agentleFS
jcesarperezjcesarperez/claude-em/.claude/skills/jira/SKILL.md

jira

Skill94 starsChanged 5 months agoMITView on GitHub

General-purpose Jira skill for any Jira project. Use for any Jira-related request: creating issues (Epic, Story, Bug, Task, Sub-task), querying issues (in progress, completed, by type/status, bugs by due date), or updating issues. Triggers include: "create an epic", "create a bug", "show me bugs", "epics in progress", "issues completed last N days", "bugs due in N days", or any request involving Jira. Also triggers when any other skill (e.g. write-us, write-epic-build) reaches a "create in Jira" confirmation step or similar.

65 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use confluence, monday and 10 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

  • 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

  • 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

  • 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

Show its rules and text

We split this skill into the rules it gives an agent

15 rules. 0 are common, 5 are distinctive, and 10 are very specific to this project.

  • 0

    Common

    Most of the 58 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 10

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before using this skill, replace the following placeholders throughout this file — including the name: and description: in the frontmatter …

    line 13
  2. Distinctive:

    Delete this section and the "Auto-detection" section below once you've replaced the placeholders.

    line 26
  3. Very specific:

    If {{PROJECT_KEY}} appears literally in this file → ask: *"What is your Jira project key?

    line 34
  4. Very specific:

    If {{CLOUD_ID}} appears literally in this file → ask: *"What is your Atlassian Cloud ID?

    line 35
  5. Very specific:

    If {{BASE_URL}} appears literally in this file → ask: *"What is your Jira domain?

    line 36
  6. Very specific:

    If yes → edit this SKILL.md file, replacing each {{PLACEHOLDER}} with the value the user provided, and confirm when done.

    line 41
  7. Distinctive:

    If no → keep them only for this conversation.

    line 42
  8. Very specific:

    Always prefer the jira CLI: Only fall back to MCP (searchJiraIssuesUsingJql, createJiraIssue, etc.) if the CLI is not available or a …

    line 65
  9. Distinctive:

    If not stated, ask. Options: Epic, Story, Bug, Task, Sub-task.

    line 120
  10. Very specific:

    Always try the CLI first: Do not skip to MCP because the description is long or structured — use --body or pass the description via stdin.

    line 171
  11. Very specific:

    If CLI flags don't support a field, fall back to createJiraIssue MCP with:

    line 183
  12. Very specific:

    Always scope queries to project = {{PROJECT_KEY}} — never query without the team filter

    line 210
  13. Distinctive:

    Never invent issue keys, user IDs, or field values

    line 211
  14. Distinctive:

    If a field value is unknown, ask — don't guess

    line 212
  15. Very specific:

    If the user says "N days", substitute the number directly into the JQL (e.g.

    line 213

“Common” is measured: kept by at least 6 in 10 of the 58 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

Skill: Jira — Project

Manual Setup

Before using this skill, replace the following placeholders throughout this file — including the name: and description: in the frontmatter above:

  • name: → use a short identifier for your project (e.g. jira-platform, jira-core)
  • description: → update "any Jira project" to mention your actual project name, so Claude picks the right skill when you have multiple

Then replace the configuration placeholders:

PlaceholderDescriptionHow to find it
{{PROJECT_KEY}}Your Jira project keyVisible in any issue key (e.g. PLAT-123 → key is PLAT)
{{CLOUD_ID}}Your Atlassian Cloud IDRun jira config list or extract from your Atlassian URL
{{BASE_URL}}Your Jira domaine.g. yourcompany.atlassian.net

Delete this section and the "Auto-detection" section below once you've replaced the placeholders.


Auto-detection (always run this first)

Before doing anything else, check if any placeholder is still unconfigured:

  • If {{PROJECT_KEY}} appears literally in this file → ask: "What is your Jira project key? (e.g. PLAT, ENG, CORE)"
  • If {{CLOUD_ID}} appears literally in this file → ask: "What is your Atlassian Cloud ID? You can find it by running jira config list or from your Atlassian admin URL."
  • If {{BASE_URL}} appears literally in this file → ask: "What is your Jira domain? (e.g. yourcompany.atlassian.net)"

Once the user provides the values, use them for the rest of the conversation without asking again.

Then ask: "Should I save these values in the skill so you don't have to enter them again in future conversations?"

  • If yes → edit this SKILL.md file, replacing each {{PLACEHOLDER}} with the value the user provided, and confirm when done.
  • If no → keep them only for this conversation.

Configuration

FieldValue
Project{{PROJECT_KEY}}
cloudId{{CLOUD_ID}}
Base URL{{BASE_URL}}
AssigneeNone (unless user specifies)
ReporterCurrent user
PriorityMedium (unless user specifies)
ComponentsNone by default
LabelsNone by default

Supported issue types: Epic, Story, Bug, Task, Sub-task


Tool usage

Always prefer the jira CLI. Only fall back to MCP (searchJiraIssuesUsingJql, createJiraIssue, etc.) if the CLI is not available or a specific operation isn't supported by it.

