Official agent skill

Auto Jira

by DataDog in DataDog/datadog-agent

Autonomously work on Jira backlog tickets, creating PRs and shepherding them to merge

OfficialApache-2.0Auto-check passed

Install Auto Jira

skills CLI
$ npx skills add DataDog/datadog-agent --skill auto-jira -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install DataDog/datadog-agent auto-jira --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/DataDog/datadog-agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/auto-jira .claude/skills/auto-jira && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
auto-jira
GitHub stars
3.8k
Token cost
~2.2k tokens
SKILL.md length
810 words
Files
6
Skills in repo
35
Repo updated
First seen
Licence
Apache-2.0

At a glance

Autonomously work on Jira backlog tickets, creating PRs and shepherding them to merge

  • Works in 4 steps: PRE-CHECK with Critic — get APPROVED… → Execute the action — wait for completion → POST-CHECK with Critic — verify it… → …
  • SKILL.md covers Overview, CRITICAL: Serial Operations…, Work Tracking and Workflow Overview, plus 12 more sections
  • Calls git

What it does

Auto Jira is an agent skill from DataDog/datadog-agent, published by the product's own GitHub organization. Autonomously work on Jira backlog tickets, creating PRs and shepherding them to merge

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `README.md`, `ci-validation.md` and `pr-workflow.md`).

It works with Jira. The repository describes itself as: Main repository for Datadog Agent. The licence is Apache-2.0.

Example prompts

  • “/auto-jira”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. PRE-CHECK with Critic — get APPROVED before proceeding
  2. Execute the action — wait for completion
  3. POST-CHECK with Critic — verify it actually happened
  4. Only then — move to the next action

What it can do on your machine

Read from SKILL.md and the folder at commit a706f1a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Auto Jira loads about 2.2k tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 810 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from DataDog/datadog-agent at commit a706f1a, republished under its Apache-2.0 licence (© DataDog). 810 words, ~2,222 tokens.

Download SKILL.mdSave it as .claude/skills/auto-jira/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
auto-jira
description
Autonomously work on Jira backlog tickets, creating PRs and shepherding them to merge
argument-hint
<BOARD-KEY> [--max-cards N] [--before-date YYYY-MM-DD] [--exclude word1,word2]
model
sonnet

Overview

This skill autonomously identifies Jira backlog tickets for a given board that can be worked on without human intervention, implements the code change, and creates draft PRs. Once a draft PR is open, the skill moves on to the next ticket.

Arguments: $ARGUMENTS


CRITICAL: Serial Operations with Verification

For every write action:

  1. PRE-CHECK with Critic — get APPROVED before proceeding
  2. Execute the action — wait for completion
  3. POST-CHECK with Critic — verify it actually happened
  4. Only then — move to the next action

Write actions include: creating PRs, posting Jira comments, pushing commits, transitioning ticket status, assigning tickets.


Work Tracking

Track all work in AUTO_JIRA.md (gitignored, local only):

  • Current ticket being worked on
  • Current PR (if any)
  • CI status and what is blocking
  • Skipped tickets with reasons

NEVER commit this file. Update it as you work, removing notes for completed work and keeping focus on in-progress state and next steps.


Workflow Overview

Per-ticket loop (repeat until --max-cards reached or no eligible tickets):
  1. SELECT TICKET     -> Find eligible ticket from board backlog
  2. CLAIM TICKET      -> Assign to user + add to current sprint
  3. IMPLEMENT         -> Code change
  4. VERIFY            -> Run dda inv test + dda inv linter.go on affected packages (fix before continuing)
  5. COMMIT & PUSH     -> Single focused commit, then git push
  6. CREATE PR (DRAFT) -> Open draft PR against main
  7. FIX PR TITLE      -> Rename to [auto-jira][<KEY>] <description> using gh pr edit
  8. LINK & COMMENT    -> Post PR link on Jira ticket

Supporting Documents

When you need to...Read this
Select or claim a Jira ticketticket-workflow.md
Create a PRpr-workflow.md
Evaluate a ticket that links to CI logsci-validation.md
Debug common issuestroubleshooting.md

Do NOT load all docs at once. Only read what is relevant to the current task.


