← Back to setup
Field Guide

Get the most from every command.

Each command explained in plain language up top, with the depth power users want below — what it does, when to reach for it, a walkthrough, and the advanced moves. New to this? The setup walkthrough gets you running in about five minutes; come back here when you want to go deeper.

Your core toolkit is covered below, then the opt-in second-act managers/career, /projects, /learning — in their own group. Start with the ones you'll reach for daily — /brief, /triage, /prep — and dip into the rest as you need them. Putting a command on a schedule is a one-time setup on the walkthrough's scheduler section.

Start here

A day with your AI OS.

Don't worry about learning commands — learn the moments. Here's how a normal day maps onto your toolkit; the full reference for each command is below.

It's 8:40am. Three meetings ahead and you're not sure what's waiting on you.
/brief

Your whole day on one screen — today's meetings and who's in them, what needs a reply, top priorities, deadlines this week — before your first coffee.

Monday morning, and the weekend piled up sixty unread emails.
/triage

One pass sorts your inbox into Needs Reply / FYI / Noise and flags calendar conflicts. Nothing is sent — just sorted, so you open a clear inbox.

A call in ten minutes and you can't remember where it last landed.
/prep

The invite, the mail thread, the relevant project and people notes, the last decisions and open items — plus the questions likely to come up. You walk in ready.

It's Friday and your status update is due — again.
/weekly

Your weekly review is already drafted — what shipped, what slipped or is blocked, decisions, next week's shape — with a status update ready to edit and send. (Just one project? /status.)

"Wait — what did we actually decide about the redesign?"
/recall

One search across everything you know — your memory and your notes — answered with citations and honest about any gaps. (Want just the deep dive into your notes? /wiki.)

It drafted something in the wrong tone, and you fixed it.
/improve

Correct it once, run /improve, and the lesson becomes a durable rule — the system gets a little more "you" every time you steer it.

Other moments, and the command they call for:

A real decision to weigh — a hire, a vendor, a strategy call/board
A pile of reading, clippings, or meeting transcripts to make sense of/ingest
Learning a topic over many sessions, without losing your place/teach
Explaining a process or system to someone (or yourself)/workflow-visualizer
Protecting it all against a lost or wiped laptop — and bringing it back/backup  ·  /restore
Checking everything's still healthy — connectors, memory, backups/doctor
Keeping your memory lean and true as it grows, or building a new command/memory-prune  ·  /skill-center

New here? The setup walkthrough gets you running in about five minutes. The full reference for every command is just below.

/improve

What it does

Turns a correction you just made into a durable rule, so the system doesn't repeat the same miss — the learning loop that makes it more "you" over time.

When to use it

Right after you fix something — its tone, a wrong assumption, a formatting preference. Claude already jots down some corrections on its own; /improve is how you make the ones that matter stick deliberately. It writes to your own local memory (a plain file you own); nothing leaves your machine.

Walkthrough

  1. After you've corrected it in the conversation, type /improve (or say "remember that" / "bake that in").
  2. It captures what changed this session as a durable memory — a one-fact rule, tagged as a preference or a project fact.
  3. Next time, that rule is in play by default. You can see and edit it — it's a plain file in your memory folder.

A capture looks about like this:

Learned this session
· Status updates: lead with the decision, not the backstory — [[status-lead-with-decision]]
· "Acme" = Acme Robotics, not Acme Foods
Saved to memory. These apply from your next session on.

Power user

/triage

What it does

One pass over your inbox and calendar that sorts the noise for you — mail bucketed into Needs Reply / FYI / Noise, plus your calendar conflicts and free blocks — so you start from a triaged list instead of a full inbox.

When to use it

Monday morning, or any time the inbox has gotten ahead of you. Like /brief it's read-only by default: it reads and sorts, and only drafts a reply, flags a message, or proposes a calendar change when you explicitly ask — and never sends or moves anything without your OK.

