github-issue-creator

作者: google-gemini

当被要求创建GitHub issue时使用此技能。它处理不同的issue

npx skills add https://github.com/google-gemini/gemini-cli --skill github-issue-creator

GitHub Issue Creator

This skill guides the creation of high-quality GitHub issues that adhere to the repository's standards and use the appropriate templates.

Workflow

Follow these steps to create a GitHub issue:

  1. Identify Issue Type: Determine if the request is a bug report, feature request, or other category.

  2. Locate Template: Search for issue templates in .github/ISSUE_TEMPLATE/.

    • bug_report.yml
    • feature_request.yml
    • website_issue.yml
    • If no relevant YAML template is found, look for .md templates in the same directory.
  3. Read Template: Read the content of the identified template file to understand the required fields.

  4. Draft Content: Draft the issue title and body/fields.

    • If using a YAML template (form), prepare values for each id defined in the template.
    • If using a Markdown template, follow its structure exactly.
    • Default Label: Always include the 🔒 maintainer only label unless the user explicitly requests otherwise.
  5. Create Issue: Use the gh CLI to create the issue.

    • CRITICAL: To avoid shell escaping and formatting issues with multi-line Markdown or complex text, ALWAYS write the description/body to a temporary file first.

    For Markdown Templates or Simple Body:

    # 1. Write the drafted content to a temporary file
    # 2. Create the issue using the --body-file flag
    gh issue create --title "Succinct title" --body-file <temp_file_path> --label "🔒 maintainer only"
    # 3. Remove the temporary file
    rm <temp_file_path>
    

    For YAML Templates (Forms): While gh issue create supports --body-file, YAML forms usually expect key-value pairs via flags if you want to bypass the interactive prompt. However, the most reliable non-interactive way to ensure formatting is preserved for long text fields is to use the --body or --body-file if the form has been converted to a standard body, OR to use the --field flags for YAML forms.

    Note: For the gemini-cli repository which uses YAML forms, you can often submit the content as a single body if a specific field-based submission is not required by the automation.

  6. Verify: Confirm the issue was created successfully and provide the link to the user.

Principles

  • Clarity: Titles should be descriptive and follow project conventions.
  • Defensive Formatting: Always use temporary files with --body-file to prevent newline and special character issues.
  • Maintainer Priority: Default to internal/maintainer labels to keep the backlog organized.
  • Completeness: Provide all requested information (e.g., version info, reproduction steps).

来自 google-gemini 的更多技能

agent-tui
google-gemini
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications…
gemini-api-cli
google-gemini
使用Gemini API CLI工具的指南。当你需要通过命令行与Gemini API交互、管理代理或生成媒体(图像、……)时使用。
behavioral-evals
google-gemini
创建、运行、修复和推广行为评估的指南。用于验证代理决策逻辑、调试故障、调试提示…
gemini-live-api-dev
google-gemini
通过WebSocket与Gemini进行实时双向流式传输,支持音频、视频和文本对话。具备音频输入/输出(16 kHz PCM)、视频帧、文本以及带语音活动检测的自动转录功能,可实现中断处理。包含原生音频特性:情感对话、主动音频和思考模式;支持同步和异步工具调用的函数调用;以及Google搜索接地功能。提供会话管理,包括上下文压缩、恢复等。
gemini-omni-flash-api
google-gemini
使用此技能进行生成式视频编辑、文本转视频、图像参考视频生成以及首帧到视频的过渡动画,基于…
gemini-api-dev
google-gemini
使用Google的Gemini模型构建应用程序,支持多模态内容、函数调用和结构化输出,覆盖Python、JavaScript、Go和Java语言。可访问当前Gemini 3模型(Pro、Flash、Pro Image),具备100万token上下文;旧版Gemini 2.x和1.5模型已弃用。支持文本生成、图像/音频/视频理解、函数调用、结构化JSON输出、代码执行、上下文缓存和嵌入功能。提供官方SDK:google-genai(Python)...
gemini-interactions-api
google-gemini
Gemini模型与代理的统一接口,支持服务端状态、流式传输和工具编排。兼容当前多款模型(gemini-3-flash-preview、gemini-3-pro-preview、gemini-2.5-flash/pro)及Deep Research代理;自动将已弃用的模型ID替换为当前替代方案。通过previous_interaction_id将对话历史卸载至服务端,实现有状态的多轮交互,无需手动管理历史记录。内置工具编排功能包括...
deliver
google-gemini
将简报的浓缩版发布到 Google Chat 或 Slack 的传入 webhook,使每日运行自行投递——当没有 webhook 时静默跳过……