run-jira
SkillProductivityLets your agent fetch a Jira issue and draft an implementation plan based on your codebase.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the run-jira skill
About this capability
Fetch a Jira issue and propose an implementation plan based on codebase analysis
What this skill tells your AI
The instructions your AI receives, as published by datadog/datadog-agent in .agents/skills/run-jira/SKILL.md and read by ahel’s review.
Fetch the Jira issue $ARGUMENTS from the Datadog Atlassian instance and use it as the basis for a codebase analysis and implementation proposal.
Step 1: Gather Jira issue data
Use the Atlassian MCP tools to fetch the issue. Only request the fields you need to avoid huge responses:
- Call
mcp__atlassian__getJiraIssuewith:cloudId:datadoghq.atlassian.netissueIdOrKey:$ARGUMENTSfields:["summary", "description", "status", "assignee", "issuetype", "comment", "priority"]
- Extract the title (summary), description, status, assignee, and comments from the response.
If the issue cannot be found, stop and inform the user.
Step 2: Summarize the issue
Present a clear summary of the Jira issue:
- Key: $ARGUMENTS
- Title: the issue summary
- Status: current status
- Assignee: who is assigned
- Description: the full description
- Comments: any relevant context or discussion from comments
- Link: https://datadoghq.atlassian.net/browse/$ARGUMENTS
Step 3: Fetch linked resources
Scan the issue description and comments for links to external resources and fetch them for additional context:
- Datadog notebooks / postmortems (
app.datadoghq.com/notebook/<id>): usemcp__datadog-mcp__get_datadog_notebookwith the notebook ID - GitHub PRs (
github.com/.../pull/<number>): usegh pr view <number>via Bash - GitLab commits/pipelines or other URLs: use
WebFetchif accessible
This step is critical — linked resources often contain the root cause analysis, timelines, and technical details that the Jira description alone does not capture.
Step 4: Analyze the codebase
Based on the issue requirements and linked resources, explore the codebase to understand:
- Which files and packages are relevant
- Existing patterns and conventions that should be followed
- Dependencies and potential impacts
Use Glob, Grep, and Read tools extensively. For broad exploration, use the Task tool with subagent_type=Explore.
Step 5: Propose an implementation
Enter plan mode with EnterPlanMode and write a detailed implementation plan that includes:
- A breakdown of the changes needed, organized by file
- Any new files that need to be created
- Test strategy
- Potential risks or open questions
Wait for user approval before implementing.
Signals
- GitHub stars
- 4k
- Forks
- 1k
- Last commit
- Sep 2026
ahel review
S4info
community integration — published by datadog, not jira
Automated review, not a security audit. Ruleset v1.
Advanced
- Catalog kind
- skill
- Gateway key
run-jira- Source
- github.com/datadog/datadog-agent