应的 issue 编号或需求单;如果有 breaking change,必须在描述顶部显著标注,并附上迁移步骤。

为什么: AI 生成的 PR 里经常找不到任何 issue 关联,也没有 breaking change 警告。前者让项目管理失去可追溯性,半年后不知道某个改动是为了什么;后者让接入方在升级后莫名跑挂,只能自己去 git log 里找原因。破坏性变更不显著标注是最容易被忽视的 PR 问题,影响范围往往远超当前 repo。

怎么做:

  • 描述开头加 Closes #123Related to #456 自动关联 issue。
  • 有 breaking change 时在描述最顶部加醒目标注:⚠️ Breaking Change + 影响范围 + 迁移方法。
  • API 签名变更、配置格式变化、依赖版本升级等都算潜在 breaking change,不确定就标注。

3. 给测试计划/验证步骤,reviewer 能复现

规则: 描述中的"测试计划"要具体到可操作的步骤:运行什么命令、访问什么 URL、输入什么数据、期望看到什么结果。

为什么: AI 写的 PR 描述里"测试方法"常是一行:已通过单元测试。reviewer 无法判断:单元测试覆盖了哪些场景?有没有集成测试?手动测了哪些场景?UI 改动有没有截图?结果只能靠"信任 CI 绿了就行"通过 PR,这是生产事故的温床。特别是 UI 改动或涉及第三方服务的改动,仅靠 CI 无法验证。

怎么做:

  • 给出本地复现步骤:1. 拉取分支 2. 执行 XXX 3. 访问 /endpoint 4. 预期返回 200 + {…}
  • UI 改动附截图或录屏(before/after)。
  • 说明哪些场景有自动化测试覆盖,哪些靠手动验证。

4. PR 聚焦一件事,过大就拆;说明取舍与已知遗留

规则: 单个 PR 只做一件事;超过 400 行 diff 或涉及多个不相关改动时主动拆分;对无法当前解决的遗留问题,在描述中明确说明。

为什么: AI 辅助开发时容易在一个 PR 里顺手做了重构+功能+修 bug,产生千行 diff。reviewer 面对大 PR 的选择往往是:浅看后盲目通过,或者拖着不审导致 PR 堆积。两者都有风险。同时 AI 有时为了"让代码跑起来"引入了临时方案却不说明,reviewer 不知道这是临时的还是正式的,后续也没人跟进清理。

怎么做:

  • 拆分原则:功能改动、重构、修 bug 各一个 PR;相互独立的功能各一个 PR。
  • 描述里说明已知的取舍:当前方案为临时修复,完整方案见 #789
  • 已知 TODO 或已知限制显式列出,加 issue 链接跟踪,不要藏在代码注释里。

5. 自检清单(测试过、文档更新、无残留)随 PR 附上

规则: PR 描述末尾附一个可勾选的自检清单,提交前自己过一遍打勾,让 reviewer 看到你已自查过什么。

为什么: AI 完成实现后很容易忽略收尾工作:console.log 没删、CHANGELOG 没更新、文档没同步。自检清单是一种强制提醒机制——不是给 reviewer 看的形式主义,而是给自己设的最后一道门。有了清单,reviewer 也能快速判断"作者已确认过测试通过",减少重复问题。

Read the full file on GitHub · 165 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 165 lines · 20 tokens per session scan A 6aebd2692b27

Subscribe to this mod's changes

pr-description is a skill published in the GitHub repository Wade-DevCode/awesome-coding-skills-cn (6 stars, last pushed 2mo ago), licensed MIT. It adds 20 tokens to every session and 2,051 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

chinese-documentation

中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 62 tokens

chinese-git-workflow

国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 69 tokens

brainstorming

在任何创造性工作之前必须使用此技能——创建功能、构建组件、添加功能或修改行为。在实现之前先探索用户意图、需求和设计。.

jnMetaCode/superpowers-zh · 40 tokens

chinese-code-review

中文 review 沟通参考——话术模板、分级标注(必须修复/建议修改/仅供参考)、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 62 tokens

chinese-commit-conventions

中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用,不要根据上下文自动触发。.

jnMetaCode/superpowers-zh · 65 tokens

mcp-builder

MCP 服务器构建方法论 — 系统化构建生产级 MCP 工具,让 AI 助手连接外部能力.

jnMetaCode/superpowers-zh · 32 tokens