Walkthrough

  1. Type /triage (or say "/triage my inbox").
  2. It reads your inbox and calendar from the fast local cache and returns three mail buckets — Needs Reply, FYI, and Noise — plus a calendar read: conflicts and your free blocks.
  3. Act on any line: "draft replies to the Needs Reply ones" (it drafts locally, never sends), "flag the second one", or "find me an hour for the Acme call" — each waits for your approval.

A triage looks about like this:

Needs Reply (3) · Finance — Q3 budget sign-off (2 days) · Sam — roadmap review, wants a time · Legal — vendor SOW redlines
FYI (5) · Two newsletters, release notes, an all-hands recap, a calendar invite
Noise (11) · Promotions and automated notifications — safe to skip
Calendar · Conflict: 14:00 1:1 overlaps the design sync · Free: 09:00–10:00, after 15:30

Power user

/brief

What it does

Your morning brief — today's meetings and who's in them, what's waiting on you, your top priorities, and what's due this week, all on one screen.

When to use it

First thing, before your first call — instead of opening five tabs to reconstruct your day. It's also a good midday reset. Because /brief is read-only, it's the safest command to run anytime: nothing it does can send, post, or change a thing.

Walkthrough

  1. Type /brief.
  2. It reads your calendar and inbox from the fast local cache, plus your project notes, and prints four short sections: Meetings (with who's attending and a one-line prep), Waiting on you, Priorities, and Due this week.
  3. Point at anything in it. Say "prep me for the 2pm" and it hands off to /prep; say "draft a reply to the first one" and it drafts locally — never sends.

A brief looks about like this:

Tue 30 Jun
Meetings · 10:00 Design sync (4 people) — last decision: ship the compare table below the fold · 14:00 1:1 w/ Sam — you owe them the Q3 roadmap
Waiting on you · Reply to Finance re: budget (2 days) · Approve the vendor SOW
Priorities · Website redesign — copy pass · Hiring — close the PM loop
Due this week · Board deck (Thu)

Power user

/prep

What it does

Everything you need for one specific meeting, gathered onto a single page — the invite, the relevant mail thread, your project and people notes, the last decisions and open items — plus a ready-made agenda, talking points, and the questions you're likely to get.

When to use it

Right before a meeting you want to walk into sharp: a client call, a team sync, a 1:1. It's read-only — it pulls together what already exists and drafts an agenda; it sends and changes nothing.

Walkthrough

  1. Type /prep and name the meeting — "/prep my 2pm with the design team" or "prep me for the Acme call".
  2. It finds the calendar invite, pulls the related mail thread, and reads your project and people notes — last decisions, open items, who's attending.
  3. It hands you a one-page pack — Context, Attendees, Agenda, Talking points, Likely questions — that you can edit, or ask it to turn into a follow-up afterward.

A prep looks about like this:

Acme quarterly review · Thu 14:00 · 3 attendees
Context · Renewal is up in 6 weeks; last call they raised onboarding friction
Attendees · Dana (their VP), Chen (their PM), you
Agenda · 1) Onboarding fixes shipped · 2) Q3 roadmap · 3) Renewal terms
Talking points · Support tickets down 40% since the March fix · SSO ships next sprint
Likely questions · "What's the SLA on the migration?" · "Can we add three seats mid-term?"

Power user

/status

What it does

A ready-to-edit status update drafted from your project notes and recent activity — what progressed, what's blocked, decisions needed, and next steps — written in your template and your tone.

When to use it

Whenever you owe someone an update — a project check-in, a stakeholder note — and don't want to start from a blank page. It drafts only; you review and send.

Walkthrough

  1. Type /status and name the project — "/status for the website redesign".
  2. It reads that project's notes and recent activity and drafts an update: Progress, Blocked, Decisions needed, Next steps.
  3. It writes in your tone and format — and if you keep separate external and internal versions, it can draft both. Edit and send; nothing goes out on its own.

