본문으로 건너뛰기
cccskills
무료GitHub에 공개

jira-workflow

Orchestrate Jira workflows end-to-end. Use when building stories with approvals, transitioning items through lifecycle states, or syncing task completion with Jira.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구Jira
설치 방법 보기

포함된 파일(2)

  • SKILL.md18.8 KB
  • skill-report.json109.1 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Jira Workflow Orchestration Skill

Complete workflow management for Jira: building stories (SAFe), getting approvals, and transitioning items through the development lifecycle (To Do → Progressing → Done).

IMPORTANT: This project uses Next-Gen (Team-managed) Jira with custom workflow states. The actual states are:

  • To Do (backlog)
  • In Review
  • Progressing (active work)
  • Out Review
  • Done

Always query available transitions first: GET /rest/api/3/issue/{key}/transitions

When to Use

  • Creating new user stories, epics, or tasks for the project
  • Getting user approval before creating Jira items
  • Moving stories through workflow states as work progresses
  • Syncing Claude Code task completion with Jira status
  • Managing sprint planning and backlog refinement
  • Tracking development progress in real-time

Prerequisites

Environment Variables:

JIRA_EMAIL=your.email@domain.com
JIRA_API_TOKEN=your_api_token
JIRA_BASE_URL=https://your-org.atlassian.net
JIRA_PROJECT_KEY=SCRUM
JIRA_BOARD_ID=1

Project Configuration:

  • Must know if project is Next-Gen (Team-managed) or Classic (Company-managed)
  • Next-Gen: Use parent field for Epic links
  • Classic: Use customfield_10014 for Epic links

Core Workflow Pattern

The Approval-Create-Track Loop

1. PLAN: Analyze task requirements
   ↓
2. PROPOSE: Present story to user for approval
   ↓
3. APPROVE: User confirms or modifies
   ↓
4. CREATE: Issue created in Jira backlog
   ↓
5. START: Transition to "Progressing" when work begins
   ↓
6. COMPLETE: Transition to "Done" when work verified
   ↓
7. SYNC: Update Jira with implementation details

Phase 1: Story Building (SAFe Format)

Building a Story Proposal

When user requests work, build a SAFe-compliant story proposal:

function buildStoryProposal(task) {
  return {
    summary: `As a ${task.persona}, I want ${task.goal}, so that ${task.benefit}`,
    description: {
      userStory: `As a **${task.persona}**, I want **${task.goal}**, so that **${task.benefit}**.`,
      acceptanceCriteria: task.scenarios.map(s => ({
        name: s.name,
        given: s.given,
        when: s.when,
        then: s.then
      })),
      definitionOfDone: [
        'Code reviewed and approved',
        'Unit tests written and passing',
        'Integration tests passing',
        'Documentation updated',
        'Deployed to staging',
        'Validated in production'
      ],
      technicalNotes: task.technicalNotes || []
    },
    category: task.category, // authentication, ui, api, database, etc.
    estimatedComplexity: task.complexity || 'medium', // small, medium, large
    subtasks: task.subtasks || []
  };
}

Presenting for Approval

CRITICAL: Always get user approval before creating Jira items.

Use this prompt pattern:

## Proposed Jira Story

**Summary:** As a [persona], I want [goal], so that [benefit]

**Category:** [category]
**Complexity:** [small/medium/large]

### Acceptance Criteria

**Scenario 1: [Name]**
- **GIVEN** [precondition]
- **WHEN** [action]
- **THEN** [expected result]

### Subtasks (if any)
1. [Subtask 1]
2. [Subtask 2]
3. [Subtask 3]

---

**Do you want me to create this in Jira?**

Options:
1. **Yes, create as-is** - I'll create the story now
2. **Modify** - Tell me what to change
3. **Skip** - Don't create in Jira, just do the work

