agentleFS
QuarktexQuarktex/qcobrain/.claude/skills/onboard/SKILL.md

onboard

Skill4 starsChanged 4 months agoMITView on GitHub

Day-1 combined wizard. Runs the 7-question intake from `intake.md`, then scaffolds the Day-1 file set in one batch — `context/` (about-you, about-business, priorities, state), `references/voice.md`, a populated `connections.md`, the four `digests/`, and fills the `{{placeholders}}` in `CLAUDE.md`. Idempotent — re-run any time after editing `intake.md`. Triggers - "set me up", "onboard me", "let's get started", "fill in my brain", or a fresh clone.

  • Reads credentials

168 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 9 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 9 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 19 projects that use this

  • CoralGameSkill

    project-stage-detect

    Automatically analyze project state, detect stage, identify gaps, and recommend next steps based on existing artifacts.

    Also in 15 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 11 projects that use this

  • +5 more from lilangMax
  • +2 more from CoralGame

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 156 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

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

    line 33
  2. Very specific:

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

    line 42
  3. Distinctive:

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

    line 53
  4. Distinctive:

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

    line 107
  5. Distinctive:

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

    line 118
  6. Very specific:

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

    line 120
  7. Distinctive:

    Closing screen is three lines: Not a menu.

    line 124
  8. Very specific:

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

    line 125
  9. Very specific:

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

    line 126

“Common” is measured: kept by at least 6 in 10 of the 156 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

Inherits references/kernel.md (the provenance contract). Reads references/wiki-spec.md for schema.

Note on provenance scope: onboarding writes context/ and digests/, which hold YOUR direct testimony about yourself and your business — not wiki/ canon — so they don't need src blocks. The cite-or-refuse gate kicks in the moment any of these facts get promoted into wiki/ (via /capture). Until then, context/ is "you telling the brain who you are," kept separate from the sourced wiki.

What this skill does

A single combined wizard. It reads or writes intake.md (the canonical 7-question intake), conducts the interview if the file isn't filled, then scaffolds the Day-1 file set inline at the end of the run. There is 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. The prompt itself plants the leverage instinct — asking, of any task, to what extent could this be automated? — for them to internalize.

When NOT to run this

  • Already onboarded and just refreshing → still run, but skip questions already answered (idempotent).
  • Wiring up a new connection → that's not onboarding. Point them at connections.md to edit directly.

Execution

Step 1 — Read the intake

Read 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: "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) → run Step 2 conversationally.

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

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

Q1 — Who are you, what do you sell, who do you sell it to? Identity, offer, ICP. One paragraph each is fine.

Q2 — Paste 1-2 things you've written recently. Don't edit them. 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, not yearly aspirations. Push back on "grow my business" — make them name a number, a deadline, or a deliverable.

Q4 — Where does revenue actually land, and where is it tracked? Multiple answers OK (Stripe, a spreadsheet, an invoicing tool, etc.).

Q5 — Where do you talk to customers, your team, and the outside world day-to-day? Email (Gmail/Outlook), Slack/Teams/Discord, DMs, phone.

Q6 — Where do meeting recordings, notes, and important docs live? Granola/Otter/Fireflies, Drive, Notion, Dropbox, a folder on the desktop.

Q7 — What's the one task that eats your week, and where do you currently track work? The biggest recurring time-suck, plus where tasks live (ClickUp/Asana/Linear/Notion/a notebook). Capture this as top_pain.

Step 3 — Scaffold the Day-1 file set (one batch)

Once the intake is complete, generate these files (or update if re-running). If any already exist, back up the originals to archives/intake-{{YYYY-MM-DD-HHMM}}/ first.

  1. context/about-you.md — from Q1 (identity, role) + Q7 (top_pain). One short paragraph each.
  2. context/about-business.md — from Q1 (offer, ICP) + Q4 (revenue model). One paragraph.
  3. context/priorities.md — from Q3. Numbered list, one line per priority.
  4. context/state.md — initialize the LIVE snapshot: a "where things stand right now" line, today's date, the active priorities, and "onboarded {{date}}" under a short changelog. This is the instant-context file every session reads first.
  5. references/voice.md — from Q2. Paste samples verbatim under a short header explaining their use: "Match this register when drafting. Don't fake the voice on external content without showing a draft first."
  6. connections.md — populate the systems table from Q4-Q7. Each row gets mechanism: not yet connected, auth: —, trust: read-only (the safe default of the trust triad: read-write | read-only | deny), last checked: —. The user wires connections later.
  7. digests/ — generate the initial four preflight files (≤~40 lines each) from the context above. Each bullet ends with its provenance pointer; on Day 1 that points at the context file it came from (e.g. (→ context/about-business.md)), and graduates to (→ note-id) once the fact is captured into wiki/:
    • product.md ← context/about-business.md
    • goals.md ← context/priorities.md
    • recent-decisions.md ← decisions/log.md (Day 1: "No decisions logged yet.")
    • user-profile.md ← context/about-you.md + references/voice.md
  8. CLAUDE.md — fill every {{...}} placeholder: the user's name, what they sell, the stated priorities, a one-line voice-register summary, and a brief connections summary.

Step 4 — The closing screen

Print one short screen — three lines, not a menu:

✓ Day 1 done. Your co-brain knows who you are, what you sell, what matters this quarter, and how you sound.

Today: ask me — "what should I focus on this week?"
This week: use it — /capture facts in, /recall to ask. Weekly: /wiki-doctor + /curator. Per session: /review.

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

  • a 3-bullet priority list, in their voice register from Q2;
  • each bullet tied back to a stated 90-day priority from Q3;
  • a 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 step? And — to what extent could this task be automated?"

That automation question seeds the leverage instinct before the user ever formalizes a workflow.

Critical implementation rules

  1. The 7-question cap is non-negotiable. Don't add a Q8 in conversation.
  2. Voice paste cannot be skipped. Typed-mid-chat samples are voice-contaminated — refuse and ask for a paste.
  3. One-shot scaffold. After Step 2, write Step 3 files in a single batch. No multi-turn confirmation; the user iterates by editing intake.md and re-running.
  4. Idempotent. Re-running with an edited intake refreshes only the changed files and backs up originals to archives/intake-{{ts}}/. Skip questions already answered unless the user wants to revise.
  5. Closing screen is three lines. Not a menu.
  6. No extra skills generated. Don't scaffold /today, /draft, etc. New skills come via /skillify.
  7. No .env writes. Don't ask for API keys on Day 1. Connections (and any optional-layer keys) come later.

Verification (for the implementer)

  • Cold-test: fresh clone, run /onboard, fill 7 answers, scaffold runs, ask the wow prompt; the answer cites Q1 + Q3 + Q7 specifically and reads in the Q2 voice. Generic = fail.
  • Idempotency: re-run with one Q3 priority changed → only context/priorities.md, digests/goals.md, and CLAUDE.md's priority line update; a backup lands in archives/intake-{{ts}}/.
  • Voice rejection: type a sample mid-chat → the skill refuses and asks for a paste.

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.