user-onboarding

user-onboarding is a skill for Claude Code, Codex from liqiongyu/lenny_skills_plus. It costs 32 tokens per session (2,328 once invoked), scanned A, original, Apache-2.0.

A method for designing the first experience a person has with a product, from signing up to reaching useful results. It covers the steps that help users understand the product and get value quickly.

In plain words
What is it for?
Use it to define the product’s “aha moment,” design guided setup and checklists, improve empty states, and plan onboarding experiments.
Why use it?
It addresses users dropping out during signup or setup, unclear empty screens, and long delays before the product becomes useful. It also provides a way to measure and improve early engagement.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to define the product’s “aha moment,” design guided setup and checklists, improve empty states, and plan onboarding experiments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/liqiongyu/lenny_skills_plus/user-onboarding
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add liqiongyu/lenny_skills_plus --skill user-onboarding
Clone the repo
git clone --depth 1 https://github.com/liqiongyu/lenny_skills_plus

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for user-onboarding

README.md
[![agentmods](https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/user-onboarding/github.svg)](https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/user-onboarding)
Your own site
<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/user-onboarding"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/user-onboarding/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for user-onboarding

Your own site · 80×15
<a href="https://agentmods.dev/skills/liqiongyu/lenny_skills_plus/user-onboarding"><img src="https://agentmods.dev/badge/skills/liqiongyu/lenny_skills_plus/user-onboarding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,328 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.02328
Opus 5 $0.00016 $0.01164
Sonnet 5 $0.00006 $0.00466
Haiku 4.5 $0.00003 $0.00233

Measured 9d ago against content hash deddba2e2890, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

user-onboarding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/user-onboarding/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Onboarding

Scope

Covers

  • Designing the first-time user experience (FTUE) from entry/signup → first value
  • Defining activation / the “aha moment” and reducing time-to-value
  • Creating a “first 30 seconds” experience and a “first mile” plan (milestones to activation)
  • Onboarding mechanics: progressive disclosure, guided setup, empty states, templates, checklists, feedback loops
  • Instrumentation + experiments to improve activation and early retention

When to use

  • “Activation is low” / “users drop during signup/onboarding”
  • “Time-to-value is too long”
  • “The first session doesn’t feel magical”
  • “We need an onboarding redesign / guided setup / empty state improvements”
  • “Define our aha moment and design onboarding to get users there”
  • “Create an onboarding experiment backlog + measurement plan”

When NOT to use

  • You’re onboarding employees, customers to a service process, or running training -- not product onboarding (use onboarding-new-hires for employee onboarding).
  • You don’t have a stable value proposition / ICP (use problem-definition or measuring-product-market-fit first).
  • You need a full retention strategy beyond onboarding (use retention-engagement); this skill covers signup-to-activation, not post-activation lifecycle retention.
  • You need to validate a prototype with real users (use usability-testing after creating a plan here).
  • You need to design viral/referral loops or acquisition flywheels (use designing-growth-loops); this skill is about converting new users, not acquiring them.
  • You want to apply behavioral science frameworks (habit loops, nudge architecture) as the primary design lens (use behavioral-product-design); this skill uses behavioral insights but is structured around the onboarding journey, not around psychological theory.

Inputs

Minimum required

  • Product + ICP/segment(s) (1–2) and the primary job-to-be-done
  • Platform + entry point (web/mobile; where FTUE starts)
  • Best-available baseline metrics (even rough):
    • visit → signup → first key action → activation
    • time-to-value (time or sessions to first value)
    • D1 retention (if available)
  • Current onboarding flow summary (steps/screens) and the biggest drop-off point(s)
  • Constraints: timebox, eng/design capacity, allowed channels (in-app/email/push), privacy/legal/brand limits

Read the full file on GitHub · 149 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 149 lines · 32 tokens per session scan A deddba2e2890

Subscribe to this mod's changes

user-onboarding is a skill published in the GitHub repository liqiongyu/lenny_skills_plus (52 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 32 tokens to every session and 2,328 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories