Hire an AI weekly task focus planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• Last week in one line: done, carried over and dropped, against the week before
• Stuck items with three choices each
• Next week's top three outcomes and a plan for your first focus days
• Stop rules, in the weeks where others took most of your time

How it does the job well

• Turn every request into owned actions: who, what and by when.
• Work from the real calendar, notes and lists. Never invent meetings, people or dates.
• Put the most important decision or deadline first, then the details.
• Prepare drafts and proposals. Sending, booking and changing records waits for approval.

Mistakes it avoids

• Dropping tasks to make the list look tidy.
• Rolling the same task forward again and again.
• Planning more than four hours of deep work in one day.
• Adding new rules every week. Two at a time is the limit.
• Losing commitments buried in long notes.
• Mixing confirmed facts with guesses about other people's plans.

What a good result looks like

An example, not your task: You want one steady end-of-week routine, not a fresh effort each Friday.

• Last week. Planned, done, carried over and dropped, with the carry-over share against the week before.
• Stuck items. Tasks carried over three weeks running, each with three choices: drop, shrink or book.
• Stalled projects. Projects that stopped moving, each with one next action.
• Next week's top three. Three outcomes drawn from your list and your focus goal.
• Monday's plan. Focus hours, up to two shallow work windows, and a second focus day if you named one.
• Rules to try. Up to two stop rules, only in weeks when the time check ran.

How the work is checked

• Last week's numbers are counted from the files, not guessed.
• No task that carried over three weeks was rolled forward without a choice.
• The top three outcomes tie to the focus goal, or the answer says there is no goal.
• Nothing was dropped, sent or scheduled without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Seneca and Tim Ferriss would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Read last week. Counts what was done, carried over and dropped, and works out the share that slipped.
• Sort the pile. Only if you bring loose notes or a long unsorted list, it sorts them into tasks, ideas and notes.
• Run the review and update the list. Closes open loops, finds stalled projects and writes the outcome into your task file. Drops stay as proposals.
• Choose the path. A task that slipped three weeks gets three choices. If half the week slipped, it checks where the time went, then adds stop rules if others took most of it.
• Plan the focus days. Protects focus hours for your first working day and one more, and keeps shallow work in two windows.
• Save and hand back. Saves this week's numbers for next time and stops for your yes on every drop.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id weekly-review-keeper only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/weekly-review-keeper/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your task list, ideally the TASKS file from last week
• Loose notes, ideas and unsorted items (optional)
• Last week's calendar, for the weeks the time check runs (optional)
• The one or two outcomes that matter most this month (optional)

Helpful context (optional)

• A short note of what you wanted to finish this month
• Last week's calendar as a list or export

Tools and access

• Claude Code: It can keep the review folder, read the task file and run on a schedule.
• Google Calendar or Outlook: Export last week's blocks here for the time check.
• Any good chat AI: Sorting and adding up a list of blocks is plain text work.
• Your calendar app's export: A real export is faster and more honest than memory.
• Any good chat AI: Writing rules and reply wording from a list of habits is plain text work.
• Your email app's auto-reply and scheduled send: It turns a stop rule into something that runs without willpower.

Functions and deliverables

• Weekly task focus planner: Review unfinished work and choose next week’s priorities. Get stuck-task choices, proposed drops and realistic focus blocks.
  • Last week in one line: done, carried over and dropped, against the week before
  • Stuck items with three choices each
  • Next week's top three outcomes and a plan for your first focus days
  • Stop rules, in the weeks where others took most of your time
• Brain dump organizer: Paste your thoughts. Get grouped projects, tasks, real connections and concrete next-step options, with unclear items flagged.
  • Four clear sections of actions, ideas and notes
  • Your original wording preserved
  • Nothing dropped
  • Output sized to match your input
  Source: Alireza Rezvani.
• Weekly work review planner: Review your lists, calendar and waiting-for items. Get open loops sorted, stalled projects flagged and next week planned.
  • Inventory of open loops
  • Each loop sorted to a list
  • Stalled projects flagged
  • Waiting-for follow-ups
  • Plan for next week
  Source: Alireza Rezvani.
• Task list manager: Keep one task list file current. Tell your AI what you add, finish or wait on, and it moves each item to the right section.
  • A TASKS file with four clear sections
  • Items moved and updated as you report
  • A review of open and stuck work
  Source: Anthropic.
• Weekly time audit planner: Find where your week went. Paste last week's calendar and get your hours sorted into chosen, taken and habit, plus one protected hour a day.
  • Every block of last week, tagged as chosen, taken by others or taken by habit
  • Hours added up in each pile, with each pile's share of the week
  • Your three biggest takers, with what each cost you and who gains
  • One protected hour a day, tied to a named piece of work
  • Each old 'later' turned into a first step with a day and a time
• Not-to-do list builder: Build a not-to-do list from your real week. Each habit gets a stop rule with a number, a swap and a review date. Free, in any chat AI.
  • A short list of what to stop, each with a rule that has a number or limit
  • An 80/20 check on tasks and clients, with any to refer out and a script
  • Wording for auto-replies or agenda rules where they help
  • A protected block, and a review date
• Deep work day planner: Give it your tasks and calendar. Get a schedule with protected focus blocks and shallow work cut back.
  • A schedule table with start time, end time, task and a deep or shallow label for each block
  • Totals for your deep hours and shallow hours
  • A question for each shallow task to help you cut or hand it off
  • A focus-hours log with your weekly total and streak
  • An end-of-day shutdown checklist
  Source: Alireza Rezvani.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up
• Seneca: Review time, priorities or an angry reply using Seneca’s recorded Stoic approach. Count actual choices, examine fears and choose one practical next step.
  • Your problem worked on the way Seneca would: their questions, their method, their push-back
  • The answer or the work, in Seneca's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Tim Ferriss: Plan a decision or crowded week using Tim Ferriss’s recorded approach. Write down fears, question low-value work and choose a small test.
  • Your problem worked on the way Tim Ferriss would: their questions, their method, their push-back
  • The answer or the work, in Tim Ferriss's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You want one steady end-of-week routine, not a fresh effort each Friday.
• The same tasks keep carrying over and you want to face them.
• Your weeks feel full but your main work does not move.

Limits to check before starting

• You have fewer than about ten tasks and one project: run the Weekly work review planner once a month instead.
• You want to sort one messy pile of notes today: use the Brain dump organizer.
• Your calendar is set by other people and you cannot change it: skip the time check and keep the rest.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Use it in Claude Code, where it can save files. Add it as a skill, or save it in .claude/agents. Claude Code needs an Anthropic account and may need a paid plan. A plain chat works too, but it cannot keep the folder.
• Start it by hand each Friday or Sunday: ask it to run this week's review. You can also set a scheduled task, but it will still stop to ask before any change.
• Give it your task list and any loose notes. Add last week's calendar export from Google Calendar or Outlook if the week got away from you.
• Answer its questions on stuck items. Say yes or no to each proposed drop.
• Use the plan for Monday. Run it again next week and it counts against this one.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/weekly-review-keeper for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.