Mk:jira Bulk

mk:jira-bulk

Forks to the jira-bulk agent. The agent enforces a hard dry-run-first rule at runtime.

Dry-Run Workflow (MANDATORY)

Step 1: invocation + --dry-run
Step 2: agent shows would_* JSON keys + impacted-count
Step 3: explicit user "yes" → re-invoke without --dry-run

Skipping Step 1 is a hard violation. The agent will refuse if asked to skip the dry-run.

Triggers

• "bulk update N issues"
• "mass transition"
• "transition 50+ issues matching JQL to Done"
• "bulk-clone all PROJ stories tagged 'epic-x' into PROJ2"
• "bulk-delete tickets older than 2 years matching JQL"

Examples

• Mass transition: "transition all PROJ tickets in 'In Progress' for >30 days to Stalled"
• Reassignment: "reassign all open PROJ tickets from alice@ to bob@"
• Cleanup: "delete spam tickets matching JQL 'reporter = ext-bot AND created 50 issues
• references/checkpoint-guide.md — checkpoint + resume strategy for 500+ issue ops
• Workflow cache (read for accurate dry-run output):
• tasks/jira-workflows/.md — discovered statuses + transitions (run bash $CLAUDE_PROJECT_DIR/.claude/skills/jira/scripts/fetch-workflow.sh if absent; see jira-lifecycle/references/workflow-discovery.md)
• For bulk transition --to "", validate the target status name exists in the cache; for --id , validate the transition ID exists. Mismatch → reject before exec.
• Peer leaves: mk:jira-search (JQL author + bulk-update overlap — same dry-run discipline), mk:jira-lifecycle (single-issue transitions; same cache), mk:jira-relationships (bulk-link is here)

Gotchas

• (none yet)

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: ngocsangyem
• Source: ngocsangyem/MeowKit
• License: MIT
• Homepage: https://docs.meowkit.dev/

Install and usage instructions live in the source repository linked above.