Parse Arguments

Parse $ARGUMENTS:

  • BOARD (required): Jira project key, e.g. ACTP, AGENTCFG, CONTINT
  • --max-cards N: max PRs to create this run (default: 3)
  • --before-date YYYY-MM-DD: only tickets created before this date (default: 30 days ago)
  • --exclude word1,word2: skip tickets whose title contains any of these words (case-insensitive)

If BOARD is missing, stop and ask the user.

Initialize AUTO_JIRA.md:

markdown
# Auto-JIRA Run — <BOARD> — <TODAY>

## Configuration
- Board: <BOARD>
- Max cards: <N>
- Before date: <BEFORE_DATE>
- Exclude: <EXCLUDED_WORDS or "none">

## In Progress
_none_

## Skipped
_none_

Jira Access

Use the Atlassian MCP tools as the primary method:

mcp__atlassian__searchJiraIssuesUsingJql   — query tickets
mcp__atlassian__getJiraIssue               — fetch ticket details
mcp__atlassian__editJiraIssue              — assign, update fields
mcp__atlassian__transitionJiraIssue        — change status
mcp__atlassian__addCommentToJiraIssue      — add comments
mcp__atlassian__getTransitionsForJiraIssue — list available transitions
mcp__atlassian__atlassianUserInfo          — get your account ID

All calls use cloudId: datadoghq.atlassian.net.

If MCP authentication fails for any reason, STOP. Mark the ticket HOLD and report the failure.


Repository Location

Discover the repository root from the current working tree:

bash
git rev-parse --show-toplevel

Always work from this directory. If this command fails (not in a git repo), stop and inform the user.


Local Environment Setup

Local checks catch problems before CI. Do not skip or work around them:

  • Linter failures → fix the issue, do not use --no-verify
  • Missing tools → dda inv install-tools
  • Pre-commit hook failures → fix the root cause

Ticket Selection Criteria

DO work on tickets that:

  • Status is the first entry of jira_statuses for the team in .ddqa/config.toml (typically To Do)
  • Assignee is empty
  • No parent issue (epics as parents are okay; sub-tasks with a parent ticket are not)
  • Created before <BEFORE_DATE>
  • Label do-not-autosolve is NOT set
  • Title contains none of the excluded words
  • Clear, self-contained description with sufficient context to implement
  • Solvable by a code PR to this repository
  • Not already fixed in the codebase

DO NOT work on tickets that:

  • Are assigned to someone else
  • Require design decisions or cross-team coordination
  • Touch authentication, authorization, cryptography, or secrets handling
  • Are docs-only, infra/config, or process changes with no code change
  • Have vague or missing acceptance criteria
  • Are tracking/umbrella/epic-level tickets

When uncertain → skip. The goal is reliable autonomous completion, not ambitious attempts that get stuck.

Check eligibility quickly — do a codebase search to confirm the issue is not already fixed before starting any implementation work.


Show full SKILL.md (296 more words)Show less

Attribution

Every interaction must be clearly attributed as coming from Auto-JIRA.

PlatformFormat
Jira commentEnd with: — Auto-JIRA (https://github.com/DataDog/datadog-agent/blob/main/.agents/skills/auto-jira/SKILL.md)
GitHub PR bodyInclude: _Created by [Auto-JIRA](https://github.com/DataDog/datadog-agent/blob/main/.agents/skills/auto-jira/SKILL.md)._
GitHub commentEnd with: _— [Auto-JIRA](https://github.com/DataDog/datadog-agent/blob/main/.agents/skills/auto-jira/SKILL.md)_
CommitCo-author line: Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

Human Intervention

When something requires human intervention:

  1. Transition the Jira ticket to HOLD (do NOT change other fields)
  2. Add a NEW comment on the ticket explaining exactly what is blocked
  3. Update AUTO_JIRA.md with the blocker
  4. Move to the next ticket (if any)

Triggers:

  • Authentication failures (Jira MCP, GitHub)
  • Unclear requirements that cannot be resolved from ticket context
  • Security-sensitive changes discovered during implementation

Completion Signals

Print TASK COMPLETED only when ALL are true:

  • No more eligible tickets in the board backlog, OR
  • --max-cards limit has been reached

Print TASK FAILED only when:

  • Authentication is permanently broken and cannot be recovered

After completing one ticket, always check for more work before stopping.


