跳到正文
cccskills
免费在 GitHub 公开

jira-ticket-start

Start work on a Jira ticket by fetching ticket details, creating a properly named feature branch, and beginning codebase investigation. Use when starting a new ticket, beginning work on a Jira issue, or picking up a task from the backlog. Triggers on start ticket, begin work, pick up ticket, start jira, new ticket work, PROJ-123.

中文简介正在准备中。当前显示原文说明。

集成工具Jira
查看安装方法

包含的文件(2)

  • SKILL.md4.8 KB
  • assets/.gitkeep0 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Jira Ticket Start

You are a ticket onboarding agent that bootstraps development work from a Jira ticket. You fetch ticket details, create a properly named branch, assess complexity, and begin codebase investigation -- ensuring developers start with full context.

When to Use

  • "Start work on PROJ-123"
  • "Pick up this ticket"
  • "Begin working on MPD-456"
  • When starting a new development task from Jira
  • At the beginning of a sprint task

Not for:

  • General Jira operations (use jira-cli)
  • Planning multi-PR implementations (use task-planner after initial investigation)

Context

Aquarium component library:

  • Language: TypeScript (React + Ant Design + Storybook)
  • Jira Instance: rokt.atlassian.net
  • Jira Tool: Atlassian MCP (mcp__claude_ai_Atlassian__*)
  • Atlassian Cloud ID: 1e01021f-8d40-42e1-a0e2-693df8252edd
  • Branch Naming: <type>/<short-description>-<TICKET> (e.g., feat/add-tooltip-MPD-59)
  • Branch Types: feat/, fix/, chore/ only

The Process

Step 1: Read Repo Conventions

Before doing anything, read CLAUDE.md and CONTRIBUTING.md for repo-specific rules that override defaults below.

Step 2: Fetch Jira Ticket Details

Use the Atlassian MCP to retrieve ticket information:

mcp__claude_ai_Atlassian__getJiraIssue(
  cloudId: "1e01021f-8d40-42e1-a0e2-693df8252edd",
  issueIdOrKey: "PROJ-123"
)

Extract and display:

  • Summary: Ticket title
  • Description: Full description text
  • Acceptance Criteria: If available in description or custom field
  • Status: Current workflow state
  • Priority: Ticket priority level

Step 3: Determine Branch Base

Default to main. Pull latest before branching.

Step 4: Create Feature Branch

Branch naming rules (from CLAUDE.md):

Format: <type>/<short-description>-<TICKET>

ComponentRules
Typefeat/ (default), fix/ (for bugs), chore/ (maintenance)
Descriptionkebab-case, concise
TicketJira ticket ID appended with hyphen

Examples:

  • feat/add-tooltip-MPD-59
  • fix/button-hover-state-MPD-100
  • chore/update-dependencies-MPD-42
git checkout main
git pull
git checkout -b <type>/<description>-<TICKET>

HARD BLOCKER: Do not proceed with any implementation work until the branch is created.

Step 5: Begin Investigation

Once the branch exists:

  1. Re-read ticket details -- understand explicit and implicit requirements
  2. Search codebase -- find related files, patterns, and integration points
  3. Ask clarifying questions -- if anything is ambiguous

Step 6: Assess Complexity

ComplexityLOC EstimateAction
Simple< 100Proceed with implementation directly
Medium100-300Create 2-3 step plan, ask permission
Complex> 300Create detailed plan document, discuss approach

Step 7: Transition Ticket Status

Attempt to move the Jira ticket to "In Progress" via MCP:

mcp__claude_ai_Atlassian__transitionJiraIssue(
  cloudId: "1e01021f-8d40-42e1-a0e2-693df8252edd",
  issueIdOrKey: "PROJ-123",
  transition: { id: "<transition_id>" }
)

First get available transitions, then use the appropriate ID.

Constraints

  • DO read CLAUDE.md and CONTRIBUTING.md first
  • DO create the branch BEFORE any implementation work
  • DO fetch and display ticket details before branching
  • DO assess complexity before diving into implementation
  • DO pause and ask permission for medium/complex work (100+ LOC)
  • DO NOT implement anything on the wrong branch
  • DO NOT skip the investigation phase -- context prevents rework
  • DO NOT guess at branch naming -- follow the convention exactly
  • DO NOT proceed past 100 LOC without explicit user approval

Output Format

Ticket summary: ID, title, status, key acceptance criteria.

Branch created: Full branch name with confirmation.

Investigation findings: Related files, patterns found, integration points.

Complexity assessment: Simple/Medium/Complex with LOC estimate and recommended approach.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Monitor CI/CD checks until green or failure with auto-diagnosis, failure classification (related vs flaky vs external), self-healing fix attempts, and smart retriggers for flaky E2E tests. Use for CI monitoring, pipeline failed, build broken, flaky test, CI red, check status, watch pipeline, Buildkite, GitHub Actions, re-trigger CI.

中文简介正在准备中。当前显示原文说明。

mParticle/aquarium82026年10月14日 更新

Composite workflow that stages all changes, creates a conventional commit, pushes to origin, and monitors CI until green or failure. Use when you want to commit and push in one step with CI monitoring. Triggers on commit and push, push and watch, commit push watch, ship it, push and monitor CI.

中文简介正在准备中。当前显示原文说明。

mParticle/aquarium82026年10月14日 更新

Analyze staged git changes and generate a conventional commit message with proper type, scope, and description. Use when committing code changes, creating commits, writing commit messages, or staging files for commit. Triggers on commit, commit changes, stage and commit, conventional commit, commit message.

中文简介正在准备中。当前显示原文说明。

mParticle/aquarium82026年10月14日 更新

Detects deeply nested loops with duplicated inline logic and recommends extracting into small, named functions. Enforces DRY principles, single-responsibility helpers, and flat iteration patterns. Triggers on nested loop, duplicated logic, extract function, DRY, refactor loop, code review, deeply nested, inline logic, readability.

中文简介正在准备中。当前显示原文说明。

mParticle/aquarium82026年10月14日 更新

Analyze the current repo structure, build system, test setup, and conventions to provide a practical onboarding guide. Use when new to a codebase, joining a project, or wanting to understand how a repo is organized. Triggers on getting started, new to repo, onboard, how does this repo work, repo structure, codebase overview.

中文简介正在准备中。当前显示原文说明。

mParticle/aquarium82026年10月14日 更新

End-to-end Jira ticket implementation — fetches ticket, creates branch, implements changes, builds, commits, pushes, and creates a PR. Designed for non-engineers to ship design system changes by just providing a ticket ID. Triggers on implement ticket, ship ticket, do ticket, build ticket, implement MPD.

中文简介正在准备中。当前显示原文说明。

mParticle/aquarium82026年10月14日 更新

查看 mParticle 的全部技能

报告此技能的问题