Phase 2: Issue Creation

Create Story in Jira

const JIRA_EMAIL = process.env.JIRA_EMAIL;
const JIRA_API_TOKEN = process.env.JIRA_API_TOKEN;
const JIRA_BASE_URL = process.env.JIRA_BASE_URL;
const PROJECT_KEY = process.env.JIRA_PROJECT_KEY;

const auth = Buffer.from(`${JIRA_EMAIL}:${JIRA_API_TOKEN}`).toString('base64');
const headers = {
  'Authorization': `Basic ${auth}`,
  'Content-Type': 'application/json',
  'Accept': 'application/json'
};

async function createStory(proposal, epicKey = null) {
  const body = {
    fields: {
      project: { key: PROJECT_KEY },
      issuetype: { name: 'Story' },
      summary: proposal.summary,
      description: buildADF(proposal.description),
      labels: [proposal.category.toLowerCase().replace(/\s+/g, '-')]
    }
  };

  // Link to Epic (Next-Gen project)
  if (epicKey) {
    body.fields.parent = { key: epicKey };
  }

  const response = await fetch(`${JIRA_BASE_URL}/rest/api/3/issue`, {
    method: 'POST',
    headers,
    body: JSON.stringify(body)
  });

  if (!response.ok) {
    const error = await response.text();
    throw new Error(`Failed to create story: ${error}`);
  }

  const issue = await response.json();
  console.log(`Created: ${issue.key} - ${proposal.summary}`);

  // Create subtasks if any
  if (proposal.subtasks?.length > 0) {
    for (const subtask of proposal.subtasks) {
      await createSubtask(issue.key, subtask);
      await delay(100); // Rate limiting
    }
  }

  return issue;
}

async function createSubtask(parentKey, summary) {
  const body = {
    fields: {
      project: { key: PROJECT_KEY },
      issuetype: { name: 'Subtask' }, // Note: 'Subtask' for Next-Gen
      parent: { key: parentKey },
      summary: summary
    }
  };

  const response = await fetch(`${JIRA_BASE_URL}/rest/api/3/issue`, {
    method: 'POST',
    headers,
    body: JSON.stringify(body)
  });

  if (!response.ok) {
    const error = await response.text();
    throw new Error(`Failed to create subtask: ${error}`);
  }

  return response.json();
}

function delay(ms) {
  return new Promise(resolve => setTimeout(resolve, ms));
}

Build Atlassian Document Format (ADF)

function buildADF(content) {
  const sections = [];

  // User Story Section
  sections.push({
    type: 'heading',
    attrs: { level: 2 },
    content: [{ type: 'text', text: 'User Story' }]
  });
  sections.push({
    type: 'paragraph',
    content: [{ type: 'text', text: content.userStory }]
  });

  // Acceptance Criteria Section
  sections.push({
    type: 'heading',
    attrs: { level: 2 },
    content: [{ type: 'text', text: 'Acceptance Criteria' }]
  });

  for (const scenario of content.acceptanceCriteria) {
    sections.push({
      type: 'heading',
      attrs: { level: 3 },
      content: [{ type: 'text', text: `Scenario: ${scenario.name}` }]
    });
    sections.push({
      type: 'bulletList',
      content: [
        { type: 'listItem', content: [{ type: 'paragraph', content: [{ type: 'text', text: `GIVEN ${scenario.given}`, marks: [{ type: 'strong' }] }] }] },
        { type: 'listItem', content: [{ type: 'paragraph', content: [{ type: 'text', text: `WHEN ${scenario.when}`, marks: [{ type: 'strong' }] }] }] },
        { type: 'listItem', content: [{ type: 'paragraph', content: [{ type: 'text', text: `THEN ${scenario.then}`, marks: [{ type: 'strong' }] }] }] }
      ]
    });
  }

  // Definition of Done Section
  sections.push({
    type: 'heading',
    attrs: { level: 2 },
    content: [{ type: 'text', text: 'Definition of Done' }]
  });
  sections.push({
    type: 'bulletList',
    content: content.definitionOfDone.map(item => ({
      type: 'listItem',
      content: [{ type: 'paragraph', content: [{ type: 'text', text: `[ ] ${item}` }] }]
    }))
  });