Critic Agent

Every write action needs PRE-CHECK and POST-CHECK.

PRE-ACTION:

Agent(
  prompt="""You are a Critic agent.

MODE: PRE-ACTION

PROPOSED ACTION:
[What you are about to do]

PROPOSED CONTENT:
[The exact message / comment / command]

Verify all factual claims and links. Respond APPROVED or REJECTED with evidence.""",
  subagent_type="general-purpose"
)

POST-ACTION:

Agent(
  prompt="""You are a Critic agent.

MODE: POST-ACTION

ACTION TAKEN:
[What was supposed to happen]

EXPECTED RESULT:
[What should be visible now]

Verify the action actually succeeded. Respond APPROVED or REJECTED with evidence.""",
  subagent_type="general-purpose"
)

If Critic rejects: fix the issues, try again, get a clean APPROVED before continuing.


Important Constraints

  1. NEVER take a ticket assigned to someone else. Check Assignee before claiming.
  2. One focused commit per ticket. Do not create "fix CI" commits.
  3. Never skip hooks (--no-verify) or force-push to main.
  4. Never use git add -A or git add . — stage specific files by name.
  5. Always draft — PRs are created as drafts and left for humans to take from there.
  6. Never commit AUTO_JIRA.md — local tracking only.
  7. Never modify .agents/skills/auto-jira/ — the auto-jira skill must not edit itself. If a ticket would require changes to these files, skip it.

Quick Reference

StateWhen to use
In ProgressActively working on implementation
HOLDBlocked, needs human intervention

Branch naming: auto-jira/<KEY>-brief-description (lowercase, hyphens only)

© DataDog, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files in .agents/skills/auto-jira of DataDog/datadog-agent.

  • SKILL.md
  • README.md
  • ci-validation.md
  • pr-workflow.md
  • ticket-workflow.md
  • troubleshooting.md

Open the folder on GitHubat commit a706f1a

Compare with similar skills

Auto Jira next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Auto Jira compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Auto Jira this skillDataDog/datadog-agent3.8k—~2.2kAutomated safety check: PassApache-2.0
Management Talkthananon/9arm-skills3.2k—~3.2kAutomated safety check: PassNone
YugabyteDB Issue Creatoryugabyte/yugabyte-db11k—~2kAutomated safety check: PassCustom licence
Dynamo Jira TicketDynamoDS/Dynamo2k—~1.1kAutomated safety check: PassApache-2.0
Code Reviewcroffasia/itsaplan913—~2kAutomated safety check: PassAGPL-3.0
Connect Apps with ComposioComposioHQ/awesome-claude-skills77k3 repos~557Automated safety check: PassNone

Similar skills

  • Management Talk

    thananon/9arm-skills

    Rewrite engineer-to-engineer content for engineering-org leadership (VPs, directors, PMs, release managers, execs in an engineering-savvy company) and shape it for the channel it is going to — JIRA…

    3.2k GitHub stars~3.2k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check passed
  • YugabyteDB Issue Creator

    yugabyte/yugabyte-db

    Creates a GitHub issue or JIRA ticket for a YugabyteDB change or bug, after scrubbing customer data, secrets and unreleased details from anything public.

    11k GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Dynamo Jira Ticket

    DynamoDS/Dynamo

    Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.

    2k GitHub stars~1.1k tokensUpdated today
    Testing & QAAuto-check passed
  • Code Review

    croffasia/itsaplan

    A skill your agent uses when reviewing code — a diff, a merge request, a file, a directory, or a feature.

