agentleFS
brainsforaibrainsforai/brains-skills/skills/lobes/weekly-review/skill.md

weekly-review

Skill1 starsChanged 5 months agoMITView on GitHub

Skill ID: weekly-review Version: 1.0.0 Domains: personal, productivity Install: fetch this file and follow the "How to use" section Read this file, then set up a weekly review project in the user's Brains knowledge base using the template and instructions below. Create the project structure, initialize the instructions page, and offer to help with this week's review. Filing — important: This lobe is a note template only; it does not choose a folder. Before creating pages, check whether a hippocampus…

92 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use quarterly-review, daily-plan and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Phoenixrr2113Skill

    quarterly-review

    Quarterly review — strategic look at the last 3 months. Career trajectory, project health, life balance, big decisions ahead. Runs 1st of Jan/Apr/Jul/Oct.

    Also in 3 projects that use this

  • steptianSkill

    daily-plan

    每日待办计划与日程管理。触发词:'今天要做'、'今日计划'、'今日待办'、'今天安排'、'安排一下'、'加个任务'、'记个任务'、'今日复盘'、'今日回顾'、'今天总结'、'本周计划'、'周总结'、'开始工作'、'上班了'、'完成了'、'加个日程'、'记个日程'、'改一下时间'、'日程调整'、'面试'、'开会'、'约了'。支持四象限优先级、时段分配、固定日程管理、智能时间估算、每日/每周复盘。当用户提到有明确时间的安排(如'下午两点面试'、'10点开会'),自动识别为日程并写入日程表。

    Also in 3 projects that use this

  • seedprodSkill

    daily-brief

    Send a morning briefing via Telegram with weather, news, and a motivational quote. Designed to run via launchd for automated daily delivery.

    Also in 5 projects that use this

  • Phoenixrr2113Skill

    morning-brief

    Full morning brief — calendar, email, meeting prep, execute actionable items, create follow-up tasks. Runs at 8:03 AM or when Randy asks for a morning update.

    Also in 4 projects that use this

  • zephyrwang6Skill

    daily-review

    每日工作回顾与洞察分析,对用户前一天的对话历史和使用数据进行总结与建议

    Also in 3 projects that use this

  • TheCraigHewittSkill

    research-brief

    Produces a one-page research brief on a topic, person, or company — what they do, what matters, what's changed recently, sources. Use when the user asks to research, look into, brief me on, or get context on a specific topic, company, competitor, or person. Pulls from the web, any project context, and recent emails involving the subject.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. 0 are common, 8 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 80 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read this file, then set up a weekly review project in the user's Brains knowledge base using the template and instructions below.

    line 10
  2. Distinctive:

    When asked to help with this week's review, prompt with open questions — don't ask for raw data.

    line 23
  3. Distinctive:

    When the user is stuck on a section, offer a prompt or example rather than filling it in for them.

    line 24
  4. Distinctive:

    When asked "what patterns do you see?", look across multiple reviews for recurring themes in challenges, lessons, or energy levels.

    line 27
  5. Very specific:

    When asked about energy trends, compare energy_level over time.

    line 28
  6. Very specific:

    When asked "what keeps slipping?", look for items that appear in next_week_goals and then appear again in loose_threads the following week.

    line 29
  7. Very specific:

    When asked to turn a review into next steps, focus on lessons + what_id_do_differently + next_week_goals.

    line 32
  8. Distinctive:

    When asked "what should I focus on next week?", synthesize from goals, loose threads, and recurring patterns — don't just repeat the goals …

    line 33
  9. Distinctive:

    When asked how a specific period went, pull the relevant weeks and give a narrative summary — not a list of bullet points from each week.

    line 36
  10. Distinctive:

    When asked what your wins were in a period, aggregate across weeks and highlight the most significant.

    line 37
  11. Very specific:

    If energy_level is missing, omit it from trend analysis rather than interpolating.

    line 41
  12. Distinctive:

    If sections are short (one bullet), work with what's there — don't pad the analysis.

    line 42
  13. Very specific:

    If loose_threads is empty, that may mean follow-through was good — note that positively rather than ignoring it.

    line 43
  14. Very specific:

    Use this template when creating a new weekly review page.

    line 53

“Common” is measured: kept by at least 6 in 10 of the 80 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
skill.md

Weekly Review Skill

Skill ID: weekly-review
Version: 1.0.0
Domains: personal, productivity
Install: fetch this file and follow the "How to use" section

How to use

Read this file, then set up a weekly review project in the user's Brains knowledge base using the template and instructions below. Create the project structure, initialize the instructions page, and offer to help with this week's review.

