agentleFS
freskhufreskhu/genesis/.claude/skills/weekly-review/SKILL.md

weekly-review

Skill5 starsChanged 6 months agoApache-2.0View on GitHub

Structured weekly check-in: scorecard, wins, losses, priority check, next week's 3 focuses, energy check. Takes 15 minutes. Use when user wants a weekly review, weekly check-in, or mentions 'weekly review'.

99 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use daily-plan, daily-brief 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.
  • 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

  • claude-office-skillsSkill

    meeting-notes

    >

    Also in 8 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

  • JerovinoSkill

    process-inbox

    Processes tasks.md inbox items by triaging each one to its proper location in the vault

    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

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 85 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check for previous reviews to track continuity.

    line 18
  2. Distinctive:

    Ask for 3-5 key metrics. For each: this week's value, trend vs last week, on track for quarterly target?

    line 24
  3. Distinctive:

    Ask: "What went well this week?" Force them to name wins -- this is pattern recognition, not fluff.

    line 28
  4. Distinctive:

    Ask: "What didn't go well?

    line 32
  5. Distinctive:

    If same issue appears in multiple reviews, flag it: "This is the Nth week you've mentioned [X].

    line 34
  6. Very specific:

    15 minutes, not 60: If something needs deeper discussion, suggest /strategic-sparring.

    line 61

“Common” is measured: kept by at least 6 in 10 of the 85 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

Structured 15-minute weekly check-in that replaces vague anxiety with clarity.

Before Starting

Load context from MemPalace:

python3 scripts/palace.py search "owner priorities quarterly goals" --limit 5
python3 scripts/palace.py search "weekly review" --wing owner --limit 3

Check for previous reviews to track continuity.

The Review (Conversational, Not a Form)

1. Scorecard (2 min)

Ask for 3-5 key metrics. For each: this week's value, trend vs last week, on track for quarterly target? Flag anything that moved more than 10%.

2. Wins (2 min)

Ask: "What went well this week?" Force them to name wins -- this is pattern recognition, not fluff. Probe: "Why did that work? Way to do more of it?"

3. Losses & Lessons (3 min)

Ask: "What didn't go well? Where did you waste time?" Then: "What will you do differently next time?" A loss without a lesson is just a bad week.

If same issue appears in multiple reviews, flag it: "This is the Nth week you've mentioned [X]. Symptom of something bigger?"

4. Priority Check (3 min)

For each quarterly priority: progress this week, status (on track / at risk / stalled), blockers.

Hard question: "Did you spend the majority of your time on these priorities, or did other things eat your calendar?"

5. Next Week's Focus (3 min)

"If next week could only have 3 priorities, what are they?" Three. Not five.

For each: what does "done" look like? First action Monday morning? What could prevent it?

6. Energy Check (2 min)

"Scale 1-10, how's your energy?" This is data, not therapy. A 4 three weeks running means burnout incoming. If low: is it a win needed, a decision avoided, a hire needed, or a day off?

Output

Generate clean review document and save:

python3 scripts/palace.py add --wing owner --room reports --hall hall_events --content "[review content]"

Rules

  1. 15 minutes, not 60. If something needs deeper discussion, suggest /strategic-sparring.
  2. Continuity matters. Reference previous reviews. Accountability without judgment.
  3. Three priorities, not thirteen. Push back.
  4. Don't let them skip wins. Founders who only review problems burn out.
  5. Patterns over incidents. One bad week is noise. Three is signal.
  6. Energy check is non-negotiable. Skip metrics before skipping this.
  7. End with clarity. They should know exactly what Monday morning looks like.

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.