agentleFS
GerardoRdz96GerardoRdz96/aios-starter-kit/.claude/skills/onboard/SKILL.md

onboard

Skill3 starsChanged 5 months agoMITView on GitHub

Use on Day 1 of an AIOS install, when someone says "set me up", "onboard me", "let's get started", "fill in my AIOS", or has just cloned the kit. Combined wizard — runs the 7-question intake AND scaffolds the Day-1 file set at the end. Idempotent — re-run any time; the working aios-intake.md resets to placeholders after each run (your durable answers live in context/).

  • Reads credentials

171 other projects use a version of this, 9 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use soak-test, team-live-ops 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.
  • lilangMaxSkill

    soak-test

    Generate a soak test protocol for extended play sessions. Defines what to observe, measure, and log during long play sessions to surface slow leaks, fatigue effects, and edge cases that only appear after sustained play. Primarily used in Polish and Release phases.

    Also in 10 projects that use this

  • lilangMaxSkill

    team-live-ops

    Orchestrate the live-ops team for post-launch content planning: coordinates live-ops-designer, economy-designer, analytics-engineer, community-manager, writer, and narrative-director to design and plan a season, event, or live content update.

    Also in 10 projects that use this

  • HK-hubSkill

    teach-impeccable

    One-time setup that gathers design context for your project and saves it to your AI config file. Run once to establish persistent design guidelines.

    Also in 18 projects that use this

  • CoralGameSkill

    team-level

    Orchestrate level design team: level-designer + narrative-director + world-builder + art-director + systems-designer + qa-tester for complete area/level creation.

    Also in 12 projects that use this

  • CoralGameSkill

    playtest-report

    Generates a structured playtest report template or analyzes existing playtest notes into a structured format. Use this to standardize playtest feedback collection and analysis.

    Also in 12 projects that use this

  • HK-hubSkill

    arrange

    Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.

    Also in 13 projects that use this

  • +5 more from lilangMax
  • +1 more from CoralGame

The file

We split this skill into the rules it gives an agent

12 rules. 0 are common, 6 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 159 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the user has already onboarded and wants to refresh: still run.

    line 15
  2. Very specific:

    If the user wants to add a new connection: that's not onboarding — point them at connections.md to edit directly, or schedule a /level-up …

    line 16
  3. Very specific:

    Read aios-intake.md. Check which Q1-Q7 sections have content vs.

    line 24
  4. Very specific:

    Ask one at a time. Write each answer into aios-intake.md as you go (so the user can resume if interrupted).

    line 32
  5. Distinctive:

    Ask for two samples. One email, one post.

    line 42
  6. Distinctive:

    When the user runs the closing prompt ("what should I focus on this week?"), respond using only the new context files.

    line 86
  7. Distinctive:

    The 7-question cap is non-negotiable: Don't add Q8 in conversation.

    line 95
  8. Distinctive:

    Voice paste cannot be skipped: If the user types samples mid-chat, refuse and tell them to paste from real writing.

    line 96
  9. Distinctive:

    One-shot scaffold: After Step 2 ends, write Step 3 files in a single batch.

    line 97
  10. Distinctive:

    Closing screen is a header line + three horizon lines: Not a menu.

    line 99
  11. Very specific:

    No extra skills generated: Don't scaffold /today, /draft, /connect, etc.

    line 100
  12. Very specific:

    No .env writes: Don't ask for API keys on Day 1.

    line 102

“Common” is measured: kept by at least 6 in 10 of the 159 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

What this skill does

Single combined wizard. Reads or writes aios-intake.md (the canonical intake), conducts the 7-question interview if the file isn't filled, then scaffolds the Day-1 file set inline at the end of the run. There's no separate scaffold skill — this is one flow.

The wow moment: at the end, suggest the closing prompt "Try this — ask me: what should I focus on this week?" The user runs it once. That's the wow. There's no /today skill to save — the prompt itself plants the Mindset framework (Default Shift) for them to internalize.

