Hire an AI weekly focus and decision planner

Everything it can hand back

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

• The worst realistic outcomes, each rated for harm and likelihood, with a repair for each
• The gains from a partial or full win, and the cost of doing nothing at one, five and ten years
• One small step to take within a day
• A short list of what to stop, each with a rule that has a number and a swap
• Your tasks sorted into big and small, three priorities for the week with protected time, and tomorrow's list

How it does the job well

• Pin down the exact question, scope and the standard of evidence needed before searching.
• Prefer primary sources, and say how strong each source is.
• Separate what is established, debated and unknown, with confidence levels.
• Cite specifically: author, work, date or page where possible.

Mistakes it avoids

• Presenting one source or a popular claim as settled.
• Inventing citations, quotes or page numbers.
• Over-generalising across places, periods or groups.

What a good result looks like

An example, not your task: You have a move you have put off for weeks, such as quitting, raising prices or ending a deal.

• Fear-setting plan. Worst realistic outcomes rated for harm and likelihood, a repair for each, the gains, the cost of waiting, and a first step.
• Not-to-do list. Where your time went, the costly few tasks or clients, and stop rules with a number and a swap.
• Weekly big tasks. Tasks sorted into big and small, three priorities with protected time, and tomorrow's list.
• Hand-back summary. Each step's file, any step not run and why, and every missing item in one list.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for 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 Tim Ferriss and Charles Darwin would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Names the worst case. Names the move you are putting off, writes the worst realistic outcomes and rates each one for lasting harm and likelihood.
• Plans the repair. Plans how to repair or limit each one, lists the gains of a partial or full win and prices the cost of doing nothing.
• Finds what eats your time. Uses your plan and last week's calendar to mark habits that cause false emergencies and finds the costly few tasks and clients.
• Writes the stop list. Writes one stop rule per habit with a number or limit, and sets a protected block and a review date.
• Sorts the big from the small. Sorts every open task into big work that pays off and small work that only feels good, and finds the one that makes the others easier.
• Plans the week. Batches or drops the small tasks, tests whether the task you have put off longest is the big one, and picks three priorities.

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 avoided-decision-week 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/avoided-decision-week/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

• The move you are putting off, in one or two sentences
• What you are afraid will happen, and limits that matter, such as savings or a lease (optional)
• A calendar or list of how last week went
• The habits you suspect cost you most
• Every open task, and the hours you really have this week
• Your main goal this month or quarter

Tools and access

• Any good chat AI: Listing, rating and pricing the cost of waiting is plain text work.
• A notebook: Writing the ratings by hand once makes them harder to wave away.
• 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.
• Any good chat AI: Sorting and ranking a task list is text work.
• Your calendar app: Protected time only counts once it is a block in your calendar.

Functions and deliverables

• Weekly focus and decision planner: Work through a delayed decision, decide what to stop doing and make room for the week's most useful tasks.
  • The worst realistic outcomes, each rated for harm and likelihood, with a repair for each
  • The gains from a partial or full win, and the cost of doing nothing at one, five and ten years
  • One small step to take within a day
  • A short list of what to stop, each with a rule that has a number and a swap
  • Your tasks sorted into big and small, three priorities for the week with protected time, and tomorrow's list
• Decision risk and delay planner: Paste the decision you keep putting off. Get a fear-setting plan: worst cases rated, repairs for each, and what waiting costs over 10 years.
  • The worst realistic outcomes, each rated for harm and for odds
  • A repair or limit step for each fear
  • The gains from a partial or full win
  • The cost of doing nothing at one, five and ten years, and a first step for today
• 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
• Weekly big task sorter: Paste your task list and sort your weekly tasks into three priorities that fit your real hours, with small tasks batched or dropped.
  • Each task sorted as big work or small work
  • The one task that makes the others easier, and the task you have put off longest
  • Small tasks batched, handed off or dropped
  • Three priorities for the week with protected time, and tomorrow's list
• Research paper and code note writer: Share a paper, repo or messy notes. Get claims, methods and evidence sorted into a clear research folder.
  • A research folder with claims, methods and results
  • Every claim linked to its supporting table or log
  • Results tables copied with exact numbers
  • A record of dead ends and decisions
  • A short report on what was filled in and what was missing
  Source: Orchestra Research.
• 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
• Charles Darwin: Build a case using Charles Darwin’s recorded approach. Keep facts that challenge your idea, face the hardest objections and show where the evidence stops.
  • Your problem worked on the way Charles Darwin would: their questions, their method, their push-back
  • The answer or the work, in Charles Darwin'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 have a move you have put off for weeks, such as quitting, raising prices or ending a deal.
• Your week fills with small tasks and the one big thing never gets done.
• You keep saying "after this busy stretch," and the stretch never ends.

Limits to check before starting

• The decision is already made and you only need to act: write the first step in your notes and book the time.
• You have routine tasks and no big decision: sort your list by hand, or pick your top three for the day.
• The move puts savings, a lease or legal rights at risk: talk to an accountant, lawyer or other qualified adviser before you act.

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.

• Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Paste the decision, last week's calendar and your task list. It works step by step and saves each result.
• Take the first small step within a day, then follow the stop rules for one week.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/avoided-decision-week 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.