Jira Safe logo

Jira Safe

Organization
aiskillstore
jira-safe

Implement SAFe methodology in Jira. Use when creating Epics, Features, Stories with proper hierarchy, acceptance criteria, and parent-child linking.

Overview

Publisheraiskillstore
Repositorymarketplace
Skill namejira-safe
Stars
427
Forks
45
Bundled files
7
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 7 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aiskillstore on GitHub. Read the source before you install it.

Installation

Install the Jira Safe AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/aiskillstore/marketplace.git /tmp/marketplace
mkdir -p .claude/skills
cp -r /tmp/marketplace/skills/01000001-01001110/jira-safe .claude/skills/jira-safe
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Jira Safe in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Jira Safe on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Jira Safe is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Jira SAFe (Scaled Agile Framework) Skill

Implements SAFe methodology for Epic, Feature, Story, and Task management in Jira Cloud.

When to Use

  • Creating Epics with business outcomes and acceptance criteria
  • Writing user stories in SAFe format ("As a... I want... So that...")
  • Breaking down Features into Stories with acceptance criteria
  • Creating Subtasks under Stories
  • Linking work items in proper hierarchy (Epic → Feature → Story → Subtask)

CRITICAL: Next-Gen vs Classic Projects

SCRUM project is Next-Gen (Team-managed). Key differences:

AspectClassic (Company-managed)Next-Gen (Team-managed)
Epic Linkcustomfield_10014parent: { key: 'EPIC-KEY' }
Epic Namecustomfield_10011Not available
Subtask Type'Sub-task''Subtask'
Project Styleclassicnext-gen, simplified: true

Always detect project type first:

javascript
const projectInfo = await fetch(`${JIRA_URL}/rest/api/3/project/${PROJECT_KEY}`, { headers });
const project = await projectInfo.json();
const isNextGen = project.style === 'next-gen' || project.simplified === true;

SAFe Hierarchy in Jira

Portfolio Level:
└── Epic (Strategic Initiative)
    └── Feature (Benefit Hypothesis)
        └── Story (User Value)
            └── Subtask (Technical Work)

SAFe Templates

Epic Template (Next-Gen)

javascript
// NOTE: Next-Gen projects do NOT use customfield_10011 (Epic Name)
const epic = {
  fields: {
    project: { key: 'PROJECT_KEY' },
    issuetype: { name: 'Epic' },
    summary: '[Epic ID]: [Epic Name] - [Business Outcome]',
    description: {
      type: 'doc',
      version: 1,
      content: [
        {
          type: 'heading',
          attrs: { level: 2 },
          content: [{ type: 'text', text: 'Business Outcome' }]
        },
        {
          type: 'paragraph',
          content: [{ type: 'text', text: 'Describe the measurable business value...' }]
        },
        {
          type: 'heading',
          attrs: { level: 2 },
          content: [{ type: 'text', text: 'Success Metrics' }]
        },
        {
          type: 'bulletList',
          content: [
            {
              type: 'listItem',
              content: [{ type: 'paragraph', content: [{ type: 'text', text: 'Metric 1: [measurable target]' }] }]
            }
          ]
        },
        {
          type: 'heading',
          attrs: { level: 2 },
          content: [{ type: 'text', text: 'Scope' }]
        },
        {
          type: 'paragraph',
          content: [{ type: 'text', text: 'What is in scope and out of scope...' }]
        }
      ]
    },
    labels: ['epic-label']  // Use labels instead of Epic Name for categorization
  }
};

Story Template (SAFe Format, Next-Gen)

