weekly-review

原文涵盖的主题

• Weekly Review — GTD Loop → Trusted System
• What this does
• Phase 1 — GET CLEAR (steps 1-3)
• Phase 2 — GET CURRENT (steps 4-8, all mandatory)
• Phase 3 — GET CREATIVE (steps 9-10)
• Scripts
• References
• Assets

Portability: Reasoning-led skill with 3 stdlib Python scripts. No external APIs, no LLM calls in scripts. Works in Claude Code CLI and Claude.ai web. The scripts do the inventory and the gating; Claude and the user do the thinking. A personal system is only trustworthy if it gets reviewed — David Allen calls the weekly review the critical success factor of the whole method. This skill walks the three phases in order and refuses to call the review COMPLETE while any of the five mandatory GET CURRENT steps is unaccounted for. Evidence first: scan the workspace for open loops before asking the user to recall anything, because their memory is exactly what the method says not to trust. Collect loose inputs, process every inbox to zero (clarify, don't do — anything over two minutes becomes a next action), then a mind sweep to empty the head. Start with evidence: Route every loop found to a list — next action, waiting-for, someday/maybe, or trash. Review the next-action lists (mark done, prune dead), the previous calendar (missed commitments become actions), the upcoming calendar (prepare, don't react), the waiting-for list (chase or drop), and every project for exactly one next action. T

这里只展示节选，请以完整原文和当前要求为准。