A status draft looks about like this:

Website redesign — status · week of 30 Jun
Progress · Compare table moved below the fold; hero copy pass done
Blocked · Waiting on legal sign-off for the new privacy page
Decisions needed · Ship the field guide as a second page? (recommend yes)
Next steps · Author the remaining command pages; QA the mobile nav

Power user

/wiki

What it does

A precedent search over your notes vault — "what did I decide or write about X?" — answered with citations down to the exact note and heading.

When to use it

When you want the deep dive into your own notes specifically: the reasoning behind a past decision, what you wrote on a topic. Read-only recall — it never edits your notes.

Walkthrough

  1. Ask "/wiki the data-migration decision" or "what did I write about pricing?".
  2. It searches your vault and returns the relevant passages, each cited as note > heading so you can open the source.
  3. Follow the citations into your notes, or ask a follow-up to narrow.

A wiki answer looks about like this:

"data-migration decision"
· Chose phased cutover over big-bang — 02 Projects/Migration > Decision
· Rollback: keep the old DB read-only for 30 days — 02 Projects/Migration > Risk
· Related: the vendor SLA thread — 03 Areas/Vendors/Acme > SLA

Power user

/recall

What it does

One question — "what do I know about X?" — answered across all your knowledge at once: your maintained memory, your notes vault, and the work your other commands produce and keep (a tracked list, a strategy doc, research). Ranked together, cited, and honest about where you have gaps.

When to use it

Any time you're sure you decided or noted something but can't find it, or you want the full picture before a meeting or a decision. It's strictly read-only — it never writes to any store.

Walkthrough

  1. Ask it plainly — "/recall what am I tracking on the website redesign" or "have I decided anything about pricing?".
  2. It searches all three sources in one pass — memory, vault, and your commands' work product — and ranks them fairly so no single source drowns out the others (each is scored, normalized, and guaranteed a minimum showing).
  3. It returns one ranked answer with citations, pulls in directly-related notes as context, and ends with an honest Gaps: line naming what it couldn't cover.

A recall looks about like this:

What you know about "website redesign"
Decision · Ship the field guide as a second page — [[field-guide-second-page]]
Note · Compare table below the fold — 02 Projects/Redesign > Layout
Tracking (live) · 11 command docs remaining — product-backlog/BACKLOG.md
Related · Connector-auth refresh, mobile-nav QA
Gaps: nothing recent on the privacy-page copy; the layout note is 3 weeks old

Power user

/weekly

What it does

Your recurring weekly review, pre-built — what shipped, the decisions, what slipped or is blocked, and the shape of next week — plus a ready-to-edit status update to send.

When to use it

End of the week — Friday, or whenever you do your review. Instead of reconstructing the week from memory, you start from a draft that's already assembled. Draft only; you send it.

Walkthrough

  1. Type /weekly.
  2. It reads your project notes and the week's activity and assembles the review: Shipped, Decisions, Slipped / blocked, Next week.
  3. It also drafts your recurring status update in your voice and format, ready to edit and send.

A weekly review looks about like this:

Weekly review · week of 30 Jun
Shipped · Field Guide pilot live · Compare table repositioned · Connector-auth refresh
Decisions · Grew AI-OS to a second public page (the guide)
Slipped / blocked · Long-tail command docs (11 remaining) · Privacy page (legal)
Next week · Author remaining command pages · Recruit the novice test

Sharper this month (monthly) · You corrected status-update openings 3× → now a
standing rule, applied to the last two drafts without a fix · /prep now pulls the
attendee's last email thread — useful for your Monday 1:1s

Power user

/skill-center

What it does

The workshop for your toolkit — find, create, and audit your own commands as your needs grow, following Anthropic's skill-authoring best practices.

When to use it

When the built-in commands don't quite cover something you do repeatedly, or you want to check an existing skill is well-formed. This is the expert on-ramp — how AI-OS grows with you instead of boxing you in.

