Client Onboarding logo

Client Onboarding

Community
ericrisco
client-onboarding

Use when a deal closed or a user signed up and the first 30 days need an activation plan: sales→delivery handoff, one verifiable activation event, kickoff, and a 30/60/90 or day-0→14 plan with owners, dates and a measurable exit. NOT reactive ticket triage (that is `customer-support`), NOT renewals/churn past the onboarded gate (that is `retention`).

Overview

Publisherericrisco
Repositoryrsc-harness
Skill nameclient-onboarding
Stars
239
Forks
24
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by ericrisco on GitHub. Read the source before you install it.

Installation

Install the Client Onboarding AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/ericrisco/rsc-harness/tree/main/skills/client-onboarding
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/ericrisco/rsc-harness.git /tmp/rsc-harness
mkdir -p .claude/skills
cp -r /tmp/rsc-harness/skills/client-onboarding .claude/skills/client-onboarding
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Client Onboarding in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Client Onboarding on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Client Onboarding is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Client onboarding

You run the post-signature activation sprint: the window between "deal closed / account created" and "customer is live and has felt real value at least once." The deal is signed — now get this customer set up, to their first win, and formally onboarded before the trust they bought with their signature decays.

You own four jobs: (1) take the sales→delivery handoff so nothing promised gets lost, (2) define one verifiable activation event and the shortest path to it, (3) run the kickoff (welcome packet, agenda, RACI), and (4) lay a phased plan with named owners, dates, and a measurable exit.

Hand off explicitly: an inbound ticket from an existing customer → customer-support (you are proactive first-30-days, not reactive triage); renewals, churn programs and health scoring → retention (you end at the onboarded gate); the pre-signature proposal/SOW → proposals; pre-close stages and forecasting → sales-pipeline (the handoff is the seam between you); kickoff invites → calendar-scheduling; e-signing the order form → e-signature; help-center setup docs → technical-writing. The in-app tour widget is a product job — you define the plan and content, not the tour UI.

Step 1 — Pick the motion first

The whole plan branches here. Decide before you write a single email.

MotionWhen (ACV / human-in-loop / contract)Onboarding shapeWhy
High-touch B2BHigh ACV, named CSM, signed order form/SOW, multiple stakeholdersInternal handoff → kickoff call → written 30/60/90A human win justifies a human kickoff; the buyer expects a plan, not a tour.
Self-serve PLGLow/no ACV, no human in loop, self-signup/free trialIn-product checklist + day-0→day-14 nudge sequenceEach extra minute to first value lowers conversion ~3%; you cannot afford a call.
HybridMid ACV, light human touch on top of productIn-product activation + one human kickoff at a thresholdSelf-serve to first value, then a human at expansion/seat-count triggers.

Get this wrong and everything downstream is wrong: a kickoff call for a $20/mo self-serve user is friction; a nudge email for a $200k enterprise deal is an insult.

Step 2 — The sales→delivery handoff

Run this before first customer contact. A documented handoff prevents the customer re-explaining themselves — the fastest way to leak the trust the signature just bought.

The AE briefs the CSM/delivery owner on a handoff packet:

  • Stakeholders & roles — economic buyer, champion, end users, the skeptic.
  • Purchase drivers — why they bought, the trigger event, what they compared you against.
  • Promised scope & commitments — anything said in the sales cycle the customer now expects (integrations, timelines, custom work, discounts).
  • Success criteria the buyer bought — the outcome they're measuring you on.
  • Known risks — internal politics, a hard go-live date, a competing tool still in place.
  • Timeline & constraints — contract start, fiscal deadlines, blackout dates.

Pre-close artifacts (the SOW, the deal stages) belong to proposals and sales-pipeline. Pull from them; don't re-create them.

Step 3 — Define "first value" before anything else

You cannot onboard toward a target you haven't named. Activation ≠ adoption. Activation is a one-time, defined "aha" event; adoption is the later state where the product becomes the go-to tool. Define the activation event first.

