Hire an AI connected notes planner

Everything it can hand back

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

• A pass or fix on each of the four rules, with the reason.
• At least two link suggestions, each with one line on why the notes belong together.
• Index entries and keywords, so you know where to look the note up later.
• One counter-question from another field, to spark a new note.
• A file path and a daily log entry with intent, changes and open loops.
• For a book or long article, a structure note with a logic tree and a reading order.

How it does the job well

• Never create a note with zero links. Never file into a folder the user calls old or archive.
• Do not skip the four-rule check.
• You cannot save files or update memory from a plain chat. Give the text to paste and say so. Only say a file was written if you wrote it in this session.
• 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: You finished a book or video and want notes you can link and find again.

• Four-rule check. A pass or fix on each rule, with the reason, so you know what to repair.
• Links and index entries. At least two links to other notes with a reason each, plus keywords for finding it later.
• Counter-question. One question from another field that points to a note you have not written yet.
• Filing path. A file name and folder path in the YYYYMMDD style, unless you gave your own rule.
• Daily log entry. Intent, changes and open loops for the task, ready to paste into your log file.
• Structure note (books and long reads). Five key questions, a logic tree and a reading order that tie your small notes together.

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.

Capabilities

• Say whose lens it uses. It opens with your name and says which expert viewpoint fits the task, such as Feynman for learning or Munger for strategy.
• Check the four rules. It asks if the note stands alone, has two or more links, avoids over-sorting and leads to more thinking.
• File and link. It picks a file path, proposes at least two links and one or more index entries, and adds back-links at the bottom.
• Propose links. It lists link candidates and keywords, then asks one counter-question from another field.
• Close the task. It writes the log entry, lists open loops and says if the note is worth sharing.

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 zk-steward 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/zk-steward/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 note, reading summary or task you want filed and linked.
• A list of your existing note titles, so links point to real notes (optional).
• Your name, so each reply opens with it (optional).
• Your folder layout or note naming rule (optional).
• The book, article or video text, if you want a structure note (optional).

Helpful context (optional)

• A list of your note titles, so links are real and not guesses.
• Your existing index or map-of-content note.
• Your past daily log, so open loops carry over.

Tools and access

• Obsidian or any Markdown notes folder: Links in double square brackets and plain files match how this agent names and links notes.
• Claude, ChatGPT or Gemini: Any of them can run the checks. One that can read your folder can find real links itself.

Functions and deliverables

• Connected notes planner: Turn loose notes into a linked knowledge base. Get a four-rule check, link suggestions, index entries and a daily log line. Paste a note.
  • A pass or fix on each of the four rules, with the reason.
  • At least two link suggestions, each with one line on why the notes belong together.
  • Index entries and keywords, so you know where to look the note up later.
  • One counter-question from another field, to spark a new note.
  • A file path and a daily log entry with intent, changes and open loops.
  • For a book or long article, a structure note with a logic tree and a reading order.
  Source: Michael Sitarzewski and Agency Agents contributors.
• AI knowledge file pack builder: Turn your notes and facts into an Open Knowledge Format folder: linked Markdown files your team and AI tools can read, reuse and check.
  • A linked Markdown knowledge folder, optional index and change log, and format review notes.
  Source: Magnus Hedemark.
• Obsidian knowledge base organizer: Build a personal wiki in Obsidian that grows with every source. Your AI files notes, links ideas and flags where sources disagree.
  • New and updated linked wiki pages
  • Cross-references between ideas
  • Flags where sources disagree
  • Answers drawn from the wiki
  Source: Alireza Rezvani.
• Text-to-knowledge-graph builder: Turn a long document into a knowledge graph. Paste your text and get the people, tools and links pulled out, plus a diagram you can paste.
  • A table of entities and their types
  • Relationship triples
  • Graph data ready to load
  • A Mermaid diagram
  • A list of gaps found
  Source: Burhan Sebin.
• 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

Tasks you can use it for

• You finished a book or video and want notes you can link and find again.
• You have a pile of loose notes with no links between them.
• You are starting a note system in Obsidian or plain Markdown files and want clear rules.
• A big task needs to be broken into linked notes, not one long answer.

Limits to check before starting

• You only want clean Obsidian formatting, such as callouts and properties. Use the Obsidian note writer.
• You want what you learned turned into small linked notes and an index for your AI to read. Use the Notes wiki builder.
• You want a graph of people, things and relations pulled out of a text. Use the Text-to-knowledge-graph builder.
• You want book notes with margin marks and no linking system. Use the Book reading routine planner.

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.

• Add the pack to your AI as a skill. In a plain chat, paste SKILL.md first, then your note.
• Paste the note or task. Add your list of note titles if you have one, so links point to real notes.
• Say "Check this note and propose links" or "Break this task into linked notes."
• Read the four-rule check first. Fix any rule marked Fix before you save the note.
• Copy the note, links and log entry into your own notes app. A plain chat cannot save files for you.
• For a book, save the single-idea notes first. Then ask for a structure note that ties them together.

Read it as data

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