javascript
// NOTE: Next-Gen uses 'parent' field, NOT customfield_10014
const story = {
  fields: {
    project: { key: 'PROJECT_KEY' },
    issuetype: { name: 'Story' },
    summary: '[US-ID]: As a [persona], I want [goal], so that [benefit]',
    description: {
      type: 'doc',
      version: 1,
      content: [
        {
          type: 'heading',
          attrs: { level: 2 },
          content: [{ type: 'text', text: 'User Story' }]
        },
        {
          type: 'paragraph',
          content: [
            { type: 'text', text: 'As a ', marks: [{ type: 'strong' }] },
            { type: 'text', text: '[persona]' },
            { type: 'text', text: ', I want ', marks: [{ type: 'strong' }] },
            { type: 'text', text: '[goal]' },
            { type: 'text', text: ', so that ', marks: [{ type: 'strong' }] },
            { type: 'text', text: '[benefit]' }
          ]
        },
        {
          type: 'heading',
          attrs: { level: 2 },
          content: [{ type: 'text', text: 'Acceptance Criteria' }]
        },
        {
          type: 'heading',
          attrs: { level: 3 },
          content: [{ type: 'text', text: 'Scenario 1: [Name]' }]
        },
        {
          type: 'bulletList',
          content: [
            {
              type: 'listItem',
              content: [{ type: 'paragraph', content: [{ type: 'text', text: 'GIVEN [precondition]', marks: [{ type: 'strong' }] }] }]
            },
            {
              type: 'listItem',
              content: [{ type: 'paragraph', content: [{ type: 'text', text: 'WHEN [action]', marks: [{ type: 'strong' }] }] }]
            },
            {
              type: 'listItem',
              content: [{ type: 'paragraph', content: [{ type: 'text', text: 'THEN [expected result]', marks: [{ type: 'strong' }] }] }]
            }
          ]
        },
        {
          type: 'heading',
          attrs: { level: 2 },
          content: [{ type: 'text', text: 'Definition of Done' }]
        },
        {
          type: 'bulletList',
          content: [
            {
              type: 'listItem',
              content: [{ type: 'paragraph', content: [{ type: 'text', text: '[ ] Code reviewed and approved' }] }]
            },
            {
              type: 'listItem',
              content: [{ type: 'paragraph', content: [{ type: 'text', text: '[ ] Unit tests written and passing' }] }]
            },
            {
              type: 'listItem',
              content: [{ type: 'paragraph', content: [{ type: 'text', text: '[ ] Integration tests passing' }] }]
            },
            {
              type: 'listItem',
              content: [{ type: 'paragraph', content: [{ type: 'text', text: '[ ] Documentation updated' }] }]
            }
          ]
        }
      ]
    },
    // Next-Gen: Link to parent Epic using 'parent' field
    parent: { key: 'EPIC_KEY' },
    labels: ['category-label', 'epic-id']
  }
};

Subtask Template (Next-Gen)

javascript
// NOTE: Next-Gen uses 'Subtask' (no hyphen), NOT 'Sub-task'
const subtask = {
  fields: {
    project: { key: 'PROJECT_KEY' },
    issuetype: { name: 'Subtask' },  // Next-Gen: 'Subtask', Classic: 'Sub-task'
    summary: '[Technical task description]',
    // Parent Story (required for subtasks)
    parent: { key: 'STORY_KEY' }
    // Note: Description is optional for subtasks
  }
};

API Implementation (Next-Gen Projects)

Create Epic with Stories (Next-Gen)

javascript
async function createEpicWithStories(epicFields, storyDefinitions) {
  const headers = {
    'Authorization': `Basic ${Buffer.from(`${EMAIL}:${TOKEN}`).toString('base64')}`,
    'Content-Type': 'application/json',
    'Accept': 'application/json'
  };

  // 1. Create Epic
  const epicResponse = await fetch(`${JIRA_URL}/rest/api/3/issue`, {
    method: 'POST',
    headers,
    body: JSON.stringify({ fields: epicFields })
  });

  if (!epicResponse.ok) {
    const error = await epicResponse.text();
    throw new Error(`Epic creation failed: ${error}`);
  }

  const createdEpic = await epicResponse.json();
  console.log(`Created Epic: ${createdEpic.key}`);

  // 2. Create Stories linked to Epic using 'parent' field (Next-Gen)
  const createdStories = [];
  for (const storyDef of storyDefinitions) {
    const storyFields = {
      ...storyDef,
      parent: { key: createdEpic.key }  // Next-Gen: use 'parent', NOT customfield_10014
    };

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

    if (!storyResponse.ok) {
      const error = await storyResponse.text();
      console.error(`Story creation failed: ${error}`);
      continue;
    }

    const createdStory = await storyResponse.json();
    createdStories.push(createdStory);
    console.log(`  Created Story: ${createdStory.key}`);

    // Rate limiting
    await new Promise(r => setTimeout(r, 100));
  }

  return { epic: createdEpic, stories: createdStories };
}

Create Story with Subtasks (Next-Gen)

javascript
async function createStoryWithSubtasks(storyFields, epicKey, subtaskSummaries) {
  const headers = {
    'Authorization': `Basic ${Buffer.from(`${EMAIL}:${TOKEN}`).toString('base64')}`,
    'Content-Type': 'application/json',
    'Accept': 'application/json'
  };

  // 1. Create Story under Epic
  const storyRequest = {
    fields: {
      ...storyFields,
      parent: { key: epicKey }  // Link to Epic
    }
  };

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

  if (!storyResponse.ok) {
    throw new Error(`Story creation failed: ${await storyResponse.text()}`);
  }

  const createdStory = await storyResponse.json();

