Weekly Reverse Review logo

Weekly Reverse Review

Community
twhsi
weekly-reverse-review

Reverse weekly review for turning inbox noise, daily plans, diaries, calendars, annual plans, and long-range life plans into one happiness-and-peace-centered weekly plan. Use when the user asks for 週檢視, 反向週計劃, 8 Big Rocks, Inbox Zero weekly review, 幸福寧靜週, or wants to synthesize Todoist/inbox notes, daily diaries, calendars, yearly plans, and life plans into iMandalArt/FIRE/JSON outputs.

Overview

Publishertwhsi
Repositoryskills
Skill nameweekly-reverse-review
Stars
259
Forks
37
Bundled files
4
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by twhsi on GitHub. Read the source before you install it.

Installation

Install the Weekly Reverse Review AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/twhsi/skills/tree/main/skills/weekly-reverse-review
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/twhsi/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/weekly-reverse-review .claude/skills/weekly-reverse-review
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Weekly Reverse Review in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Weekly Reverse Review on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Weekly Reverse Review is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Weekly Reverse Review

Purpose

Turn one week of evidence into the next week's meaningful plan by asking:

Is this making me prove myself, or bringing real happiness and peace?

This skill is a reverse planning skill. It does not start by adding tasks. It first gathers evidence from life, removes noise, checks long-range meaning, then produces a compact weekly plan.

Core Principle

Use the center phrase 幸福寧靜週 unless the user gives another five-Han-character center.

Default final question:

那件事情能帶來真正的幸福與寧靜?

Default operating sentence:

少說,陪伴,慢慢做。

Inputs

Gather only the sources available in the user request or local context:

  • Inbox or Todoist export: loose tasks, reminders, and noise.
  • Daily plan / diary / calendar: what actually happened.
  • Year plan / hundred-year life plan: long-range meaning and values.
  • Existing weekly plan: user's human-made 8 Big Rocks.
  • Photos, social posts, TheBrain, AIDA, or other record stores when provided.

When source files are present, read them before synthesizing.

Skill Connections

Use these skills when available and relevant:

  • fire-analysis-card: semantic analysis, numbering, index, route, evolution.
  • imandalart: final 2.01 hard-line weekly 3x3 card.
  • todays-daily-plan: daily plan and diary extraction.
  • markdown-nine-grid-clipboard: Markdown table version of the weekly card.
  • project-note-json-to-epub: publishing-ready project-note JSON when weekly reviews become manuscript material.
  • Calendar skills or apps: calendar evidence, not planning fantasy.

Workflow

  1. Collect evidence

    • Inbox: what is asking for attention?
    • Diary/calendar: what actually happened?
    • Year/life plan: what matters over a longer arc?
    • Existing weekly plan: what the human brain already chose.
  2. Detect imbalance

    • Identify the strongest domain.
    • Identify domains being swallowed by the strongest domain.
    • Health, leisure, and finance often need explicit minimum actions.
  3. Reverse-check motives

    • Is this for proving myself?
    • Is this for real happiness and peace?
    • Does this support family, friendship, service, health, or meaningful work?
    • What should be deleted, delayed, delegated, or downgraded?
  4. Choose weekly rocks

    • Keep eight domains, but make each domain evidence-backed.
    • Give every weak domain a minimum viable action.
    • Convert people meetings into person / theme / next step cards.
    • Convert writing progress into at most three manuscript cards.
  5. Produce outputs

    • Short recommendation.
    • FIRE-style semantic summary when requested or when enough evidence exists.
    • iMandalArt weekly card in the fixed weekly layout.
    • Optional JSON using references/output-json-schema.md.

Fixed Weekly Layout

When generating iMandalArt weekly plans, use the user's weekly-domain layout, not the default process layout:

text
Ⓕ內在 Ⓒ財流 Ⓖ學習
...
...

Ⓑ工作 ◎◎◎◎◎ Ⓓ家庭
... 幸福寧靜週 ...
... ◎◎◎◎◎ ...

Ⓔ社群 Ⓐ健康 Ⓗ休閒
...
...

Read references/weekly-eight-domain-layout.md for the full mapping and phrase guidance.

Reverse Questions

Before finalizing, ask internally:

  • Which one thing brings the most genuine happiness and peace?
  • What can be smaller and still count?
  • Which domain needs a minimum action rather than a heroic plan?
  • Which relationship needs presence instead of advice?
  • Which writing task becomes a card instead of a vague ambition?

Read references/reverse-review-questions.md when the review needs deeper diagnosis.

Default Output

For a normal weekly review, return:

  1. One concise diagnosis.
  2. One iMandalArt weekly card.
  3. Three minimum actions.
  4. Three cards to keep or publish.
  5. One short "do less" note.

Do not over-explain unless the user asks for a full analysis.

Quality Rules

  • Prefer evidence from files over generic productivity advice.
  • Do not optimize only for achievement; optimize for happiness, peace, service, health, and meaningful work.
  • Keep the weekly plan small enough to live.
  • Mark uncertain claims as 待證, 推論, or 需補.
  • If writing or tool-building dominates, explicitly protect health, leisure, and finance.
  • If relationships appear, turn them into presence and next-step cards, not contact chores.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Weekly Reverse Review AI skill do?

Reverse weekly review for turning inbox noise, daily plans, diaries, calendars, annual plans, and long-range life plans into one happiness-and-peace-centered weekly plan. Use when the user asks for 週檢視, 反向週計劃, 8 Big Rocks, Inbox Zero weekly review, 幸福寧靜週, or wants to synthesize Todoist/inbox notes, daily diaries, calendars, yearly plans, and life plans into iMandalArt/FIRE/JSON outputs.

Why use Weekly Reverse Review on TypingMind?

Because you install it once and use it with any model. Weekly Reverse Review is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Weekly Reverse Review in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/twhsi/skills/tree/main/skills/weekly-reverse-review. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Weekly Reverse Review?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Weekly Reverse Review?

As many as you like. As long as a model supports skills, you can use Weekly Reverse Review with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Weekly Reverse Review AI skill free?

It is published on GitHub by twhsi. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