Jira AssistantSAFE

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

---
alwaysApply: false
---

# Jira Project Configuration

This workspace uses the following Jira configuration:

- **Project Key:** YOUR_PROJECT_KEY
- **Cloud ID:** your-cloud-id-uuid-or-url
- **URL:** https://your-site.atlassian.net/
- **Project Name:** Your Project Name (optional)
- **Board URL:** https://your-site.atlassian.net/jira/software/projects/YOUR_PROJECT_KEY/boards/1 (optional)

# Jira Configuration

- **Project Key:** YOUR_PROJECT_KEY
- **Cloud ID:** your-cloud-id-uuid-or-url
- **URL:** https://your-site.atlassian.net/
- **Project Name:** Your Project Name (optional)
- **Board URL:** https://your-site.atlassian.net/jira/software/projects/YOUR_PROJECT_KEY/boards/1 (optional)

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
description: Manage Jira issues via Atlassian MCP — search, create, update, transition status, and handle sprint tasks. Auto-detects workspace configuration. Use when user says "create a Jira ticket", "update my sprint", "check Jira status", "transition this issue", "search Jira", or "move ticket to done". Do NOT use for Confluence pages (use confluence-assistant).
name: jira-assistant
---

# Jira Assistant

You are an expert in using Atlassian MCP tools to interact with Jira.

## When to Use

Use this skill when the user asks to:

- Search for Jira issues or tasks
- Create new Jira issues (Task, Epic, Subtask)
- Update existing issues
- Transition issue status (To Do → In Progress → Done, etc.)
- Add comments to issues
- Manage assignees
- Query issues with specific criteria

## Configuration

**Project Detection Strategy (Automatic):**

1. **Check workspace rules first**: Look for Jira configuration in `.cursor/rules/jira-config.mdc`
2. **If not found**: Use MCP search tools to discover available projects
3. **If still unclear**: Ask user to specify project key
4. **Use detected values** for all Jira operations in this conversation

### Configuration Detection Workflow

When you activate this skill:

1. Check if workspace has `.cursor/rules/jira-config.mdc` with Jira configuration
2. If found, extract and use: Project Key, Cloud ID, URL, Board URL
3. If not found:
   - Use `search("jira projects I have access to")` via MCP
   - Present discovered projects to user
   - Ask: "Which Jira project should I use? (e.g., KAN, PROJ, DEV)"
4. Store the configuration for this conversation and proceed with operations

**Note for skill users:** To configure this skill for your workspace, create `.cursor/rules/jira-config.mdc` with your project details.

## Workflow

### 1. Finding Issues (Always Start Here)

**Use `search` (Rovo Search) first** for general queries:

```
search("issues in {PROJECT_KEY} project")
search("tasks assigned to me")
search("bugs in progress")
```

- Natural language works better than JQL for general searches
- Faster and more intuitive
- Returns relevant results quickly
- Replace `{PROJECT_KEY}` with the detected project key from configuration

### 2. Searching with Specific Criteria

**Use `searchJiraIssuesUsingJql`** when you need precise filters:

**⚠️ ALWAYS include `project = {PROJECT_KEY}` in JQL queries**

Examples (replace `{PROJECT_KEY}` with detected project key):

```
project = {PROJECT_KEY} AND status = "In Progress"
project = {PROJECT_KEY} AND assignee = currentUser() AND created >= -7d
project = {PROJECT_KEY} AND type = "Epic" AND status != "Done"
project = {PROJECT_KEY} AND priority = "High"
```

### 3. Getting Issue Details

Depending on what you have:

- **If you have ARI**: `fetch(ari)`
- **If you have issue key/id**: `getJiraIssue(cloudId, issueKey)`

### 4. Creating Issues

**ALWAYS use the detected `projectKey` and `cloudId` from configuration**

#### Step-by-step process:

```
a. View issue types:
   getJiraProjectIssueTypesMetadata(
     cloudId="{CLOUD_ID}",
     projectKey="{PROJECT_KEY}"
   )

b. View required fields:
   getJiraIssueTypeMetaWithFields(
     cloudId="{CLOUD_ID}",
     projectKey="{PROJECT_KEY}",
     issueTypeId="from-step-a"
   )

c. Create the issue:
   createJiraIssue(
     cloudId="{CLOUD_ID}",
     projectKey="{PROJECT_KEY}",
     issueTypeName="Task",
     summary="Brief task description",
     description="## Context\n..."
   )
```

**Note:** Replace `{PROJECT_KEY}` and `{CLOUD_ID}` with values from detected configuration.

**Available issue types:**

- Task (default)
- Epic
- Subtask (requires `parent` field with parent issue key)

### 5. Updating and Transitioning Issues

#### Edit fields:

```
editJiraIssue(cloudId, issueKey, fields)
```

#### Change status:

```
1. Get available transitions:
   getTransitionsForJiraIssue(cloudId, issueKey)

2. Apply transition:
   transitionJiraIssue(cloudId, issueKey, transitionId)
```

#### Add comment:

```
addCommentToJiraIssue(cloudId, issueKey, comment)
```

## Default Task Template

**ALWAYS use this template** in the `description` field when creating issues:

```markdown
## Context

[Brief explanation of the problem or need]

## Objective

[What needs to be accomplished]

## Technical Requirements

[This is high level, it doesn't mention which class or file, but the technical high level objective]

- [ ] Requirement 1
- [ ] Requirement 2
- [ ] Requirement 3

## Acceptance Criteria

- [ ] Criteria 1
- [ ] Criteria 2
- [ ] Criteria 3

## Technical Notes

[Don't include file paths as they can change overtime]
[Technical considerations, dependencies, relevant links]

## Estimate

[Time estimate or story points, if applicable]
```

## Best Practices

### ✅ DO

- **Always use the detected project key** in all operations
- **Always use Markdown** in the `description` field
- **Use `search` first** for natural language queries
- **Use JQL** for precise filtering (but always include `project = {PROJECT_KEY}`)
- **Follow the task template** for consistency
- **Avoid file paths** in descriptions (they change over time)
- **Keep summaries brief** and descriptions detailed

### ⚠️ IMPORTANT

- **Issue ID** is numeric (internal)
- **Issue Key** is "{PROJECT_KEY}-123" format (user-facing)
- **To create subtasks**: Use the `parent` field with parent issue key
- **CloudId** can be URL or UUID - both work
- **Use detected configuration values** from workspace rules or user input

## Examples

### Example 1: Create a Task

```
User: "Create a task to implement user authentication"

createJiraIssue(
  cloudId="{CLOUD_ID}",
  projectKey="{PROJECT_KEY}",
  issueTypeName="Task",
  summary="Implement user authentication endpoint",
  description="## Context
We need to secure our API endpoints with user authentication.

## Objective
Implement JWT-based authentication for API access.

## Technical Requirements
- [ ] Create authentication middleware
- [ ] Implement JWT token generation
- [ ] Add token v

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (1)

CLAUDE.md

Gates applied: no_behavioural_pass.