Walkthrough

  1. Type /skill-center and say what you want — "create a command that drafts my expense report" or "audit my /triage skill".
  2. To create: it scaffolds a new skill to best practices, then you refine it.
  3. To find or audit: it lists your skills and flags ones that could be tightened.

A session looks about like this:

Skill Center
· Installed: 17 commands · 1 flagged (missing a clear trigger)
· Created: /expenses — drafts a monthly report from your receipts folder
Start a fresh session to register the new command.

Power user

/ingest

What it does

Turns raw sources you drop in — clippings, transcripts, meeting or Teams exports, reading — into maintained, interlinked concept pages, so you synthesize once and navigate later instead of re-summarizing the same material every time.

When to use it

When you've collected material you'll want to reuse — research, meeting exports, articles — and don't want a growing pile of unprocessed files. Safety fence: it writes end-to-end only inside your Synthesis folder; everywhere else in your vault it's propose-only (a link into one of your own notes is a suggestion for your review, never a silent edit).

Walkthrough

  1. Drop raw sources into your _inbox/ folder.
  2. Run /ingest. For each source it reads it, then for each distinct idea creates or updates a short, cited concept page (one idea per page) with [[wikilinks]] to sibling pages.
  3. It rebuilds the Synthesis index and archives the raw source to _inbox/processed/ — so your inbox stays clean and your knowledge stays linked.

A run looks about like this:

Ingested 3 sources → 5 concept pages
· New: Synthesis/context-windows.md, Synthesis/rag-vs-finetune.md
· Updated: Synthesis/agent-harness.md (+2 links)
· Archived raws → _inbox/processed/ · Rebuilt Synthesis/index.md
Suggested 2 links into your hand-authored notes — review before applying.

Power user

/memory-prune

What it does

An on-demand health check for your memory — it verifies each memory is still true, fixes drift, rebuilds the index, and flags what's stale or orphaned, proposing deletions for your OK. It never auto-deletes.

When to use it

Every so often as your memory grows, or when answers start feeling out of date. This is the maintenance half of the memory lifecycle — what keeps a long-lived memory true rather than just large.

Walkthrough

  1. Type /memory-prune.
  2. It walks your memories: verifies each is still accurate, converts relative dates ("last week") to absolute, rebuilds the MEMORY.md index (grouped, one line each), and flags orphans and dangling [[links]].
  3. It proposes deletions for your approval — nothing is removed without your OK. A small ledger means it won't re-flag the same items next time.

A run looks about like this:

Memory check · 84 memories
· Fixed 6 relative dates → absolute · Rebuilt MEMORY.md index
· 2 dangling links, 1 orphan flagged
· Proposed for deletion (your OK): "trial ends Friday" (expired) · duplicate of [[acme-contact]]

Power user

/board

What it does

Runs a real decision past a panel of advisor profiles — experts whose thinking you admire, each distilled into a note in your vault — and synthesizes their distinct takes: where they'd agree, where they'd dissent, and a recommendation.

When to use it

For a decision worth several sharp perspectives — a hire, a strategy call, a design trade-off. It's advisory and read-only, grounded only in the profiles you've curated (no external lookups).

Walkthrough

  1. Bring a decision — "ask the board whether to ship the field guide as a second page".
  2. It consults each advisor profile and gives you each one's distinct take, then a synthesis: agreements, dissents, and a recommendation.
  3. To add or refresh an advisor, point it at someone's public work and it builds a profile — how they think, their heuristics, what they'd push back on.

A board run looks about like this:

The board on: "ship docs as a second page?"
· Advisor A (systems) — yes; keep the main page lean, docs are a separate job
· Advisor B (growth) — yes, but link it where users hit friction, not just the footer
· Advisor C (minimalist) — dissents; wary of a second thing to maintain
Synthesis · Strong lean yes; the live risk is maintenance — generate it, don't hand-write.

Power user

/teach

What it does

A stateful tutor for learning a topic over many sessions — it keeps a syllabus and your progress, and picks up each time exactly where you left off.

