agentleFS
aya-talebaya-taleb/productivity-skills/skills/weekly-review/SKILL.md

weekly-review

Skill1 starsChanged 23 days agoMITView on GitHub

One weekly review across every business you run, plus school or anything else you track. Looks back (wins, numbers, what slipped, last week's focus) and sets one focus per business and one overall for next week, then saves it to weekly/YYYY-Www.md. Use it at the end or start of a week, or whenever the user says "weekly review", "let's do my week", "how did this week go", "plan next week", "what should I focus on next week", "Friday wrap-up", "Sunday reset", "I feel scattered across my projects", "what slipped this week". Reads tasks.md, decisions.md and last week's review, so run it even if the user only gives a few numbers.

95 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use quarterly-review, 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.
  • 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

  • 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

  • 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

We split this skill into the rules it gives an agent

12 rules. 0 are common, 9 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 82 edited versions we read keep these.

  • 9

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run python3 <this skill's folder>/../tasks/scripts/tasks.py context.

    line 14
  2. Distinctive:

    Read, in this order:

    line 22
  3. Distinctive:

    No founder-context: ask once for the businesses (short name and stage for each) and say that running the founder-context skill will save …

    line 34
  4. Distinctive:

    No last week's review: say this is the first one and skip the "did last week's focus happen" check.

    line 37
  5. Distinctive:

    No tasks.md or an empty one: say so.

    line 39
  6. Distinctive:

    Use only numbers the user gives or that are written in the files.

    line 44
  7. Distinctive:

    Never estimate, round up or fill a trend from memory.

    line 47
  8. Very specific:

    Always commit to your best pick for every focus line, overall included, and write it in the file.

    line 68
  9. Distinctive:

    Don't invent wins to cheer the user up.

    line 76
  10. Distinctive:

    Keep the review short enough to read in two minutes: about one screen per business at most.

    line 78
  11. Very specific:

    Write weekly/<YYYY>-W<WW>.md in the founder folder with the layout in references/review-template.md.

    line 82
  12. Distinctive:

    Keep the reply short and plain: sentences under 25 words, light formatting (a few bullets or one small table, little bold), no em or en …

    line 96

“Common” is measured: kept by at least 6 in 10 of the 82 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

The anchor of this repo. Someone running several small ventures while studying needs one place, once a week, to see all of them side by side and pick what matters. One focus per business keeps each venture moving. One overall focus says which venture gets the best hours.

Find the files

Run python3 <this skill's folder>/../tasks/scripts/tasks.py context. Below, tasks.py means python3 <this skill's folder>/../tasks/scripts/tasks.py, run from the user's current folder (don't cd into the skill folder; the tool looks for ./founder/ where it runs). It prints the founder folder ($FOUNDER_HOME, a project ./founder/ that already has these files, or ~/.founder/), the businesses from founder-context and the tasks file. If Python is not there, look in ./founder/ and then ~/.founder/ yourself.

Read, in this order:

  1. Businesses: businesses/<slug>.md (name, stage, goals). This is the list of rows in the review.
  2. Last week's review: weekly/<last ISO week>.md. Its focus lines are what you check first.
  3. Tasks: tasks.py list --done-since <Monday of this week>, tasks.py list --overdue, and tasks.py list --due-by +7d. Use --json if you want to count.
  4. Decisions: decisions.md, for any entry whose revisit date is in this week or earlier.

Work out dates with a command (date +%G-W%V, or Python), not in your head. The file name is the ISO week, such as weekly/2026-W43.md. A wrong week number breaks next week's review.

If something is missing

  • No founder-context: ask once for the businesses (short name and stage for each) and say that running the founder-context skill will save them for next time. Never make up a business or its goals.
  • No last week's review: say this is the first one and skip the "did last week's focus happen" check.
  • No tasks.md or an empty one: say so. Ask what got done, don't guess.
  • Batch every question into one message. A review that asks five times does not get finished.

Numbers

Use only numbers the user gives or that are written in the files. Copy them exactly. Basic math on those numbers is fine if you show it ("241, up 29 from 212"). When a business has no number this week, write {{signups this week}} or similar and ask for it once. Never estimate, round up or fill a trend from memory. A review with a made-up number is worse than one with a blank, because next week builds on it.

The review

For each business:

  • Wins: done tasks this week (from Done), plus anything the user says.
  • Numbers: the user's numbers, or placeholders.
  • Slipped: tasks whose due date is before today, and last week's focus if it did not happen. Something due today or later has not slipped yet. Name slips plainly. Ask why only if the user wants to talk about it; the point is to see the slip, not to judge it.
  • Next week's focus: one line, one outcome that can be checked next Friday. "Ship the paywall test to 50 users" beats "work on growth". Pick it from the business goals, the overdue list and what the numbers say. A focus is a step forward, not catch-up admin; overdue chores go under "Carry or drop".

Then overall:

  • Overall focus: which one business gets the first and best hours next week, and why in one sentence. Say which business can idle at maintenance level. Trying to push all of them at once is how all of them stall.

Always commit to your best pick for every focus line, overall included, and write it in the file. Mark it (suggested) until the user agrees, then remove the mark. A blank focus line means next week's review has nothing to check.

  • Revisit: decisions due for a second look, with the date they were due.
  • Carry or drop: overdue tasks to reschedule, move to Someday or drop. List them with how late each is, and ask. Don't recommend which way; the user knows what each one costs.

Be honest. If the week was thin, say so in a plain, kind sentence and move to next week. Don't invent wins to cheer the user up. Real progress, even small, is better encouragement.

Keep the review short enough to read in two minutes: about one screen per business at most.

Save it

Write weekly/<YYYY>-W<WW>.md in the founder folder with the layout in references/review-template.md. Use the save tool so it lands in the same folder the other skills read and never overwrites by accident. Write it in the project first, then put it in place and delete the project copy: tasks.py save weekly/<YYYY>-W<WW>.md --from <project file>. If the file for this week already exists, read it, merge, and save with --replace rather than making a second one. Show the user the focus lines and the path.

Then offer, don't do without a yes:

  • To add each focus as a task due Friday (tasks.py add ... --due friday).
  • To run tasks.py rollover and work through the overdue list.

Reply style

Keep the reply short and plain: sentences under 25 words, light formatting (a few bullets or one small table, little bold), no em or en dashes (write times as 09:00-10:00). Don't guess at consequences ("the site may be down") that the files don't show. Finish with the one-line next step.

Handoff

End the reply with one line on what's next (for example "On Monday, run daily-plan; it reads these focus lines.").

  • Reads: founder-context businesses, tasks.md, decisions.md, last week's weekly/ file.
  • Writes: weekly/YYYY-Www.md; tasks.md only after the user says yes.
  • Next: daily-plan on Monday morning picks up the focus lines. personal-crm's weekly check-in list fits well right after the review. decision-log for anything due to revisit.

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.