  // Technical Notes (if any)
  if (content.technicalNotes?.length > 0) {
    sections.push({
      type: 'heading',
      attrs: { level: 2 },
      content: [{ type: 'text', text: 'Technical Notes' }]
    });
    sections.push({
      type: 'bulletList',
      content: content.technicalNotes.map(note => ({
        type: 'listItem',
        content: [{ type: 'paragraph', content: [{ type: 'text', text: note }] }]
      }))
    });
  }

  return { type: 'doc', version: 1, content: sections };
}

Phase 3: Workflow Transitions

Get Available Transitions

async function getTransitions(issueKey) {
  const response = await fetch(
    `${JIRA_BASE_URL}/rest/api/3/issue/${issueKey}/transitions`,
    { headers }
  );

  if (!response.ok) {
    throw new Error(`Failed to get transitions: ${response.status}`);
  }

  const data = await response.json();
  return data.transitions;
}

Transition Issue to State

async function transitionTo(issueKey, targetState) {
  // Get available transitions
  const transitions = await getTransitions(issueKey);

  // Find the transition to target state
  const transition = transitions.find(t =>
    t.to.name.toLowerCase() === targetState.toLowerCase() ||
    t.name.toLowerCase() === targetState.toLowerCase()
  );

  if (!transition) {
    console.log(`Available transitions for ${issueKey}:`);
    transitions.forEach(t => console.log(`  - ${t.name} → ${t.to.name}`));
    throw new Error(`No transition to "${targetState}" found`);
  }

  // Execute the transition
  const response = await fetch(
    `${JIRA_BASE_URL}/rest/api/3/issue/${issueKey}/transitions`,
    {
      method: 'POST',
      headers,
      body: JSON.stringify({ transition: { id: transition.id } })
    }
  );

  if (!response.ok) {
    const error = await response.text();
    throw new Error(`Failed to transition: ${error}`);
  }

  console.log(`${issueKey} transitioned to ${targetState}`);
  return true;
}

Common Workflow Operations

// Start work on a story (To Do → Progressing)
async function startWork(issueKey) {
  await transitionTo(issueKey, 'Progressing');
  console.log(`Started: ${issueKey}`);
}

// Complete a story (Progressing → Done)
async function completeWork(issueKey) {
  await transitionTo(issueKey, 'Done');
  console.log(`Completed: ${issueKey}`);
}

// Move back to backlog (any state → To Do)
async function moveToBacklog(issueKey) {
  await transitionTo(issueKey, 'To Do');
  console.log(`Moved to backlog: ${issueKey}`);
}

// Reopen a completed issue (Done → To Do)
async function reopenWork(issueKey) {
  await transitionTo(issueKey, 'To Do');
  console.log(`Reopened: ${issueKey}`);
}

Phase 4: Add Comments and Updates

Add Work Log Comment

async function addComment(issueKey, comment) {
  const body = {
    body: {
      type: 'doc',
      version: 1,
      content: [
        {
          type: 'paragraph',
          content: [{ type: 'text', text: comment }]
        }
      ]
    }
  };

  const response = await fetch(
    `${JIRA_BASE_URL}/rest/api/3/issue/${issueKey}/comment`,
    {
      method: 'POST',
      headers,
      body: JSON.stringify(body)
    }
  );

  if (!response.ok) {
    throw new Error(`Failed to add comment: ${response.status}`);
  }

  console.log(`Comment added to ${issueKey}`);
  return response.json();
}

Add Implementation Details Comment

async function addImplementationDetails(issueKey, details) {
  const content = [
    { type: 'heading', attrs: { level: 3 }, content: [{ type: 'text', text: 'Implementation Details' }] },
    { type: 'paragraph', content: [{ type: 'text', text: `Completed: ${new Date().toISOString()}` }] }
  ];

