Hire an AI chief of staff
Turn your task list and notes into a one-page state of play. Get what needs you now, the decisions waiting, the open hand-offs and one top priority.
What you give
- Your current work as a list or loose notes, with deadlines and who owns each item
- For a decision, the choice, the options and what depends on it
- How you like things laid out, and whether you want one next step at a time (optional)
What you get
- A state of play, with where things stand and today's or this week's one priority
- Every item sorted into three groups, which are tell me now, handle and brief later, and park
- Open hand-offs with an owner and a date
- A list of documents to update after a change, taken only from the names you gave
An example
Your task list is long and you cannot tell what must reach you and what someone else can handle.
You ask: “Turn your task list and notes into a one-page state of play. Use the material I attach and ask for anything essential that is missing.”
You get back:
- State of play. One line on where things stand, the single top priority, and any blockers that need you.
- Sorted items. Every item in tell me now, handle and brief later, or park, with a reason.
- Decisions waiting. Each decision with options, whether it can be undone, the cost of waiting, a recommendation and a date.
An example, not your task.
Hire this specialist
It is free and needs no account. Download the pack, give it to your AI and tell it the job. Your AI asks for anything it is missing, then does the work and checks it.
Related specialists
Details
Everything it can hand back
Your task sets the actual outputs. The specialist picks the methods that cover them.
- A state of play, with where things stand and today's or this week's one priority.
- Every item sorted into three groups, which are tell me now, handle and brief later, and park.
- Each waiting decision with options, the cost of waiting a week, a recommendation and a decide-by date.
- Open hand-offs with an owner and a date.
- A list of documents to update after a change, taken only from the names you gave.
How it does the job well
- You recommend. You do not decide for the user, and you do not claim someone agreed to something they did not.
- Do not state a fact about the user's business, people or dates that they did not give you.
- 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
- Losing commitments buried in long notes.
- Mixing confirmed facts with guesses about other people's plans.
- Adding process when a short checklist would do.
What a good result looks like
An example, not your task: Your task list is long and you cannot tell what must reach you and what someone else can handle.
- State of play. One line on where things stand, the single top priority, and any blockers that need you.
- Sorted items. Every item in tell me now, handle and brief later, or park, with a reason.
- Decisions waiting. Each decision with options, whether it can be undone, the cost of waiting, a recommendation and a date.
- Open hand-offs. What each person or tool owes next, with a date, and what it depends on.
- Documents to update. The documents you named that a change affects, and what to change in each.
- Checks still needed. Facts it could not confirm and the steps only you can do.
How the work is checked
- Every action has an owner and a date, or is marked as missing one.
- Each item points to the note or message it came from.
- The output fits where it will be used, such as one screen or one page.
- 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 Ed Catmull and Stephen Covey would. This is a way of reviewing the work. It does not mean they wrote or endorse it.
Capabilities
- Pick the job. It confirms which of the six jobs you want and what you gave it. Missing facts are marked, not guessed.
- Sort the noise. Each item goes into one of three groups, which are tell me now, handle and brief later, and park, with a reason.
- Lay out decisions. For each decision it asks if it can be reversed, what waiting a week costs and who is affected, then gives a recommendation.
- Trace the knock-on. When something changed, it lists the plans, pages and messages that mention it, from the names you gave.
- Name the owners. Each open item gets an owner and a date. Items with neither are flagged.
- Close out. It lists what is still unchecked and what you must do yourself.
How the role works
- Checks your task, context and available tools.
- Picks the methods needed and prepares a work plan.
- Carries out supported tasks, with each method's limits and review gates.
- Checks the real deliverables and corrects supported faults.
- 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 specialized-chief-of-staff 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/specialized-chief-of-staff/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
- Which job you want, such as daily check-in, weekly closeout, decision, meeting prep, hand-off or document update.
- Your current work as a list or loose notes, with deadlines and who owns each item.
- For a decision, the choice, the options and what depends on it.
- For a document update, what changed and the names of the documents that may be affected (optional).
- How you like things laid out, and whether you want one next step at a time (optional).
Helpful context (optional)
- Last week's state of play note.
- A list of your key documents and which decisions they depend on.
- A line on what you always want to see first, and what you never want to be asked.
Tools and access
- Claude, ChatGPT or Gemini with file upload: You can attach your task export, notes and the documents a change might touch.
- Your task tool or calendar, such as Notion, Trello or Google Calendar: Copy the list out and paste it in. The agent cannot read these tools in a plain chat.
Functions and deliverables
- Chief of staff: Turn your task list and notes into a one-page state of play. Get what needs you now, the decisions waiting, the open hand-offs and one top priority.
- A state of play, with where things stand and today's or this week's one priority.
- Every item sorted into three groups, which are tell me now, handle and brief later, and park.
- Each waiting decision with options, the cost of waiting a week, a recommendation and a decide-by date.
- Open hand-offs with an owner and a date.
- A list of documents to update after a change, taken only from the names you gave.
- Weekly task planner: Share tasks, deadlines and focused hours. Get a week plan with up to three priorities, a time buffer and work to park.
- Every task sized and the gap stated
- The big three placed in real slots
- The rest batched, pushed, dropped or handed off
- A one-line Friday test
- Top-priority shift memo writer: Write a one-page memo that resets your team's top priority after a market change, with a stop and a start for each area.
- A one-page memo of about 450 words with the new top priority in the first lines
- A stop, a start, an owner and a date for each area
- A request to each leader to try the new thing and report one lesson
- A date when the plan is revised, and what would bring it forward
- MISSING lines for anything you did not tell it, so nothing is made up
- 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
- 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
- Ed Catmull: Plan feedback or protect rough creative work using Ed Catmull’s recorded approach. Name the problem, keep the creator’s choice and find hidden issues.
- Your problem worked on the way Ed Catmull would: their questions, their method, their push-back
- The answer or the work, in Ed Catmull's voice, using their ideas by name
- Anything that goes beyond their public record, marked
- One suggested next step
- Stephen Covey: Plan priorities, handoffs or a hard talk using Stephen Covey’s recorded approach. State the goal, listen first and agree a next step.
- Your problem worked on the way Stephen Covey would: their questions, their method, their push-back
- The answer or the work, in Stephen Covey'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
- Your task list is long and you cannot tell what must reach you and what someone else can handle.
- A date or price changed, and you need to know which plans, pages and emails still say the old one.
- You are about to launch or raise money and want a short daily check-in.
- A decision is stuck and you want the options, the cost of waiting and a recommendation on one page.
Limits to check before starting
- You want to sort a week of tasks and loose notes and close the open loops. Use the Weekly task focus planner.
- You only need three priorities from a task list and your real hours. Use the Week priority picker.
- You need meeting notes turned into minutes and next actions. Use the Meeting minutes and action tracker.
- You want one choice written up for the record, with the options you passed on. Use the Decision record writer.
- You want it to send messages, move files or edit your documents. A chat AI cannot do that. It lists what to change.
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 pack from this page and add it to your AI as a skill. Or paste SKILL.md into a new chat, then paste references/source-agent.md after it.
- Say which job you want. For example, "Weekly closeout" or "Help me decide this."
- Paste your tasks, notes and deadlines. Add who owns each item if you know.
- Read the "tell me now" group first. Move anything you disagree with to another group and say why. It learns your line for the rest of the chat.
- Make the changes it lists yourself, or ask for a draft message first. It will not send anything.
- Save the result as your state of play note and paste it back next 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/specialized-chief-of-staff 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.