weekly-review
Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says "/cs:weekly-review". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.
- License 许可
- MIT
- 最近更新
- 2026-10-15
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- weekly-review
- license
- MIT
- metadata
- { "version": "1.0.0", "build_pattern": "Path-B ritual skill — GTD weekly-review loop preserved + deterministic scanner/gate/auditor scripts added", "distinct_from": "reflect (per-conversation reflection, not a recurring cadence); capture (intake that feeds the system, not the review that maintains it); project-management sprint retros (team ceremony, not a personal trusted-system audit)" }
- description
- Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says "/cs:weekly-review". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.
- argument-hint
- [optional: directory or notes to review]
02 资源文件 8
- 资产文件assets/example_weekly_review.md4.1 KB
- 资产文件assets/weekly_review_checklist.md2.4 KB
- 参考文档references/gtd_weekly_review_canon.md6.2 KB
- 参考文档references/open_loop_psychology.md6.0 KB
- 参考文档references/review_cadence_design.md6.2 KB
- 脚本scripts/commitment_auditor.py7.3 KB
- 脚本scripts/open_loop_scanner.py7.6 KB
- 脚本scripts/weekly_review_gate.py9.2 KB
03 SKILL.md 正文
Weekly Review — GTD Loop → Trusted System
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.
What this does
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.
Phase 1 — GET CLEAR (steps 1-3)
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:
# Inventory open loops: unchecked checkboxes, TODO/FIXME markers, stale files
python scripts/open_loop_scanner.py --dir ~/notes --stale-days 14
Route every loop found to a list — next action, waiting-for, someday/maybe, or trash.
Phase 2 — GET CURRENT (steps 4-8, all mandatory)
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. Then gate honestly:
python scripts/weekly_review_gate.py --list # show the numbered ten-step checklist
python scripts/weekly_review_gate.py --done "1,2,3,4,5,6,7,8" --skip "9:no someday list yet"
The gate computes completion %, names every missing step, and exits 0 (COMPLETE) or 2 (INCOMPLETE). An unskipped missing GET CURRENT step always forces INCOMPLETE.
Phase 3 — GET CREATIVE (steps 9-10)
Review someday/maybe (activate, keep, or kill), capture new ideas while the head is clear, then audit the whole commitment portfolio:
python scripts/commitment_auditor.py --input commitments.json
Flags STALLED / NO-NEXT-ACTION / SOMEDAY-CANDIDATE, prints the health formula with the score, and issues HEALTHY / DRIFTING / OVERCOMMITTED. End the review with one named next action.
Scripts
| Script | Role |
|---|---|
scripts/open_loop_scanner.py |
Inventories unchecked checkboxes, TODO/FIXME markers, and stale files across a directory; grouped counts + per-file locations; --json. |
scripts/weekly_review_gate.py |
The ten-step three-phase checklist; --done/--skip/--list; completion % + named gaps → COMPLETE (exit 0) / INCOMPLETE (exit 2). |
scripts/commitment_auditor.py |
Flags stalled and actionless commitments, computes the 0-100 health score with the formula shown → HEALTHY / DRIFTING / OVERCOMMITTED. |
References
references/gtd_weekly_review_canon.md— why the weekly review is the critical success factor; the three-phase structure; cadence discipline (7 sources)references/open_loop_psychology.md— Zeigarnik effect, plan-making research, attention residue: why open loops tax attention (6 sources)references/review_cadence_design.md— horizons of focus, habit anchoring, timeboxing, failure modes, restart-after-lapse (7 sources)
Assets
assets/weekly_review_checklist.md— fillable three-phase checklistassets/example_weekly_review.md— a full worked review (scan → checklist → gate → audit → next action)
Rules
- All five GET CURRENT steps are mandatory; skip only with a stated reason, and the gate still names it.
- Never self-certify — the gate issues the verdict; relay its exit code, don't soften it.
- Process, don't do: during the review, anything over two minutes becomes a next action, not a detour.
- Timebox 60-90 minutes; past two hours, gate what's done honestly and schedule the remainder.
- A lapsed habit restarts with a shorter pass and zero guilt — a review is maintenance, not judgment.
Distinct From (don't reach for the wrong sibling)
productivity/reflect— reflects on one conversation or piece of work, once. The weekly review is a recurring cadence over the whole system.productivity/capture— the intake funnel (brain dump → actions). Capture feeds the system; this review keeps it trusted.project-managementsprint retros — a team ceremony about a shared iteration. This is a personal trusted-system audit.
Version: 1.0.0 · Build pattern: Path-B ritual skill — GTD weekly-review loop preserved + deterministic gate/scanner/auditor scripts added.
04 同仓库更多 Skills
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
eu-ai-act-reviewer
Review user journeys, public content, and codebases for potentially relevant EU AI Act provisions, with exact official citations, evidence gaps, application dates, and plain-language next actions. Use for EU AI Act issue-spotting, not final legal or compliance decisions.
discernment-nudge
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.
academy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.