  if (details.files?.length > 0) {
    content.push(
      { type: 'heading', attrs: { level: 4 }, content: [{ type: 'text', text: 'Files Modified' }] },
      {
        type: 'bulletList',
        content: details.files.map(f => ({
          type: 'listItem',
          content: [{ type: 'paragraph', content: [{ type: 'text', text: f }] }]
        }))
      }
    );
  }

  if (details.commits?.length > 0) {
    content.push(
      { type: 'heading', attrs: { level: 4 }, content: [{ type: 'text', text: 'Commits' }] },
      {
        type: 'bulletList',
        content: details.commits.map(c => ({
          type: 'listItem',
          content: [{ type: 'paragraph', content: [{ type: 'text', text: c }] }]
        }))
      }
    );
  }

  if (details.notes) {
    content.push(
      { type: 'heading', attrs: { level: 4 }, content: [{ type: 'text', text: 'Notes' }] },
      { type: 'paragraph', content: [{ type: 'text', text: details.notes }] }
    );
  }

  const body = { body: { type: 'doc', version: 1, content } };

  const response = await fetch(
    `${JIRA_BASE_URL}/rest/api/3/issue/${issueKey}/comment`,
    {
      method: 'POST',
      headers,
      body: JSON.stringify(body)
    }
  );

  return response.json();
}

Complete Workflow Example

Full Cycle: Propose → Approve → Create → Work → Complete

async function fullWorkflowCycle(task) {
  // 1. Build proposal
  const proposal = buildStoryProposal(task);

  // 2. Present for approval (use AskUserQuestion tool)
  const approved = await presentForApproval(proposal);

  if (!approved) {
    console.log('Story creation skipped by user');
    return null;
  }

  // 3. Create in Jira
  const issue = await createStory(proposal, task.epicKey);
  console.log(`Created: ${issue.key}`);

  // 4. Start work (transition to In Progress)
  await startWork(issue.key);

  // 5. Do the actual work (your implementation here)
  const result = await doTheWork(task);

  // 6. Add implementation details
  await addImplementationDetails(issue.key, {
    files: result.modifiedFiles,
    commits: result.commits,
    notes: result.notes
  });

  // 7. Complete the work
  await completeWork(issue.key);

  return issue;
}

Integration with Claude Code Orchestration

Sync with TodoWrite

When working on Jira stories, sync with TodoWrite:

TodoWrite todos:
[
  { "content": "SCRUM-55: Create signup API", "status": "in_progress", "activeForm": "Working on SCRUM-55" },
  { "content": "SCRUM-56: Create login API", "status": "pending", "activeForm": "Waiting for SCRUM-55" },
  { "content": "SCRUM-57: Create logout API", "status": "pending", "activeForm": "Waiting for SCRUM-56" }
]

As each task completes:
1. Mark TodoWrite item as completed
2. Transition Jira issue to Done
3. Add implementation comment to Jira
4. Move to next task

Auto-Transition Pattern

// When starting a task
async function startTask(issueKey) {
  // 1. Transition Jira to Progressing
  await startWork(issueKey);

  // 2. Update TodoWrite (in Claude Code)
  // TodoWrite: Mark as in_progress

  return issueKey;
}

// When completing a task
async function completeTask(issueKey, details) {
  // 1. Add implementation comment
  await addImplementationDetails(issueKey, details);

  // 2. Transition Jira to Done
  await completeWork(issueKey);

  // 3. Update TodoWrite (in Claude Code)
  // TodoWrite: Mark as completed

  return issueKey;
}

Quick Reference

Status Transitions (SCRUM Project - Next-Gen)

FromToTransition NameTypical Use
To DoProgressing"Progressing"Starting work
To DoIn Review"In Review"Needs review first
ProgressingDone"Done"Work complete
ProgressingTo Do"To Do"Blocked/deprioritized
DoneTo Do"To Do"Reopening

Available States: To Do, In Review, Progressing, Out Review, Done

Note: Always query transitions first - they vary by issue type and current state.

