From productivity
Review the past week's activity and suggest a prioritised plan for the coming week
npx claudepluginhub seabbs/skills --plugin productivityThis skill uses the workspace's default tool permissions.
Review what happened last week and suggest priorities for the coming week.
Verifies tests pass on completed feature branch, presents options to merge locally, create GitHub PR, keep as-is or discard; executes choice and cleans up worktree.
Guides root cause investigation for bugs, test failures, unexpected behavior, performance issues, and build failures before proposing fixes.
Writes implementation plans from specs for multi-step tasks, mapping files and breaking into TDD bite-sized steps before coding.
Review what happened last week and suggest priorities for the coming week.
Read bot_account, owner_account from the org's CLAUDE.md ## Automation config table.
A pre-built script at ~/.claude/scripts/weekly-plan.sh gathers all planning context in one pass.
Run it first to avoid spending tokens on individual gh and git calls.
~/.claude/scripts/weekly-plan.sh > /tmp/weekly-plan.json
If the script is missing or not executable, flag this to the user and stop.
The script outputs a JSON object with:
today, week_start: date rangedaily_logs: list of available daily log dates from ~/code/claude-log/open_prs: all open PRs by the owner and bot accounts across orgsassigned_issues: all issues assigned to the owner across orgsrecent_commits: commit counts per repo for the past weekprs_merged_this_week, issues_closed_this_week: totalsdaily_logs for narrative contextGroup work into:
Score each item:
Write to ~/code/claude-log/weekly-plan-YYYY-MM-DD.md:
# Weekly plan: YYYY-MM-DD
## Last week summary
- [2-3 sentences on what was accomplished]
- PRs merged: N
- Issues closed: N
- New PRs opened: N
## Blockers
- [ ] item (reason blocked)
## This week's priorities
### Must do
1. item (reason)
### Should do
1. item (reason)
### Could do
1. item (reason)
## Maintenance backlog
- item
Also present the plan in the terminal.
IMPORTANT: If this command is being run as a standalone request, automatically exit after completing all phases successfully.