agentleFS
siddathsiddath/lifeOS/.claude/skills/setup/SKILL.md

setup

Skill7 starsChanged 23 days agoMITView on GitHub

First-run onboarding for a fresh LifeOS clone. Use when the owner says "set up LifeOS", "onboard me", "get started", "make this mine", or is running the vault for the first time. Runs an AI-guided interview, writes dashboard/lifeos.config.json, invites a brain-dump about their life, maps it into the schemas and templates, and generates the first daily brief.

  • Reads credentials

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask, a few at a time (accept partial answers, infer sensible defaults, confirm rather than interrogate):

    line 14
  2. Very specific:

    Use templates/ for any new note's shape.

    line 39
  3. Distinctive:

    Write real files, not just suggestions — onboarding should leave the vault populated.

    line 46
  4. Distinctive:

    Keep the owner's own words in their notes.

    line 48
  5. Distinctive:

    Stop when the vault renders end-to-end with the real owner.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Setup — Make this LifeOS yours

This is the front door. A fresh clone ships with the "Alex Rivera" demo persona so everything renders; this skill replaces it with the real owner. Be warm, brief, and concrete — ask a little, write real files, show a result fast. Don't turn onboarding into a planning marathon.

The contract you are filling lives in schemas/. Read schemas/lifeos.config.schema.json before writing config, and the other schemas before writing any state.

Phase 1 — Identity interview (short)

Ask, a few at a time (accept partial answers, infer sensible defaults, confirm rather than interrogate):

  1. Name — full name + what they like to be called (owner.name, owner.shortName, owner.greeting).
  2. Where / when — timezone (IANA, e.g. America/Los_Angeles), locale (BCP-47), currency (ISO 4217).
  3. Life areas — the handful of areas they want to track. Offer a starter set and let them edit. Each becomes an entry in areas[] with a lowercase code (^[a-z0-9_]+$), a label, and an emoji.
  4. Modules — which parts to switch on (modules): missions, trackers, finance, knowledge_base, anchor, flashcards. Default most on, flashcards off.
  5. Current hero mission (if missions is on) — the one outcome they're racing toward right now, and its gate date. This seeds dashboard/mission.json.

Phase 2 — Write dashboard/lifeos.config.json

Copy dashboard/lifeos.config.example.json to dashboard/lifeos.config.json and replace the demo values, validated against schemas/lifeos.config.schema.json. It holds identity + toggles, not secrets — but it is personal data. Check the instance is private first: if this clone is (or pushes to) a public repo, tell the owner to move to a private repo (private clone, or a new private repo from the template) before committing personal config or data. In a private instance, committing the config inside dashboard/ (the deploy root) is what makes a hosted dashboard render as the owner instead of the demo persona. Keep the product block. Leave integrations.*.enabled false until the owner wires them (secrets go in .env, never here).

Phase 3 — "Paste anything about your life"

Invite the owner: "Paste anything — a brain-dump, an old journal, notes, goals, whatever. Messy is fine. I'll sort it." Then map what they give you into the vault, honoring the schemas:

  • Tasks → dashboard/tasks-data.json (shape: tasks.schema.json — title, area code, priority, status). This seeds an empty browser once. If the dashboard has already been used, reconcile its private backup before changing the seed; file edits do not replace browser entries. Mirror to 06_Trackers/tasks.md only if the owner wants a long-form vault copy.
  • Habits / routines → dashboard/habits-data.json (habits.schema.json) — the weekly matrix seeds an empty browser from this file, then saves edits in browser storage.
  • "About me" facts (strengths, values, watch-outs, preferences, one per area) → dashboard/kb-data.json following kb.schema.json. This is the surface the Knowledge Base page renders — it reads the JSON, not markdown. Keep 02_Areas/knowledge_base/*.md as an optional long-form layer.
  • Dated things → 06_Trackers/reminders.md.
  • Loose ideas / worries → 06_Trackers/inbox.md (append, timestamped).
  • A fresh clone ships tracker templates — create a needed live tracker from its template in the private instance. Markdown trackers, JSON seeds and current browser state are separate write surfaces; none automatically updates the others. Use docs/browser-data.md to reconcile them. Never clear browser storage to force a seed refresh.
  • Area notes → one file per area under 02_Areas/, each starting with frontmatter (title/area/type/tags/updated).
  • The hero mission → dashboard/mission.json following mission.schema.json (pick a slug, fill hero, week, evidence). Snapshot the demo mission into archive/ first if you're replacing it.

Use templates/ for any new note's shape. Tag every task and note with an area code that exists in the config — don't invent new ones.

Phase 4 — First daily brief

Once state exists, run the daily-brief skill so the owner immediately sees the payoff: a calm "here's today" built from their own mission and tasks. Then point them at 00_START_HERE.md and the dashboard.

Rules

  • Write real files, not just suggestions — onboarding should leave the vault populated.
  • Confirm before overwriting the demo persona's files; snapshot demo content to archive/ rather than deleting outright.
  • Keep the owner's own words in their notes; you organize, you don't rewrite their voice.
  • Stop when the vault renders end-to-end with the real owner. Don't gold-plate the first session.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.