When to use it

When you're learning something bigger than one sitting — a system, a skill, a subject — and want a course that remembers you rather than starting over each time.

Walkthrough

  1. Say "/teach me system design" (or "continue my system-design lessons").
  2. First time, it builds a syllabus and a per-topic workspace in your vault; after that it resumes where you left off, teaches the next piece, and checks your understanding.
  3. It updates a progress file each session — what you've covered, where you struggled — and adapts the depth to your level.

A session looks about like this:

System design · session 4
Last time: caching, load balancing (you were shaky on cache invalidation)
Today: consistent hashing → a quick check → then sharding
Progress saved to 04 Resources/Learning/system-design/

Power user

/workflow-visualizer

What it does

Turns a system or process you describe into one self-contained interactive HTML diagram — clickable nodes, hover detail — that you can open in a browser.

When to use it

When a wall of text would be clearer as a picture: an architecture, an approval flow, how a project's pieces connect. Good for sharing, or for thinking something through visually.

Walkthrough

  1. Describe the thing — "diagram our release process" or "map out how these services connect".
  2. It builds one self-contained interactive HTML file (up to ~20 nodes, with clickable nodes and hover detail).
  3. It saves the file in your vault (04 Resources/Diagrams/) and gives you the path to open.

A run looks about like this:

Release process → diagram
7 nodes: PR → CI → review → staging → QA → deploy → monitor
Saved: 04 Resources/Diagrams/release-process.html — open it in your browser.

Power user

/backup

What it does

Protects your whole AI-OS — memory, notes, and your skills — against a lost or wiped machine. One command keeps an on-disk history and tucks an encrypted copy into the cloud folder you already sync (the 3-2-1 rule), no setup required.

When to use it

Regularly, and before anything risky — a big cleanup, a migration. Your skills live outside ~/ai-os, so nothing else captures them; this is the one thing that does.

Walkthrough

  1. Type /backup. With no arguments it just works.
  2. It commits your ~/ai-os to its own git history (the cheap, frequent layer), builds a timestamped full snapshot under backups/, encrypts it, and drops the encrypted copy into your synced cloud folder.
  3. You end up with a working copy, on-disk history, and an offsite copy — 3-2-1 — without thinking about it.

A backup looks about like this:

Backup complete
· Committed ~/ai-os (git) · Snapshot backups/2026-06-30T09-12.tar.gz.enc (encrypted)
· Copied offsite → your cloud folder
Memory, notes, and 17 skills all captured.

Power user

/restore

What it does

Brings your whole AI-OS back from a snapshot — after a new laptop, a bad edit, or a lost folder. It picks the newest snapshot, lays everything back, and is fully reversible.

When to use it

When you need your system back — recovery, a fresh machine — or when you want to prove your backups actually work (with --drill, safely). Anything it would overwrite is moved aside first, so a restore can itself be undone.

Walkthrough

  1. Type /restore. It lists the snapshots it can find — local and in your cloud folder — and defaults to the newest.
  2. It lays everything back into place: your memory, notes, and skills.
  3. Anything it would overwrite is moved aside first, so the restore is reversible. Use --dry-run to see exactly what it would change before committing.

A dry run looks about like this:

Restore (dry-run)
Source: backups/2026-06-30T09-12.tar.gz.enc (newest)
Would restore: memory/ (84 notes), notes vault, 17 skills
Existing files → moved to restore-backup/ first — nothing lost.
Re-run without --dry-run to apply.

Power user

/doctor

What it does

A read-only checkup for your system — are your connectors still signed in, your memory and commands healthy, your last backup recent, and is your AI-OS itself up to date? It reports what needs attention and points you at the fix; it changes nothing.

When to use it

Any time something feels off — a command "does nothing", mail looks stale — or as a periodic once-over. It's strictly inspect-and-report: it never changes, deletes, or sends anything.