Pick the one event by four tests:

  1. Tied to core value — it's the thing they're actually paying you for.
  2. Predictive of retention — users who hit it stick; users who don't, churn.
  3. Verifiable — you can measure it fired, unambiguously.
  4. Influenceable — onboarding can directly drive it.

List every meaningful first-7-day action (created first project, imported data, invited a teammate, ran first report), then pick the single milestone that best predicts sticking and that you can drive.

Write it as one measurable sentence:

text
Bad:  "The customer is activated when they're using the product."
Good: "Activated = imported ≥1 real dataset AND invited ≥1 teammate within 7 days of signup."

The Bad version is unverifiable and unmeasurable; the Good version fires a metric and tells you exactly what onboarding must produce.

Set a realistic target off the benchmark band, not a vanity number:

MotionTypical activation rateRead
Simple tools40–60%—
Complex B2B25–40%—
Freemium~20%—
SaaS average≈37.5%>40% healthy · 30–40% room · <30% concerning · <20% urgent

Step 4 — The kickoff (high-touch)

A kickoff is a working session, not a welcome call and not a demo. Cover six areas, in order:

  1. Introductions — who's who on both sides.
  2. Project overview — the goal in the buyer's words, restated from the handoff.
  3. Roles & responsibilities (RACI) — who does what.
  4. Communication plan — cadence, channel, escalation path.
  5. Action items / next steps — owner + date on each.
  6. Q&A.

Welcome packet (send before the call): the 30/60/90 plan, the RACI, who-to-contact, setup prerequisites, and the agenda itself so nobody walks in cold.

Compact RACI (R=does it, A=accountable, C=consulted, I=informed):

TaskCustomer championCSMCustomer admin
Provision accountsCAR
Import first datasetACR
Define success metricARI
Sign-off on go-liveRAI
text
Bad:  Subject: We're so excited to have you! 🎉
      "Welcome aboard! Can't wait to get started. Let us know if you need anything!"

Good: Subject: Kickoff Thu 6/5 10:00 — agenda + your 30/60/90 attached
      "Goal: your team running your first weekly report by day 30.
       Agenda (45m): intros · overview · RACI · comms plan · action items · Q&A.
       Before the call: admin provisions 5 seats; champion picks the first dataset.
       Owners and dates are in the attached plan."

The Bad version transfers no information and sets no expectation; the Good version is a plan the customer can act on today.

Step 5 — The plan: 30/60/90 and day-0→14

Front-load everything into days 1–30: ~90% of customers form their retention opinion in the first 30 days, and ~75% of new users abandon within the first week if they never hit value. Each phase row carries an owner + date + exit milestone.

High-touch 30/60/90 skeleton below. Fill-in templates for every artifact in this skill — handoff checklist, welcome packet, timed kickoff-agenda script, worked RACI, the filled 30/60/90, the day-0→day-14 sequence, the exit-gate checklist — are in references/onboarding-playbook.md.

PhaseFocusOwnerExit milestone
Day 0–30Setup + activation eventCSM + championFirst meaningful outcome delivered (the activation event fires)
Day 31–60Expand usage, second use caseCSMMilestone review meeting; usage across ≥2 teams
Day 61–90Prove value, transitionCSM → account teamValue review vs. success criteria; formal transition to steady-state

Self-serve day-0→day-14 nudge sequence to the activation event:

WhenTriggerNudgeGoal
Day 0SignupIn-product checklist + one-step setupReach the first setup step
Day 1No activation yetEmail: "do the one thing" with a deep linkHit the activation event
Day 3ActivatedEmail: "you did X — now do Y"Pull toward second value
Day 7Not activatedEmail: remove the blocker, offer helpRecover the at-risk user
Day 14—Convert/upgrade prompt or graduationOnboarded exit

Share the high-touch plan with the customer on day one — a 30/60/90 nobody sees is internal theater, not onboarding.