  // 2. Create Subtasks under Story
  const createdSubtasks = [];
  for (const summary of subtaskSummaries) {
    const subtaskResponse = await fetch(`${JIRA_URL}/rest/api/3/issue`, {
      method: 'POST',
      headers,
      body: JSON.stringify({
        fields: {
          project: { key: storyFields.project.key },
          issuetype: { name: 'Subtask' },  // Next-Gen: 'Subtask', NOT 'Sub-task'
          summary: summary,
          parent: { key: createdStory.key }
        }
      })
    });

    if (subtaskResponse.ok) {
      createdSubtasks.push(await subtaskResponse.json());
    }

    await new Promise(r => setTimeout(r, 50));  // Rate limiting
  }

  return { story: createdStory, subtasks: createdSubtasks };
}

Get Epic Link Field ID

Epic link field varies by Jira instance. Find it:

javascript
async function findEpicLinkField() {
  const response = await fetch(`${JIRA_URL}/rest/api/3/field`, { headers });
  const fields = await response.json();

  const epicLinkField = fields.find(f =>
    f.name === 'Epic Link' ||
    f.name.toLowerCase().includes('epic link')
  );

  return epicLinkField?.id; // Usually customfield_10014
}

Bulk Delete Issues

javascript
async function bulkDeleteIssues(projectKey, maxResults = 100) {
  // Search for all issues
  const jql = encodeURIComponent(`project = ${projectKey} ORDER BY key ASC`);
  const searchResponse = await fetch(
    `${JIRA_URL}/rest/api/3/search/jql?jql=${jql}&maxResults=${maxResults}&fields=key`,
    { headers }
  );
  const { issues } = await searchResponse.json();

  // Delete each issue
  for (const issue of issues) {
    await fetch(`${JIRA_URL}/rest/api/3/issue/${issue.key}?deleteSubtasks=true`, {
      method: 'DELETE',
      headers
    });
    console.log(`Deleted: ${issue.key}`);
    await new Promise(r => setTimeout(r, 100)); // Rate limit
  }

  return issues.length;
}

SAFe Best Practices

Epic Naming

  • Format: [Domain] - [Business Outcome]
  • Example: Marketing Copilot - Enable 24/7 Brand-Aware Content Generation

Story Naming (INVEST Criteria)

  • Independent: Can be developed separately
  • Negotiable: Details can be discussed
  • Valuable: Delivers user value
  • Estimable: Can be sized
  • Small: Fits in a sprint
  • Testable: Has clear acceptance criteria

Story Format

As a [specific persona],
I want [concrete action/capability],
So that [measurable benefit].

Acceptance Criteria (Given-When-Then)

Scenario: [Descriptive name]
GIVEN [initial context/precondition]
WHEN [action/event occurs]
THEN [expected outcome]
AND [additional outcome if needed]

Issue Link Types (Next-Gen)

Link TypeUse CaseField
Parent (Next-Gen)Story → Epicparent: { key: 'EPIC-KEY' }
Parent (Next-Gen)Subtask → Storyparent: { key: 'STORY-KEY' }
Blocks/Is blocked byDependenciesLink type
Relates toRelated itemsLink type

Classic Projects Only:

Link TypeUse CaseField
Epic LinkStory → Epiccustomfield_10014
Epic NameEpic short namecustomfield_10011

Custom Fields by Project Type

Next-Gen (Team-managed) - SCRUM Project

PurposeMethod
Link Story to Epicparent: { key: 'EPIC-KEY' }
Link Subtask to Storyparent: { key: 'STORY-KEY' }
Subtask issue typeissuetype: { name: 'Subtask' }

Classic (Company-managed)

FieldID (typical)Purpose
Epic Linkcustomfield_10014Links Story to Epic
Epic Namecustomfield_10011Short name for Epic
Story Pointscustomfield_10016Estimation
Sprintcustomfield_10007Sprint assignment

Error Handling

javascript
async function safeJiraRequest(url, options = {}) {
  const response = await fetch(url, { ...options, headers });

  if (!response.ok) {
    const error = await response.text();
    throw new Error(`Jira API ${response.status}: ${error.substring(0, 200)}`);
  }

  if (response.status === 204) return null;
  return response.json();
}

References

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Jira Safe AI skill do?

Implement SAFe methodology in Jira. Use when creating Epics, Features, Stories with proper hierarchy, acceptance criteria, and parent-child linking.

Why use Jira Safe on TypingMind?

Because you install it once and use it with any model. Jira Safe is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Jira Safe in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aiskillstore/marketplace/tree/main/skills/01000001-01001110/jira-safe. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Jira Safe?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Jira Safe?

As many as you like. As long as a model supports skills, you can use Jira Safe with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Jira Safe AI skill free?

It is published on GitHub by aiskillstore. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