Walkthrough

  1. Type /doctor.
  2. It checks the six things the platform's own checker can't see: Connectors (via /mcp — the thing most likely to be quietly broken), Memory (exists, rough size, note count, whether a /memory-prune is worth it), Toolkit (which skills are registered under ~/.claude/skills/), Protection (the age of your most recent /backup), Currency (whether your installer build and command roster have fallen behind the current AI-OS — if so, it points you at re-running setup, which upgrades in place), and Standing work (if you've scheduled a manager to draft between sessions, whether it's actually still running — a silently-skipped run is worse than none).
  3. It finishes with a short green / needs-attention summary naming the one or two things worth doing next — and points you to Claude Code's own built-in /doctor for the deeper system layer (install, versions, config).

A checkup looks about like this:

/doctor · AI-OS health
✓ Connectors — Google signed in · Memory — 84 notes (~180 KB), healthy
⚠ Toolkit — 16 of 17 skills registered (/expenses needs a fresh session)
⚠ Protection — last backup 9 days ago → run /backup
⚠ Currency — build 2026.05.12a is behind current 2026.06.30m; missing /restore, /update → re-run setup once to catch up (it upgrades in place, adds only what's new) — after that, /update does this for you
  What's new for you — the newer build's /brief now drafts your morning digest before you're even at your desk
⚠ Standing work — your /projects check-in hasn't run since Jul 1 (expected weekly) → check its routine (a sleeping laptop skips runs)
For install/version checks, run Claude Code's built-in /doctor.

Power user

/capture

What it does

Turns the reasoning of a session you just finished into durable, routed knowledge — the rules and preferences into your memory, the decisions and what-you-learned into your notes vault — so a session that mattered doesn't evaporate when you close it.

When to use it

At the end of a session where real thinking happened — a decision got made, an approach got chosen, you learned something worth keeping. /improve captures a correction into memory; /ingest files raw notes you drop in; /capture is the one that closes a whole working session across both brains. Everything stays in plain files you own; nothing leaves your machine.

Walkthrough

  1. When you finish a session worth keeping, type /capture (or say "write that back").
  2. It distills what was decided and learned, and sorts each piece: memory rules vs a vault decision note.
  3. It proposes the vault note for your OK before writing it; memory rules follow the /improve contract. Both stores stay yours to edit.

Power user

/gift

What it does

Lets you give a capability you've proven to a friend — and safely accept one — as a single plain-markdown file you can both read. Stripping, provenance, and a review-before-install gate are built in.

When to use it

When a command or domain setup has genuinely earned its keep and someone you know would want it — or when a friend sends you theirs.

Walkthrough

  1. "Gift my /expenses command to Sam" — it packages the skill, strips anything personal, shows you the stripped file for your OK, and gives you one file to send.
  2. Sam pastes the file into their Sasha and says "my friend sent me this."
  3. Their Sasha reviews it out loud first — what it is, what it creates, what it reads — and installs only after an explicit yes. The uninstall line is shown up front.

Power user

/update

What it does

Fetches the current setup prompt from the AI-OS repo, checks it's byte-exact against a checksum before touching anything, and hands it into this session as if you'd pasted it yourself — then lets the setup prompt's own upgrade mode (the same one that runs when you paste by hand) decide what's new and wait for your OK. If you're already current, it says so and does nothing else.

When to use it

Any time /doctor's currency check says you're behind, or whenever you feel like checking — it's free to run and does nothing if there's nothing new.

Walkthrough

  1. Type /update.
  2. It checks the current build against yours. Already current → it tells you and stops.
  3. Behind → it shows you what's changing (the same "what's new for you" notes /doctor uses).
  4. If you have Playwright MCP connected, it fetches the prompt and verifies it byte-for-byte before doing anything with it. If verification ever fails, it stops cold and points you at pasting the prompt yourself — same safe path as always, no half-measures.
  5. If you don't have Playwright MCP connected, it tells you plainly and points you at pasting the prompt yourself — same outcome as today, no worse.
  6. When it does fetch clean, the setup prompt's own upgrade mode takes over exactly as if you'd pasted it: it shows you a diff of what it would add and waits for your OK. Nothing changes until you say yes.

