Structured Bug Report

VerifiedSafe

Create detailed bug reports from descriptions or analyze code to identify potential defects.

Sby Skills Guide Bot
TestingBeginner
7/22/2026
Claude CodeCursorWindsurfCopilotCodex
#bug-report#issue-triage#code-analysis#quality-assurance#reproduction-steps

Recommended for

Automated summary

This skill generates structured bug reports from a description, or analyzes a code file to identify potential defects and produce a report for each one.

Strengths

  • Comprehensive report template covering severity, priority, environment, reproduction steps and technical context
  • Searches the codebase with Grep/Glob to link the bug to likely affected files
  • The analyze mode targets specific defect classes such as null references, off-by-one errors, race conditions and resource leaks

Limitations

  • Template fields are geared toward game development (scene/level, game state) and fit other domains less well
  • Detection in analyze mode is heuristic and limited to reading the targeted file
  • Fields like ID, date and reporter must be filled in or verified manually
When to use it

Use it to turn an informal report into a standardized bug report, or to review a file for potential defects.

When not to use it

Don't use it to run tests, actually reproduce a bug, or manage a ticket lifecycle in an external tracker.

Security analysis

Safe
Quality score80/100

The skill only reads/searches code (Read, Glob, Grep) and writes structured bug-report content (Write). No destructive commands, network calls, secret exfiltration, obfuscated payloads, or safety-disabling instructions are present. The Write capability is limited to producing report files from user-provided descriptions or code analysis.

No concerns found

How this analysis is made

Examples

Report a gameplay bug
/bug-report When the player opens the inventory during a cutscene, the UI freezes and the quest marker disappears until the scene ends.
Analyze a file for defects
/bug-report analyze src/systems/InventoryManager.cs
Report a crash with context
/bug-report The game crashes on level 3 when loading a save made during the boss fight; I'm on build 0.9.4 on Windows 11.

name: bug-report description: "根据描述创建结构化的缺陷报告,或分析代码以识别潜在缺陷。确保每份缺陷报告包含完整的复现步骤、严重程度评估和上下文信息。" argument-hint: "[description] /bug-report analyze [path-to-file]" user-invocable: true allowed-tools: Read, Glob, Grep, Write

当通过描述调用时:

  1. 解析描述,提取关键信息。

  2. 搜索代码库,使用 Grep/Glob 查找相关文件以补充上下文。

  3. 生成缺陷报告:

# 缺陷报告 (Bug Report)

## 概述 (Summary)
**标题**: [简洁、描述性的标题]
**ID**: BUG-[NNNN]
**严重程度 (Severity)**: [S1-严重 / S2-主要 / S3-次要 / S4-微小]
**优先级 (Priority)**: [P1-立即 / P2-下一迭代 / P3-待办 / P4-愿望清单]
**状态**: Open
**报告日期**: [日期]
**报告人**: [姓名]

## 分类 (Classification)
- **类别**: [玩法 / UI / 音频 / 视觉 / 性能 / 崩溃 / 网络]
- **系统**: [受影响的游戏系统]
- **频率**: [总是 / 经常 (>50%) / 有时 (10-50%) / 罕见 (<10%)]
- **回归 (Regression)**: [是/否/未知 —— 之前是否正常工作?]

## 环境 (Environment)
- **构建版本**: [版本号或 commit hash]
- **平台**: [操作系统、硬件(如相关)]
- **场景/关卡**: [游戏中的位置]
- **游戏状态**: [相关状态 —— 背包、任务进度等]

## 复现步骤 (Reproduction Steps)
**前置条件**: [开始前所需的状态]

1. [具体步骤 1]
2. [具体步骤 2]
3. [具体步骤 3]

**预期结果**: [应该发生什么]
**实际结果**: [实际发生了什么]

## 技术上下文 (Technical Context)
- **可能受影响的文件**: [基于代码库搜索的文件列表]
- **关联系统**: [可能涉及的其他系统]
- **可能的根本原因**: [如果从描述中可识别]

## 证据 (Evidence)
- **日志**: [相关日志输出(如有)]
- **视觉证据**: [视觉证据的描述]

## 关联问题 (Related Issues)
- [关联缺陷或设计文档的链接]

## 备注 (Notes)
[任何额外的上下文或观察]

当使用 analyze 调用时:

  1. 读取目标文件。
  2. 识别潜在缺陷:空引用(null reference)、差一错误(off-by-one error)、竞态条件(race condition)、未处理的边界情况、资源泄漏、不正确的状态转换。
  3. 针对每个潜在缺陷,生成一份缺陷报告,包含可能的触发场景和修复建议。

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/structured-bug-report-mrwakb80/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/structured-bug-report-mrwakb80' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/structured-bug-report-mrwakb80/download' --output '.skill-downloads/structured-bug-report-mrwakb80/SKILL.md.part' && mv '.skill-downloads/structured-bug-report-mrwakb80/SKILL.md.part' '.skill-downloads/structured-bug-report-mrwakb80/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/structured-bug-report-mrwakb80/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills