packages/skills-catalog/skills/(development)/jira-assistant/SKILL.md
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).
npx skillsauth add tech-leads-club/agent-skills jira-assistantInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are an expert in using Atlassian MCP tools to interact with Jira.
Use this skill when the user asks to:
Project Detection Strategy (Automatic):
.cursor/rules/jira-config.mdcWhen you activate this skill:
.cursor/rules/jira-config.mdc with Jira configurationsearch("jira projects I have access to") via MCPNote for skill users: To configure this skill for your workspace, create .cursor/rules/jira-config.mdc with your project details.
Use search (Rovo Search) first for general queries:
search("issues in {PROJECT_KEY} project")
search("tasks assigned to me")
search("bugs in progress")
{PROJECT_KEY} with the detected project key from configurationUse 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"
Depending on what you have:
fetch(ari)getJiraIssue(cloudId, issueKey)ALWAYS use the detected projectKey and cloudId from configuration
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:
parent field with parent issue key)editJiraIssue(cloudId, issueKey, fields)
1. Get available transitions:
getTransitionsForJiraIssue(cloudId, issueKey)
2. Apply transition:
transitionJiraIssue(cloudId, issueKey, transitionId)
addCommentToJiraIssue(cloudId, issueKey, comment)
ALWAYS use this template in the description field when creating issues:
## 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]
description fieldsearch first for natural language queriesproject = {PROJECT_KEY})parent field with parent issue keyUser: "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 validation
- [ ] Secure existing endpoints
## Acceptance Criteria
- [ ] Users can login with credentials
- [ ] JWT tokens are generated on successful login
- [ ] Protected endpoints validate tokens
- [ ] Invalid tokens return 401
## Technical Notes
Use bcrypt for password hashing, JWT for tokens, and implement refresh token logic.
## Estimate
5 story points"
)
Note: Use actual values from detected configuration in place of placeholders.
User: "Find my in-progress tasks and update the first one"
1. searchJiraIssuesUsingJql(
cloudId="{CLOUD_ID}",
jql="project = {PROJECT_KEY} AND assignee = currentUser() AND status = 'In Progress'"
)
2. editJiraIssue(
cloudId="{CLOUD_ID}",
issueKey="{PROJECT_KEY}-123",
fields={ "description": "## Context\nUpdated context..." }
)
Note: Replace placeholders with detected configuration values.
User: "Move task {PROJECT_KEY}-456 to Done"
1. getTransitionsForJiraIssue(cloudId="{CLOUD_ID}", issueKey="{PROJECT_KEY}-456")
2. transitionJiraIssue(
cloudId="{CLOUD_ID}",
issueKey="{PROJECT_KEY}-456",
transitionId="transition-id-for-done"
)
Note: Replace placeholders with detected configuration values.
User: "Create a subtask for {PROJECT_KEY}-789"
createJiraIssue(
cloudId="{CLOUD_ID}",
projectKey="{PROJECT_KEY}",
issueTypeName="Subtask",
parent="{PROJECT_KEY}-789",
summary="Implement validation logic",
description="## Context\nSubtask for implementing input validation..."
)
Note: Replace placeholders with detected configuration values.
All queries MUST include project = {PROJECT_KEY} (use detected project key):
# My current work
project = {PROJECT_KEY} AND assignee = currentUser() AND status = "In Progress"
# Recent issues
project = {PROJECT_KEY} AND created >= -7d
# High priority bugs
project = {PROJECT_KEY} AND type = Bug AND priority = High
# Epics without completion
project = {PROJECT_KEY} AND type = Epic AND status != Done
# Unassigned tasks
project = {PROJECT_KEY} AND assignee is EMPTY AND status = "To Do"
# Issues updated this week
project = {PROJECT_KEY} AND updated >= startOfWeek()
Note: Replace {PROJECT_KEY} with the actual project key from detected configuration.
project = {PROJECT_KEY} in JQL queries.cursor/rules/jira-config.mdc or ask usertools
Feature planning and implementation with 4 adaptive phases (Specify, Design, Tasks, Execute). Auto-sizes depth by complexity. Writes testable requirements in EARS notation, atomic tasks, atomic Conventional Commits, and requirement traceability. Ships deterministic Python validation scripts so structural gates are enforced by code, not memory. Features an independent Verifier (author != verifier, evidence-or-zero), a discrimination sensor, a decision log (STATE.md), a test-coverage matrix, and a self-improving lessons layer. Stack-agnostic and tool-agnostic. Use when (1) planning features, (2) implementing with verification and atomic commits, (3) validating an implementation against a spec. Triggers on "specify feature", "discuss feature", "design", "tasks", "implement", "validate", "verify work", "UAT", "record decision", "pause work", "resume work". Do NOT use for pure architecture decomposition analysis or standalone technical design documents.
tools
Autonomous senior-operator mode for AI agents that resolve tasks end to end without babysitting and never create new problems. The agent verifies every claim against real evidence (web search dated to the current month and year, the codebase, and available tools, MCPs, and CLIs); it never guesses, never fakes confidence, and never claims something is done without proof. It stays silent and keeps working, interrupting the user only on three stops, namely a destructive or irreversible action, a dead-end with no evidence after exhausting sources, or genuine ambiguity that changes the outcome. Output is short, literal, and human. Use when the user says "not-your-babysitter", "nanny mode", "work autonomously", "stop babysitting", or "no hand-holding", or wants an agent that solves problems on its own, especially hands-on engineering and operational tasks. Do not use when the user explicitly wants a tutorial, a verbose walkthrough, or open-ended brainstorming.
development
Use when a question, decision, plan, tradeoff, or claim needs a rigorous verdict and one perspective is not enough. Spawns a panel of 3 to 5 subagent jurors that form independent blind opinions, deliberate anonymously under an anti-anchoring and anti-sycophancy protocol, and return one committed verdict with confidence, preserved dissent, and a concrete next action. Domain-agnostic across engineering, architecture, data, product, hiring, strategy, vendor choice, build-vs-buy, and research design. Trigger phrases include "convene a jury", "have agents debate and decide", "get a panel to decide", "multi-agent decision", "stress-test this and decide", "monte um juri", "tribunal de agentes", "painel para decidir". Do NOT use to only critique without deciding (use the-fool for that), to build a plan or write the solution itself, or for simple factual lookups.
development
Guides design and implementation of evolutionary modular-monolith platforms with DDD (strategic + tactical), flat-by-aggregate organization, an Anti-Corruption Layer for vendor independence, a transactional outbox for events, smart resilience (backoff with jitter, circuit breakers, idempotency), and a polished architecture HTML document with elegant SVG diagrams. Use when designing a platform or backend, defining bounded contexts, organizing modules and folders, choosing monolith vs microservices, decoupling from an external service (ERP, storage, AI), making calls resilient, adding real-time push, picking a 2026 TypeScript stack (Nx, NestJS, React), or producing an architecture document or diagram. Also triggers on 'modular monolith', 'bounded contexts', 'flat-by-aggregate', 'ports and adapters', 'architecture diagram'. Do NOT use for simple CRUD, NestJS-only deep implementation (use nestjs-modular-monolith), or pure domain-model review (use tactical-ddd).