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

commit-jira提交 Jira

Agent Skill

用于处理 Jira 项目、任务、缺陷、Sprint、负责人和状态流转。它适合让 Agent 辅助查询工单、汇总迭代进展、创建任务或整理需求和缺陷信息。使用时要确认项目权限、字段配置和工作流规则,不同团队的 Issue 类型、状态和必填字段可能不同;涉及批量改状态、改负责人或创建工单时,应先预览变更内容再执行。

总安装

218

周安装

9

GitHub Stars

公开资料未说明

下载量

71
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:commit-jira(提交 Jira)
来源仓库:https://github.com/bohdan-shulha/skills
仓库路径:skills/commit-jira
安装命令:
npx skills add https://github.com/bohdan-shulha/skills --skill commit-jira
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/bohdan-shulha/skills --skill commit-jira

简介

commit-jira 创建结构安全、质量一致的提交,集成 Jira 工单编号和校验机制。

  • 适用于需要将代码变更与 Jira 任务关联、确保提交合规性的开发流程。
  • 运行预提交守卫脚本,强制要求 Jira 风格主题和正文要点,提升消息完整性。
  • 必须从本技能目录解析脚本路径,建议确认 Python 环境和执行权限。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Commit Jira

Overview

Create safe, structured commits with deterministic checks and consistent message quality. Run a guard before staging, then commit using a required JIRA-style subject and required body bullets.

Path Resolution (Mandatory)

  • Resolve any relative path in this skill from this skill directory, not from the caller's current working directory.
  • For this skill, set skill_dir to the directory that contains this file (commit-jira/SKILL.md), then use skill_dir/scripts/precommit_guard.py.
  • Do not search for scripts/precommit_guard.py at repo root.

Workflow

  1. Run safety guard:

- python3 <skill_dir>/scripts/precommit_guard.py

  1. Abort immediately if the guard exits non-zero.

- Do not run git add or git commit when blocked.

  1. Stage all changes only after guard passes:

- git add. -A

  1. Review staged changes:

- git diff --cached --name-only - git diff --cached --stat

  1. Ensure the user provided a ticket number (example: JIRA-123).

- If missing, stop and ask the user for the ticket number.

  1. Compose commit subject and body using the format rules below.
  2. Execute commit:

- git commit -m "<subject>" -m "<body>"

Safety Guard Rules

Abort when any path matches one of these conditions:

  1. Log-like files:
  • *.log, *.out, *.err
  • npm-debug.log*, yarn-debug.log*, yarn-error.log*, pnpm-debug.log*
  • any file under a logs/ directory
  1. Untracked high-risk binary extensions:
  • .exe, .dll, .so, .dylib, .bin, .class
  • .zip, .tar, .gz, .bz2, .xz, .7z, .rar, .jar
  • .iso, .dmg, .db, .sqlite, .sqlite3

If blocked, list offending files grouped by reason and request user action. Do not auto-delete files.

Commit Message Format

Use JIRA subject format:

  • <ticket>: <description>
  • Ticket must be provided by the user (example: JIRA-123).
  • If no ticket is provided, return an error and ask the user for the ticket number before committing.
  • Subject must describe what changed (not only intent), be imperative, and avoid trailing period.
  • Keep subject concise (prefer <= 72 chars).

Require commit body:

  • Provide bullet lines summarizing key changes and impact.
  • Mention migration/risk notes when relevant.
  • Use concise, factual bullets.

Example:

Subject:

  • JIRA-123: my important changes

Body:

  • - Serialize refresh attempts per user session to prevent duplicate refresh calls.
  • - Add timeout handling so failed refresh does not block subsequent requests.
  • - Update session middleware tests for concurrent request scenarios.

Execution Notes

  • Prefer one logical commit for the current request.
  • If changes are unrelated, split into separate commits and repeat the guard + staging flow for each.
  • If message quality is uncertain, summarize staged diff first, then derive subject/body.

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

34.52%
按下载量换算25

Claude

32.37%
按下载量换算23

Cursor

18.5%
按下载量换算13

Gemini CLI

10.18%
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