Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Onboarding Flow · mkurman | DecimalAI

marketingby mkurman

Onboarding Flow

mkurman/onboarding-flow

Source mkurman/zorai ↗License MIT

When the user needs to design, improve, or audit a post-signup activation flow to get new users to their first value moment.

SkillScore73Maintained

Automatic

Product Management pack

Last verified 8/21/2026

What it changes

Passed 16 of 22 test cases with the skill, and 12 of 22 without it.

Without skill55%

With skill73%

Checks it passed that the model alone missed

Limits the setup checklist to a maximum of 3 to 5 items.
Restricts push and SMS notifications strictly to high-intent signals.
Requires that each individual checklist item takes under 2 minutes to complete.

and 4 more in the full report

4 fixed12 passed either way6 still failing0 broke

Pass-rate lift: +18 pp
Tokens: +50%
Agent turns: 0%
Response time: +6%

Model gemini-3.6-flashMeasured 8/21/2026v116 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/mkurman-onboarding-flow/SKILL.md https://app.decimal.ai/s/mkurman-onboarding-flow/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add mkurman-onboarding-flow, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/mkurman-onboarding-flow/ and pins it in .decimal/skills.lock

decimalai skills add mkurman-onboarding-flow

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/mkurman-onboarding-flow/SKILL.md https://app.decimal.ai/s/mkurman-onboarding-flow/SKILL.md

Raw file: /s/mkurman-onboarding-flow/SKILL.md ↗ · machine-readable summary at /s/mkurman-onboarding-flow.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

We are launching a consumer mobile habit tracking app. The team wants to require users to complete a 10-step profile setup and watch an introductory video before entering the main app interface. What is the recommended onboarding target and timeframe for a consumer mobile application?

What was checked, without and with the skill
Checked	Without skill	With skill
Defines activation for a B2C application as completing the first session or transaction.	Missed	Passed
Sets the target time-to-first-value for B2C applications to under 3 minutes.	Passed	Passed

case-08 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md66 linessingle file

-------|------------------------|---------------------| | B2B SaaS (simple) | Complete first core workflow | < 10 minutes | | B2B SaaS (complex) | Import data + run first report | < 24 hours | | PLG / Self-serve | Invite first team member + collaborate | < 48 hours | | Developer tool | First successful API call or deploy | < 30 minutes | | B2C app | Complete first session/transaction | < 3 minutes |

Inside-the-Product Onboarding

Prioritize onboarding that happens within the product experience itself, not detached from it. Product tours that overlay the UI without context are less effective than:

Empty states that teach — Every blank screen guides the next action
Inline prompts — Contextual guidance that appears when the user reaches a decision point
Progressive disclosure — Reveal complexity as the user demonstrates readiness
Sample data — Let users experience the product's value before investing their own data

Multi-Channel Coordination Rules

In-app: Real-time guidance for active users. Checklists, tooltips, progress bars, empty state CTAs.
Email: Async nudges for users who leave. Day 0 welcome, Day 1 reinforcement, Day 3 re-engagement, Day 7 value recap.
Push/SMS: Reserve for high-intent signals only ("Your report is ready," "Your teammate just joined"). Never use for generic reminders.
Suppression rule: If the user completed the action in-app, suppress the corresponding email. Nothing kills trust faster than "Complete your setup!" emails sent after setup is done.

Checklist Design Principles

3-5 items maximum. Completion rates drop sharply above 5.
First item should be pre-completed. Starting with visible progress significantly increases completion rates (endowed progress effect).
Each item takes under 2 minutes. If longer, break it into sub-steps.
Show the reward. "Connect Slack -> Get instant notifications" not just "Connect Slack."
Allow skipping with consequences. Let users skip but show what they lose.

Re-Engagement for Stalled Users

Diagnose before prescribing. Different stall points indicate different problems:

Stall Point	Likely Cause	Intervention
Signed up, never returned	Unclear value prop or bad timing	Email with specific use case matching signup context
Started setup, abandoned	Too many steps or hit a blocker	Email linking directly to where they stopped
Completed setup, never used	No compelling reason to return	Trigger-based email when something relevant happens
Used once, never returned	First experience was not valuable	Ask what they were trying to accomplish; offer guided call

Quality Guardrails

All onboarding designs should include:

Risk documentation identifying assumptions that could be wrong

Track record

Benchmark

16 / 22

test cases passed, vs 12 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

mkurman / zorai

skills/nontechnical/startup-founder-skills/onboarding-flow/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.