Power user

Second act — opt-in managers

These aren't part of the core setup. You hire them after your first win, one paste at a time, from the bench on the setup page — a standing chief-of-staff for one part of your life. Each drafts and proposes; you always approve.

/career

What it does

/career is a standing career chief-of-staff. It learns how you write from a few of your own samples, keeps a living career strategy, and drafts LinkedIn posts in your voice — you always publish; it never posts anything or edits your profile. Everything lives in ~/ai-os/career/, so it shares your memory and /recall.

When to reach for it

When you want to show up in your field on a cadence without it sounding like generic AI, or when you want a standing view of where your career is headed rather than one-off help. It's an opt-in second act — hire it after your core AI-OS is running and you've had your first win, not before.

A walkthrough

The one-time setup interviews you: you paste 3–5 things you're proud of writing (mix a public post, a colleague email, and your bio), answer three short questions about what you want to be known for, and it distills a VOICE.md fingerprint — then reads it back and asks "anything wrong, or just not you?" Once it's running, drive it by mode:

You: /career post about the migration project I just wrapped
/career: Draft (graded against your voice rubric, checked against RULES.md):
"Six months ago we bet on a phased cutover instead of a big-bang migration…"
— sound like you? I can sharpen the open or cut the third line.

Power user & honest limits

/projects

What it does

/projects is a manager for one project you own — it keeps that project's strategy, backlog, and decision log (the same STRATEGY / BACKLOG / DECISIONS shape that runs this very product) and drafts the weekly status update you actually send, pulled from the plan rather than written from scratch. It drafts; you send. It never posts an update or edits a shared doc. Everything lives under ~/ai-os/projects/<slug>/, so it shares your memory and /recall.

When to reach for it

When a project you own needs a steady drumbeat — a status on a cadence, a place decisions don't get lost, a backlog that stays honest — and you'd rather steer than re-draft the update every week. Opt-in second act; hire it after your first win.

A walkthrough

Setup interviews you about the project itself — its goal / North Star and roughly by when, who reads the status, how often you report and what a good update covers, and how you'll know each milestone is truly done — then reads it back and asks "anything wrong or missing?" before it seeds the workspace. Then:

You: /projects update
/projects: Draft weekly status — Website Relaunch, week of Jun 30:
Progress · Checkout redesign shipped to staging…
Risks · Vendor SLA sign-off still open (owner: Procurement)…
Decisions needed · Confirm the phased-cutover date…
— this the update you'd send? I can tighten the risks or add an ask.

Power user & honest limits

/learning

What it does

/learning is a standing strategist for everything you're trying to learn. It keeps a living portfolio of your goals and a prioritized, prerequisite-ordered topic queue across all of them, drafts a roadmap for a goal, and tells you what's gone cold and worth revisiting. It plans; /teach teaches — it hands each topic to /teach (the tutor that already ships with your AI-OS) and never runs a lesson itself. Everything lives in ~/ai-os/learning/, so it shares your memory and /recall.

When to reach for it

When you're trying to learn several things at once and want an order that respects prerequisites and your time, instead of learning at random — and a standing "what should I pick up next, and what have I let go cold?" Opt-in second act; hire it after your first win.

A walkthrough

Setup interviews you about your whole learning portfolio — what you want to be able to do (concrete outcomes), why each matters, what you already know, and how much time you realistically have — then reads back a suggested order and asks "anything wrong or missing?" The first win is a roadmap that ends by handing you off to /teach:

You: /learning roadmap for "ship a small web app"
/learning: Prioritized roadmap (needs-X-first noted):
1. HTML/CSS basics — the surface you'll build on
2. JavaScript fundamentals — needs #1
3. START HERE → a first small page…
When you're ready, run /teach me HTML/CSS basics — it keeps a syllabus and remembers where you struggle.

Power user & honest limits