Jira CLI quick reference

# Search / query — using native flags (preferred for simple filters)
jira issue list -p {{PROJECT_KEY}} -a "<email>" -s "<status>" -t <IssueType> \
  --created-after "YYYY-MM-DD" --created-before "YYYY-MM-DD" \
  --plain --columns KEY,SUMMARY,STATUS,ASSIGNEE,PRIORITY \
  --paginate 0:100

# Search / query — using raw JQL (for complex filters)
# ⚠️ Do NOT include ORDER BY in the JQL string — the CLI adds it automatically and will return a 400 error if you include it
jira issue list -p {{PROJECT_KEY}} --jql "<JQL without ORDER BY>"

# Create issue
jira issue create -p {{PROJECT_KEY}} -t <IssueType> -s "<summary>" [flags]

# View issue
jira issue view <ISSUE-KEY>

Prefer native flags over --jql when the filter maps cleanly (assignee, status, type, date range). Use --jql only for filters that have no native flag equivalent (e.g. resolutiondate, custom fields).


A. Querying issues

Identify the query intent and build the appropriate query. Always scope to project = {{PROJECT_KEY}}.

Common queries

User requestPreferred command
Epics in progressjira issue list -p {{PROJECT_KEY}} -t Epic -s "In Progress" --plain --columns KEY,SUMMARY,STATUS,ASSIGNEE --paginate 0:100
Bugs open / in progressjira issue list -p {{PROJECT_KEY}} -t Bug --jql 'project = {{PROJECT_KEY}} AND "customfield_10001" = "82dc66a2-af52-404a-8663-a25bb3c10093" AND issuetype = Bug AND status != Done' --plain --paginate 0:100
Issues completed last N daysjira issue list -p {{PROJECT_KEY}} --jql 'project = {{PROJECT_KEY}} AND "customfield_10001" = "82dc66a2-af52-404a-8663-a25bb3c10093" AND status = Done AND resolutiondate >= -Nd' --plain --paginate 0:100
Issues of type X in status Yjira issue list -p {{PROJECT_KEY}} -t X -s "Y" --plain --paginate 0:100
Bugs due in ≤ N daysjira issue list -p {{PROJECT_KEY}} -t Bug --jql 'project = {{PROJECT_KEY}} AND "customfield_10001" = "82dc66a2-af52-404a-8663-a25bb3c10093" AND issuetype = Bug AND duedate <= Nd AND status != Done' --plain --paginate 0:100
All open issuesjira issue list -p {{PROJECT_KEY}} --jql 'project = {{PROJECT_KEY}} AND "customfield_10001" = "82dc66a2-af52-404a-8663-a25bb3c10093" AND status != Done' --plain --paginate 0:100
Issues by assignee in date rangejira issue list -p {{PROJECT_KEY}} -a "<email>" --created-after "YYYY-MM-DD" --plain --columns KEY,SUMMARY,STATUS,PRIORITY --paginate 0:100

Output format for queries

Show results as a markdown table with columns: Key | Type | Summary | Status | Priority | Due Date | Assignee

Omit columns that are empty for all results. Include a total count at the end.


B. Creating issues

Step 1 — Determine issue type

If not stated, ask. Options: Epic, Story, Bug, Task, Sub-task.

Step 2 — Gather required fields by type

Epic

FieldRequiredNotes
SummaryYesConcise title
DescriptionRecommendedContext and goals
Start DateAskcustomfield_10015 (YYYY-MM-DD)
Due DateAskduedate (YYYY-MM-DD)
ParentNoEpics are top-level by default

Story

FieldRequiredNotes
SummaryYesConcise title, start with verb
DescriptionYesUse Story format (see §C)
Parent EpicAskQuery recent epics if not given; allow null

Bug

FieldRequiredNotes
SummaryYesDescribe the defect clearly
DescriptionYesSteps to reproduce, expected vs actual
PriorityAskDefault Medium; consider High/Critical if user hints urgency
Due DateAskEspecially relevant for bugs
Parent EpicAskOptional

Task

FieldRequiredNotes
SummaryYesAction-oriented title
DescriptionRecommendedWhat needs to be done and why
ParentAskCan be Epic or Story

Sub-task

FieldRequiredNotes
SummaryYes
DescriptionRecommended
ParentRequiredMust have a parent issue key

Step 3 — Draft and confirm

Present the issue draft before creating. Ask the user to confirm or edit.

Do not create in Jira until explicit confirmation.

Step 4 — Create via CLI

Always try the CLI first. Do not skip to MCP because the description is long or structured — use --body or pass the description via stdin. Only fall back to MCP if the CLI command fails or explicitly does not support a required field.

jira issue create \
  -p {{PROJECT_KEY}} \
  -t "<IssueType>" \
  -s "<summary>" \
  [--priority "Medium"] \
  [--custom "duedate=YYYY-MM-DD"] \
  [--parent "<PARENT-KEY>"]

If CLI flags don't support a field, fall back to createJiraIssue MCP with:

{
  "cloudId": "{{CLOUD_ID}}",
  "projectKey": "{{PROJECT_KEY}}",
  "issueType": "<IssueType>",
  "summary": "<summary>",
  "description": "<ADF description>",
  "priority": "Medium",
  "duedate": "YYYY-MM-DD",
  "parent": { "key": "<PARENT-KEY>" }
}

ADF note: When using MCP, description must be in Atlassian Document Format (type: "doc"). Use level-2 headings for sections and paragraphs for content.

Step 5 — Output after creation

Share:

  • Direct link: https://{{BASE_URL}}/browse/{{PROJECT_KEY}}-XXXX
  • Brief summary: type, title, parent (if any), due date (if set)

General rules

  • Always scope queries to project = {{PROJECT_KEY}} — never query without the team filter
  • Never invent issue keys, user IDs, or field values
  • If a field value is unknown, ask — don't guess
  • If the user says "N days", substitute the number directly into the JQL (e.g. -7d)
  • For date fields use ISO format: YYYY-MM-DD

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.