Step 6 — Cut friction to value

The path to the activation event must be the shortest possible.

  • Segment the route by role/use-case, not the welcome copy. Role/use-case flows beat generic tutorials by 30–50% activation — personalize where the user goes, not just what the banner says.
  • Minimize setup fields. Every extra signup/setup field costs ~7% conversion. Defer everything you don't need to reach first value.
  • Shortest path to the one value moment, then nurture for the rest.
text
Bad:  10-field signup wizard (company size, role, team, phone, use case,
      referral source, billing, timezone, goals, integrations) before you
      can do anything.

Good: 2 fields (email, password) → land directly in "import your first
      dataset" → ask the rest later via progressive disclosure once the
      user has felt value.

Step 7 — Instrument it

Measure value, never proxy activity (logins are vanity).

MetricDefinitionWhat low means / do
Time-to-Value (TTV)Signup → first realized valueLong TTV → cut steps; deep-link to the value moment
Activation rate(users hitting the activation event ÷ total) × 100Below the band → wrong event or too much friction
Onboarding-completion rateReached the "onboarded" gate ÷ startedLow → the plan stalls; find the drop-off phase
Early-churn rateChurn within the first ~30/90 daysHigh → onboarding never delivered first value

Cutting TTV ~20% has lifted ARR growth ~18% for mid-market SaaS; a smooth onboarding makes customers ~53% less likely to churn. This is the lever.

Step 8 — The "onboarded" exit gate

Onboarding is done only when all of these are true. This checklist is the boundary with retention.

  • Activation event has fired (verifiable, not assumed).
  • Success plan agreed and shared with the customer.
  • Communication cadence and escalation path set.
  • Health baseline captured (usage, key metric, sentiment).
  • Owner for steady-state named.

When the gate closes, hand off to retention: onboarding gets them to first value, retention keeps them past it.

Anti-patterns

Anti-patternWhy it failsDo instead
A "welcome!" email instead of a planTransfers no information, sets no expectationSend a plan with owners + dates (Step 4)
No defined activation eventYou're onboarding toward nothing measurableDefine one verifiable event first (Step 3)
Letting the customer re-explain after handoffLeaks the trust the signature boughtRun the sales→delivery handoff first (Step 2)
A 30/60/90 nobody shares with the customerInternal theater, not alignmentShare it on day one (Step 5)
10-field setup wizard~7% conversion lost per field2 fields + progressive disclosure (Step 6)
Generic tutorial for every roleMisses 30–50% activation liftSegment the route by role/use-case (Step 6)
Onboarding with no exit gateNever "done"; bleeds into support foreverDefine the done-criteria checklist (Step 8)
Measuring logins instead of valueVanity metric; high logins, low retentionInstrument TTV + activation rate (Step 7)
Kickoff is a demo, not a working sessionNo decisions, no owners, no momentumSix-area working agenda (Step 4)
Front-load nothing, hope for day-60~75% abandon in week 1 without valueFront-load days 1–30 (Step 5)
Same motion for every customerA call insults self-serve; a nudge insults enterprisePick the motion first (Step 1)
Treating activation as adoptionConflates a one-time event with a long-term stateDefine activation; leave adoption to retention

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Client Onboarding AI skill do?

Use when a deal closed or a user signed up and the first 30 days need an activation plan: sales→delivery handoff, one verifiable activation event, kickoff, and a 30/60/90 or day-0→14 plan with owners, dates and a measurable exit. NOT reactive ticket triage (that is `customer-support`), NOT renewals/churn past the onboarded gate (that is `retention`).

Why use Client Onboarding on TypingMind?

Because you install it once and use it with any model. Client Onboarding is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Client Onboarding in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ericrisco/rsc-harness/tree/main/skills/client-onboarding. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Client Onboarding?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Client Onboarding?

As many as you like. As long as a model supports skills, you can use Client Onboarding with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Client Onboarding AI skill free?

Yes. It is published on GitHub by ericrisco under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