Filing — important: This lobe is a note template only; it does not choose a folder. Before creating pages, check whether a hippocampus skill (PARA, Johnny.Decimal, Zettelkasten, or Mind Palace) is active. If one is, ask it where each page belongs and record that path in the page's filed_at field. If no structure is active, fall back to a flat weekly-review/ folder. Never hardcode a location here.


Agent Instructions

You help the user reflect on and learn from their weekly reviews. Pages in this domain follow the Weekly Review template below: each page covers one week, with frontmatter (week_start, energy_level, theme) and sections for wins, challenges, lessons, next-week goals, and loose threads.

Core capabilities

Reflection support

  • When asked to help with this week's review, prompt with open questions — don't ask for raw data. Example: "What moment this week felt most meaningful? What made it hard?" Draw out reflection before asking for the structured fields.
  • When the user is stuck on a section, offer a prompt or example rather than filling it in for them.

Pattern recognition across weeks

  • When asked "what patterns do you see?", look across multiple reviews for recurring themes in challenges, lessons, or energy levels. Name the pattern, not just the data.
  • When asked about energy trends, compare energy_level over time. Flag weeks where energy dropped and surface any adjacent challenges that may explain it.
  • When asked "what keeps slipping?", look for items that appear in next_week_goals and then appear again in loose_threads the following week.

Synthesis into action

  • When asked to turn a review into next steps, focus on lessons + what_id_do_differently + next_week_goals. Translate reflection into concrete actions.
  • When asked "what should I focus on next week?", synthesize from goals, loose threads, and recurring patterns — don't just repeat the goals list.

Retrospective queries

  • When asked how a specific period went, pull the relevant weeks and give a narrative summary — not a list of bullet points from each week.
  • When asked what your wins were in a period, aggregate across weeks and highlight the most significant.

Handling incomplete data

  • If energy_level is missing, omit it from trend analysis rather than interpolating.
  • If sections are short (one bullet), work with what's there — don't pad the analysis.
  • If loose_threads is empty, that may mean follow-through was good — note that positively rather than ignoring it.

Tone

Weekly reviews are personal and often written when the user is tired. Match their energy. Be direct but not clinical. Short, clear observations beat long analyses.


Page Template

Use this template when creating a new weekly review page. This lobe defines the note shape only — it does not pick a folder. The active hippocampus skill decides where it is filed (recorded in filed_at); with no structure active, default to weekly-review/<YYYY-MM-DD>.md.

---
file_type: weekly-review
filed_at: ""
# filed_at: path set by the active hippocampus skill — flat `weekly-review/` folder if no structure active
week_start: ""
# week_start: ISO date of the Monday, e.g. 2026-05-26
energy_level: 
# energy_level: 1–5 (1 = burned out, 5 = fully energized)
theme: ""
# theme: optional one-word label for the week, e.g. "shipping", "recovery", "deep work"
tags: []
---

## Wins

<!-- What went well? List 3–5 things, big or small. -->

-
-
-

## Challenges

<!-- What was hard? What didn't go the way you wanted? Be honest. -->

-
-

## Lessons

<!-- What did you learn — about your work, yourself, or the world? -->

-
-

## What I'd do differently

<!-- If you replayed the week, what one or two things would you change? -->

## Next week: goals

<!-- 3–5 concrete goals. Each should be achievable in one week. -->

- [ ]
- [ ]
- [ ]

## Loose threads

<!-- Things you said you'd do that slipped. Capture them so they don't get lost. -->

-

## Energy note

<!-- Optional. What drained you this week? What gave you energy? -->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.