agentleFS
sd0xdevsd0xdev/sd0x-dev-flow/skills/jira/SKILL.md

jira

Skill192 starsChanged 37 days agoMITView on GitHub

Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).

62 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use confluence, meet and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • SpillwaveSolutionsSkill

    confluence

    Manage Confluence documentation with downloads, uploads, conversions, and diagrams. Use when asked to "download Confluence pages", "upload to Confluence", "convert Wiki Markup", "sync markdown to Confluence", "create Confluence page", or "handle Confluence images".

    Also in 9 projects that use this

  • kv0906Skill

    meet

    Process meeting notes into structured notes with extracted decisions, blockers, and action items. Use for "/meet project type title" then paste notes.

    Also in 3 projects that use this

  • er1chuSkill

    monday

    Full Monday morning setup. Creates week folder, pulls carry-forward, and generates briefing in one pass. Use on Monday mornings or when the user says "monday", "start my week", or "monday morning".

    Also in 3 projects that use this

  • refly-aiSkill

    hubspot

    Integrate with HubSpot for CRM management. Use when you need to: (1) manage contacts and deals, (2) track sales pipelines, or (3) automate marketing and CRM workflows.

    Also in 4 projects that use this

  • koderoverSkill

    jenkins

    Jenkins CI/CD 操作。用于:(1) 触发 Jenkins 任务构建 (2) 查询任务状态和构建历史 (3) 获取构建日志 (4) 操作 Jenkins 节点和配置

    Also in 3 projects that use this

  • SentrySkill

    datadog

    Query live Datadog telemetry (logs, metrics, traces, spans, monitors, incidents, dashboards, services, hosts) through Datadog's Pup CLI. Use when users ask to investigate production behavior in Datadog, including searching logs, checking monitor status, inspecting traces or spans, looking up incidents, finding services, or correlating metrics. Do not use it for Sentry issues, repository/source-code work, or ticketing.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 55 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do NOT persist cloudId. Resolve at runtime each time.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 55 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Jira Skill

View Jira issues, generate branch names from tickets, transition issue status — all via Atlassian MCP.

Trigger

  • Keywords: jira, ticket, issue key ([A-Z][A-Z0-9]+-\d+), branch from ticket, transition status, start work, pr opened, pr merged
  • User says /jira

When NOT to Use

  • GitHub Issues → use /issue-analyze
  • Searching Jira issues → v1.1 (deferred)
  • Generic project management

Input Parsing

Extract issueKey and optional host from user input:

Input FormatExampleExtraction
Bare keyOK-51513key=OK-51513
Full URLhttps://foo.atlassian.net/browse/OK-51513key=OK-51513, host=foo.atlassian.net
Software URLhttps://foo.atlassian.net/jira/software/.../OK-51513key=OK-51513, host=foo.atlassian.net
Branch context(auto from git branch --show-current)key via {TICKET_PATTERN} regex

Regex:

  • Issue key: ([A-Z][A-Z0-9]+-\d+)
  • Host: https?://([^/]+\.atlassian\.net)

CloudId Resolution

1. Call getAccessibleAtlassianResources()
2. 0 results → error: "Atlassian MCP not configured or unauthorized"
3. 1 result  → use its cloudId automatically
4. N results →
     Host provided and matches?    → use matching cloudId
     Host provided but no match?   → warn: "Host '<host>' not found. Available: ..." → AskUserQuestion to select or abort
     No host?                      → AskUserQuestion to choose instance

Do NOT persist cloudId. Resolve at runtime each time; Claude context naturally caches within a session.