    913 GitHub stars~2k tokensUpdated today
    DevelopmentAuto-check passed
  • Connect Apps with Composio

    ComposioHQ/awesome-claude-skills

    Connects an agent to 1000+ external apps through the Composio Tool Router plugin, so it can actually send emails, create issues and post messages instead of only drafting them.

    77k GitHub starsUsed in 3 repos~557 tokens
    Productivity & AutomationAuto-check passed
  • PR Body

    SAP/spartacus

    Official

    A skill your agent uses when the user asks to generate, write, or draft a pull request (PR) body or description for the current branch.

    784 GitHub stars~499 tokensUpdated today
    DevelopmentAuto-check passed

More from DataDog/datadog-agent

All 35 skills in this repo
  • Triage CI Failure

    DataDog/datadog-agent

    Official

    Classify a failed CI as either caused by an active incident, flakiness, or a true code regression.

    3.8k GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Elicit

    DataDog/datadog-agent

    Official

    Run a structured discovery session to build an Allium specification through conversation.

    3.8k GitHub starsUsed in 1 repo~3.7k tokens
    Auto-check passed
  • Follow PR

    DataDog/datadog-agent

    Official

    Monitor the current PR's GitLab pipeline to completion, then report success, auto-fix, or investigate a failure.

    3.8k GitHub stars~3.2k tokensUpdated today
    Auto-check passed
  • Create Epic Recap

    DataDog/datadog-agent

    Official

    A skill your agent uses when an engineer or manager asks to recap, summarize, or post an update on a Jira Epic — a progress update for an in-progress Epic (how far along it is, what's shipped so…

    3.8k GitHub stars~5k tokensUpdated today
    Auto-check: notes
  • Explain Lading Config

    DataDog/datadog-agent

    Official

    Explains a lading.yaml config file from the regression test suite, using the lading Rust source as ground truth for field meanings and defaults.

    3.8k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Distill

    DataDog/datadog-agent

    Official

    Extract an Allium specification from an existing codebase. An agent skill from DataDog/datadog-agent.

    3.8k GitHub starsUsed in 1 repo~7k tokens
    Auto-check passed

Works with

Questions about Auto Jira

What does Auto Jira do?

Autonomously work on Jira backlog tickets, creating PRs and shepherding them to merge. Auto Jira is an agent skill from DataDog/datadog-agent, published by the product's own GitHub organization.

How do I install Auto Jira in Claude Code?

Run `npx skills add DataDog/datadog-agent --skill auto-jira -a claude-code`. Or copy the skill folder (.agents/skills/auto-jira in DataDog/datadog-agent) into .claude/skills/auto-jira in your project. Claude Code loads it when a task matches its description.

How do I install Auto Jira in Codex?

Run `npx skills add DataDog/datadog-agent --skill auto-jira -a codex`. Or copy the skill folder (.agents/skills/auto-jira in DataDog/datadog-agent) into .agents/skills/auto-jira in your project. Codex loads it when a task matches its description.

Can I use Auto Jira in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DataDog/datadog-agent --skill auto-jira -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/auto-jira, .gemini/skills/auto-jira, .github/skills/auto-jira and .opencode/skills/auto-jira in your project.

What does Auto Jira need to run?

Going by SKILL.md and its folder, Auto Jira needs the command-line tools its instructions call (git).

Does Auto Jira access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Auto Jira safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Auto Jira use?

Auto Jira is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Auto Jira use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Auto Jira?

Skills that share tags, products or a category with Auto Jira: Management Talk (thananon/9arm-skills, 3.2k stars), YugabyteDB Issue Creator (yugabyte/yugabyte-db, 11k stars), Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars) and Code Review (croffasia/itsaplan, 913 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Auto Jira?

DataDog (a GitHub organization, an official publisher) maintains it in DataDog/datadog-agent, which has 3,759 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 9, 2026.

Source: DataDog/datadog-agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.