Jira Worklog Report

Jira: Worklog Report

Read-only. Run from this skill's directory:

python3 ../jira/scripts/jira_tool.py worklog_report [--since -14d] [--until 2026-07-20] [--max_issues 50]

(First-time setup, once per environment: pip install -r ../jira/requirements.txt.)

--since/--until accept a JQL-style relative date (-14d, -2w) or an ISO date/datetime; --since defaults to 14 days ago, --until defaults to now. Prints one JSON document:

{"since": "-14d", "until": null, "total_logged_seconds": 0,
 "total_original_estimate_seconds": 0, "total_delta_seconds": 0,
 "issue_count": 0, "issues": [{"key": "...", "summary": "...",
 "status": "...", "original_estimate_seconds": null,
 "logged_seconds": 0, "delta_seconds": null, "worklogs": [...]}]}

• Only worklogs authored by the current user and started within the window are counted -- never sum or estimate from memory, always run the command fresh.
• original_estimate_seconds (and therefore delta_seconds) is null for any issue with no estimate set. Exclude those issues from an "over/under estimate" claim instead of treating a missing estimate as zero.
• For "what did I get stuck on", reason over each issue's logged_seconds vs. original_estimate_seconds and its worklogs' comment text -- don't just name the top issue by hours without reading what the comments actually say happened.
• Convert *_seconds fields to hours/minutes in your response; don't make the user do that arithmetic.

If the result contains "error", tell the user what went wrong in plain language instead of retrying silently or fabricating a result.

See ../jira/README.md for architecture details and the full environment-variable table.