Subcommand: view

StepAction
1Parse input → issueKey (+ host if URL)
2Resolve cloudId
3getJiraIssue(cloudId, issueKey)
4Format output

Output format:

## KEY: Summary

| Field | Value |
|-------|-------|
| Status | ... |
| Assignee | ... |
| Priority | ... |
| Type | ... |
| Created | ... |

### Description
(first 500 chars, truncated if longer)

Subcommand: branch

StepAction
1Parse input → issueKey
2Resolve cloudId
3getJiraIssue → get summary + issuetype
4Map issue type → branch prefix (see references/branch-policy.md)
5Apply --type override if provided
6Generate slug from summary
7Assemble branch name: ${prefix}/${issueKey}-${slug}
8Check collision (local + remote)
9Plan mode: output branch name + command. Execute mode: run git checkout -b

See references/branch-policy.md for full mapping table, slug algorithm, and collision detection.

Plan output (default):

Branch: feat/OK-51513-add-user-profile-page
From: OK-51513 "Add user profile page" (Story)

To create: git checkout -b feat/OK-51513-add-user-profile-page

Execute mode (--execute): run git checkout -b <branch> directly.

Subcommand: transition

StepAction
1Parse input → issueKey + --event value
2Resolve cloudId
3getJiraIssue → current status
4getTransitionsForJiraIssue → available transitions
5Match event → target transition (see references/transition-mapping.md)
6Plan mode: show plan. Execute mode: AskUserQuestion → transitionJiraIssue

See references/transition-mapping.md for event vocabulary, regex patterns, and resolution algorithm.

Plan output (default):

## Transition Plan

- Issue: OK-51513 "Add user profile page"
- Current: To Do
- Event: start_work
- Target: In Progress (transition id: 21)

Execute? /jira transition OK-51513 --event start_work --execute

Subcommand: create

StepAction
1Extract project key from input (bare key like OK, or from issue key prefix)
2Resolve cloudId
3getJiraProjectIssueTypesMetadata(cloudId, projectKey) → list available types
4Validate issue type against available types (case-insensitive match)
5Format description as markdown (see references/create-policy.md)
6Plan mode: display creation plan. Execute mode: AskUserQuestion → createJiraIssue

Input sources (both supported):

  • --summary and --description flags: explicit values
  • Context inference: extract summary and description from user's prompt (structured content like Background, Items, etc.)

MCP call (createJiraIssue):

ParameterSource
cloudIdResolved via step 2
projectKeyFrom input
issueTypeNameValidated against available types
summaryFrom --summary or context
descriptionFormatted markdown from --description or context
contentFormatAlways "markdown"

Plan output (default):

## Create Issue Plan

- Project: OK
- Type: Task
- Summary: P1 Hardening — Quote state machine + Recovery Worker
- Description: (preview first 200 chars...)

Execute? /jira create OK --summary "..." --type Task --execute

Execute output:

✅ Created: OK-51514
https://yourorg.atlassian.net/browse/OK-51514

See references/create-policy.md for description format guidelines, project key extraction, and issue type validation.

Graceful Degradation

FailureMessage
MCP tools not available"Atlassian MCP not connected. Enable Atlassian integration in claude.ai settings."
OAuth expired"Atlassian authorization expired. Please re-authorize."
Issue not found"Issue <KEY> not found. Verify the key and your access permissions."
Transition not available"Cannot execute <event> from current status <status>. Available transitions: ..."
Network error"Atlassian API unreachable. Please retry later."
Project not found"Project '<KEY>' not accessible. Check key and permissions."
Issue type not available"Type '<type>' not in project '<KEY>'. Available: [list from metadata]"

Examples

/jira view OK-51513
→ Displays issue details (summary, status, assignee, priority, type, description)

/jira branch OK-51513
→ Plan: feat/OK-51513-add-user-profile-page

/jira branch OK-51513 --type fix --execute
→ Executes: git checkout -b fix/OK-51513-add-user-profile-page

/jira transition OK-51513 --event start_work
→ Plan: To Do → In Progress

/jira transition OK-51513 --event pr_merged --execute --comment "Merged via PR #42"
→ Executes transition + adds comment

/jira create OK --summary "Fix login timeout" --type Bug
→ Plan: Create Bug in OK

/jira create OK --summary "Add user dashboard" --type Story --description "## Background\nDashboard needed for..." --execute
→ ✅ Created: OK-51515

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.