API Endpoints

ActionMethodEndpoint
Create IssuePOST/rest/api/3/issue
Get IssueGET/rest/api/3/issue/{key}
Update IssuePUT/rest/api/3/issue/{key}
Delete IssueDELETE/rest/api/3/issue/{key}
Get TransitionsGET/rest/api/3/issue/{key}/transitions
Do TransitionPOST/rest/api/3/issue/{key}/transitions
Add CommentPOST/rest/api/3/issue/{key}/comment
SearchGET/rest/api/3/search/jql?jql=...

Rate Limiting

  • Max 10 requests/second
  • Add 100ms delay between bulk operations
  • Batch operations where possible

Error Handling

async function safeJiraOperation(operation, issueKey) {
  try {
    return await operation();
  } catch (error) {
    console.error(`Jira operation failed for ${issueKey}: ${error.message}`);

    // Common error patterns
    if (error.message.includes('404')) {
      console.log('Issue not found - may have been deleted');
    }
    if (error.message.includes('401')) {
      console.log('Authentication failed - check API token');
    }
    if (error.message.includes('403')) {
      console.log('Permission denied - check project access');
    }
    if (error.message.includes('400')) {
      console.log('Bad request - check field names and values');
    }

    throw error;
  }
}

Executable Scripts

Ready-to-run scripts are available in both Node.js and Python:

Using the Cross-Platform Runner

# From the .claude/skills/jira directory
node scripts/run.js workflow demo SCRUM-100  # Demo full workflow
node scripts/run.js test                      # Test authentication

# Force specific runtime
node scripts/run.js --python workflow demo SCRUM-100
node scripts/run.js --node workflow demo SCRUM-100

Direct Script Execution

# Node.js
node scripts/jira-workflow-demo.mjs demo SCRUM-100
node scripts/jira-workflow-demo.mjs start SCRUM-100
node scripts/jira-workflow-demo.mjs complete SCRUM-100
node scripts/jira-workflow-demo.mjs reopen SCRUM-100
node scripts/jira-workflow-demo.mjs status SCRUM-100

# Python (recommended on Windows)
python scripts/jira-workflow-demo.py demo SCRUM-100
python scripts/jira-workflow-demo.py start SCRUM-100
python scripts/jira-workflow-demo.py complete SCRUM-100
python scripts/jira-workflow-demo.py reopen SCRUM-100
python scripts/jira-workflow-demo.py status SCRUM-100

Available Scripts

ScriptNode.jsPythonPurpose
Workflow Demojira-workflow-demo.mjsjira-workflow-demo.pyFull To Do → Progressing → Done demo
Add Subtasksjira-add-subtasks.mjsjira-add-subtasks.pyCreate subtasks under a story
Create Storyjira-create-one.mjsjira-create-one.pyCreate single story
Bulk Createjira-bulk-create.mjsjira-bulk-create.pyCreate from git commits

References

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aiskillstore/marketplace4432026년 10월 23일 업데이트

Trigger for: explaining current FAR, DFARS, or agency-supplement text; determining documented acquisition-policy status for an agency and FAR part; comparing codified text, RFO model text, and agency deviations; tracing acquisition rulemaking; finding procurement comment periods; analyzing public comments; refreshing prior policy analysis; or producing an Acquisition Policy Impact Brief. Use published federal sources and supplied policy documents without making legal or procurement-specific applicability determinations. Do not use for clause selection, market research execution, opportunities, pricing, grants, or cooperative agreements.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aiskillstore/marketplace4432026년 10월 23일 업데이트

Systematic framework for extracting actionable items from documents and organizing them into prioritized, trackable checklists. Use when converting reports, meeting notes, audits, or any document with embedded action items into structured TODO lists.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aiskillstore/marketplace4432026년 10월 23일 업데이트

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aiskillstore/marketplace4432026년 10월 23일 업데이트

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aiskillstore/marketplace4432026년 10월 23일 업데이트

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

aiskillstore/marketplace4432026년 10월 23일 업데이트

aiskillstore의 스킬 모두 보기

이 스킬의 문제 신고