# Google Tasks Prioritize

> Pulls active Google Tasks from Eisenhower lists (1, 2, 3) and ranks them by group priority plus recent Gmail traffic on each topic. Use when the user asks to prioritize tasks, review what to work on, triage Google Tasks, or rank tasks by email activity.

- Skill: `cgray-redhat/google-tasks-prioritize` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add cgray-redhat/google-tasks-prioritize`
- Raw SKILL.md: https://api.skillmd.com/api/skills/cgray-redhat/google-tasks-prioritize/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: cgray-redhat (https://skillmd.com/u/cgray-redhat)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/cgray-redhat/google-tasks-prioritize

---


# Google Tasks Prioritize

Rank active Google Tasks by Eisenhower group (1 → 2 → 3), then by recent Gmail traffic on each topic.

## Prerequisites

1. `gws` CLI installed and authenticated:
   ```bash
   gws auth status
   ```
2. If auth fails, run `gws auth login` (requires `tasks` and `gmail` scopes).
3. Read `TEAM.md` at the project root (if present) for team mission, programs, and current priorities.

## Workflow

1. **Read `TEAM.md`** at the project root if it exists — who the team is, what we do, and current focus areas (use this to interpret and rank task importance beyond Eisenhower group and email traffic).
2. Run the prioritization script from the project root:
   ```bash
   python3 ~/.cursor/skills/google-tasks-prioritize/scripts/prioritize_tasks.py
   ```
   Optional flags:
   - `--days 14` — email lookback window (default: 14)
   - `--format markdown|json` — output format (default: markdown)
   - `--dry-run` — fetch tasks only, skip Gmail scoring
3. Present the report to the user using the template below.
4. **Add team context** — in the Summary (or a short **Team alignment** note), call out when top tasks map to priorities in `TEAM.md` (if present). Do not invent alignment; only note clear matches.
5. If the script fails, follow the manual fallback in [reference.md](reference.md).

## Output template

```markdown
# Prioritized Tasks — {date}

## Summary
- {count} active tasks across groups 1/2/3
- Top focus: {top 3 task titles}
- Team alignment: {how top tasks relate to TEAM.md priorities, if applicable}

## Group 1 — Urgent and Important
| Rank | Task | Due | Email (14d) | Sources |
...

## Group 2 — Not Urgent / Important
...

## Group 3 — Urgent / Not Important
...
```

Within each group, tasks are ranked by **email traffic score (desc)**, then **due date (asc, overdue first)**, then **title**.

## Scoring (summary)

- **Group 1** = "1 Urgent and Important (DO!!)"
- **Group 2** = "2 Not Urgent / Important (Consider)"
- **Group 3** = "3 Urgent / Not Important (Delegate)"

Email score uses linked Gmail threads first (from `links` and `notes`), then falls back to a title search with `newer_than:14d`. See [reference.md](reference.md) for details.

## Additional resources

- `TEAM.md` at project root — team org, programs, and priorities (if present)
- [reference.md](reference.md) — gws commands, URL parsing, scoring rules