When NOT to run this

  • If the user has already onboarded and wants to refresh: still run; it re-interviews and re-scaffolds, backing up the current context/ files first (the working intake resets to placeholders after each run, so there are no old answers to skip).
  • If the user wants to add a new connection: that's not onboarding — point them at connections.md to edit directly, or schedule a /level-up Phase 2 walk.

Execution

Step 1: Read the intake

First run bash .claude/skills/onboard/scripts/scaffold.sh init (RUN it, don't read it) — it creates the working aios-intake.md from aios-intake.md.template if it's missing, and does nothing otherwise. The template is the canonical pristine intake that ships with the kit; aios-intake.md is the working copy the user fills in.

Read aios-intake.md. Check which Q1-Q7 sections have content vs. [Your answer here] placeholders.

  • All filled → skip Step 2, jump to Step 3 (scaffold).
  • Some filled → ask the user: "I see Q1, Q3, Q4 are answered. Want to fill the rest now, or scaffold from what's there?" Their call.
  • None filled (fresh clone, or reset after a previous run) → run Step 2 conversationally.

Step 2: The interview (7 questions, hard cap)

Ask one at a time. Write each answer into aios-intake.md as you go (so the user can resume if interrupted).

Q1 — Who are you, what do you do, and what should I call myself? Identity, role/offer, and the name the user wants to give this AIOS (the default is Sage — keep it if they don't care). One paragraph for identity/role is fine. Record the chosen AIOS name so the scaffold step can use it.

Q2 — Paste 1-2 things you've written recently. Don't edit them. This is the only question with a hard rule. Voice samples MUST be pasted, not typed mid-conversation. If the user starts typing fresh prose, refuse:

"Stop — paste it raw. If you type it here while we're talking, the sample is already shaped by our conversation. Open your last email or post in another tab and paste the unedited text. This is the one rule I can't bend."

Ask for two samples. One email, one post. Or two of either.

Q3 — What are your 2-3 biggest priorities for the next 90 days? Quarterly priorities. Push back if they say "grow my work" — make them name a number, a deadline, or a deliverable.

Q4 — Where does the value of your work actually land, and where is it tracked? Multiple answers OK. Map to Tier-1 Domain 1 (Outcomes/Financials).

Q5 — Where do you talk to people you work with, your team, and the outside world day-to-day? Email, chat, DMs. Map to Domains 2 + 4.

Q6 — Where do meeting recordings, notes, and important docs live? Map to Domains 6 + 7.

Q7 — What's the one task that eats your week, and where do you currently track work? Capture top_pain (used by /level-up) + Domain 5 (tasks).

Domain 3 (Calendar) is auto-inferred from Q5 (which email/calendar system the user named). Confirm in Step 3.

Step 3: Scaffold the Day-1 file set

Once the intake is complete, first run bash .claude/skills/onboard/scripts/scaffold.sh backup — it backs up the files this step overwrites to archives/intake-{YYYY-MM-DD-HHMM}/. Then generate these files (or update if re-running):

  1. context/about-me.md — from Q1 (identity, role) + Q7 (top_pain). One short paragraph each.
  2. context/about-work.md — from Q1 (what you do) + Q4 (how value lands). One paragraph.
  3. context/priorities.md — from Q3. Numbered list, one line per priority.
  4. references/voice.md — from Q2. Fill the existing template, don't regenerate it. Paste the samples verbatim into its Samples section, and fill the Your register fields (tone, sentence style, punctuation quirks, etc.) if Q2 reveals them. Keep the register fields, the Dos/Don'ts, and the Sources: / Related: provenance footer intact.
  5. connections.md — populate the 7-row table from Q4-Q7 answers. Each row gets mechanism: not yet connected, auth: —, last checked: —. The user wires connections on Day 2.
  6. CLAUDE.md — fill the two real placeholders only: {{ABOUT_ME}} (name + role, from Q1) and {{VOICE_REGISTER}} (a one-line voice summary, from Q2). Then rename the AIOS by running bash .claude/skills/onboard/scripts/scaffold.sh rename "<chosen name>" — a deterministic kit-wide whole-word rename from the default Sage. Never hand-edit the rename; an LLM pass misses occurrences, the script doesn't. If re-running after an earlier rename, pass the current name as a second argument (… rename "<new>" "<current>"). Don't invent a priorities or connections placeholder — priorities live in context/priorities.md and connections in connections.md.

After scaffolding, reset the staging file: run bash .claude/skills/onboard/scripts/scaffold.sh reset — it copies aios-intake.md.template back over aios-intake.md, returning it to placeholders. The user's answers now live in context/; this keeps personal data — especially the pasted voice samples — out of the working intake. (Why a clean staging→durable handoff matters in a re-runnable loop: references/agent-loops.md.)

Step 4: The closing screen

Print one screen — a header line plus three horizon lines (Today / Tomorrow / Day 7):

✓ Day 1 done. Your AIOS knows who you are, what you do, what matters this quarter, and how you sound.

Today: ask me — "what should I focus on this week?"
Tomorrow: pick one tool from connections.md and wire it up (check for a CLI first; if none, write a small API script + save references/{tool}-api.md; MCP last).
Day 7: run /aios-audit to see your score.

When the user runs the closing prompt ("what should I focus on this week?"), respond using only the new context files. Hit:

  • 3-bullet priority list, in their voice register from Q2
  • Each bullet ties back to a stated 90-day priority from Q3
  • Final line: "If I had to pick one thing for Monday, it'd be [X], because [reason from priorities]. Want me to draft the first email? And — where could the Default Shift apply here? To what extent could AI be leveraged on this task?"

The Default Shift question seeds the Mindset framework before /level-up formally introduces it.

Critical implementation rules

  1. The 7-question cap is non-negotiable. Don't add Q8 in conversation. The AIOS name folds into Q1.
  2. Voice paste cannot be skipped. If the user types samples mid-chat, refuse and tell them to paste from real writing.
  3. One-shot scaffold. After Step 2 ends, write Step 3 files in a single batch. No multi-turn confirmation. The user iterates by re-running /onboard (it re-interviews) or by editing the context/ files directly — the working aios-intake.md resets to placeholders after each run.
  4. Idempotent. Re-running re-scaffolds the context files and backs up originals to archives/intake-{ts}/. Skips questions already answered within the current run unless the user wants to revise. The durable record is context/, not the intake (which is reset).
  5. Closing screen is a header line + three horizon lines. Not a menu.
  6. No extra skills generated. Don't scaffold /today, /draft, /connect, etc. The kit ships its starter skills; the user authors more via /level-up.
  7. Read-only on references/3ms-framework.md. It already ships in the kit. Don't overwrite.
  8. No .env writes. Don't ask for API keys on Day 1. Connections come Day 2.
  9. Deterministic steps run through the bundled script. The template copy/reset, the archives backup, and the kit-wide rename all go through scripts/scaffold.sh (RUN it, never re-derive those steps by hand). Add --dry-run to preview any subcommand.

Verification (for the implementer)

  • Cold-test: clone a fresh kit, run /onboard, fill 7 answers, scaffold runs, ask the wow prompt, response cites Q1 + Q3 + Q7 specifically. Generic = fail.
  • Idempotency: re-run /onboard and give a changed Q3 answer. Expected: context/priorities.md re-scaffolds; originals backed up to archives/intake-{ts}/; the working aios-intake.md ends back at placeholders (matching aios-intake.md.template). Note CLAUDE.md has no priority placeholder — priorities live only in context/priorities.md.
  • Voice rejection: type a sample mid-chat. Expected: skill refuses, asks for paste.

The Three Ms of AI is a framework by Nate Herk. The Mindset language used in the closing screen comes from references/3ms-framework.md.

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.