Agent skill

Exposure Onboarding

by hashgraph-online in hashgraph-online/awesome-codex-plugins

Use the exposure effect deliberately in onboarding and habit formation — getting users to repeated, low-friction encounters with the product so familiarity builds and preference forms.

Apache-2.0Auto-check passedProductivity & Automation

Install Exposure Onboarding

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill exposure-onboarding -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins exposure-onboarding --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/aesthetics-and-emotion-principles/skills/exposure-onboarding .claude/skills/exposure-onboarding && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
exposure-onboarding
GitHub stars
1.3k
Token cost
~2.1k tokens
SKILL.md length
1,177 words
Files
2 (incl. references)
Skills in repo
716
Repo updated
First seen
Licence
Apache-2.0

At a glance

Use the exposure effect deliberately in onboarding and habit formation — getting users to repeated, low-friction encounters with the product so familiarity builds and preference forms.

  • Designing onboarding flows
  • SKILL.md covers The first-week imperative, Designing for early exposure, What "low friction" means and Worked examples, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Planning feature introductions

What it does

Exposure Onboarding is an agent skill from hashgraph-online/awesome-codex-plugins. Use the exposure effect deliberately in onboarding and habit formation — getting users to repeated, low-friction encounters with the product so familiarity builds and preference forms. Use when designing onboarding flows, planning feature introductions, building user habits, or evaluating why users churn after first use. The exposure effect operates over time; products that get users to come back early benefit from accumulated familiarity that single-session products don't.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/onboarding-cadences.md`).

It sits in Productivity & Automation. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • Designing onboarding flows
  • Planning feature introductions
  • Building user habits
  • Evaluating why users churn after first use

Example prompts

  • “/exposure-onboarding”

What it can do on your machine

Read from SKILL.md and the folder at commit 3e1456a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Exposure Onboarding loads about 2.1k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 125 tokens; SKILL.md has 1,177 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~125
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 3e1456a, republished under its Apache-2.0 licence (© hashgraph-online). 1,177 words, ~2,150 tokens.

Download SKILL.mdSave it as .claude/skills/exposure-onboarding/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
exposure-onboarding
description
Use the exposure effect deliberately in onboarding and habit formation — getting users to repeated, low-friction encounters with the product so familiarity builds and preference forms. Use when designing onboarding flows, planning feature introductions, building user habits, or evaluating why users churn after first use. The exposure effect operates over time; products that get users to come back early benefit from accumulated familiarity that single-session products don't.

Exposure Effect — onboarding and habit

The exposure effect operates through repetition. A user who encounters your product once is at the start of the curve; a user who encounters it daily for a week is much further along. Designing onboarding to maximize early exposure — getting users back into the product repeatedly with low friction — builds the familiarity that supports long-term retention.

The first-week imperative

Most product churn happens in the first week. Users who don't return within a week typically don't return at all. The mechanism is exposure: users who don't return haven't built enough familiarity for the exposure effect to operate. Their initial impression doesn't have time to consolidate.

Products that successfully retain users almost always achieve high first-week return frequency. Whether this is by:

  • Genuinely useful daily-use cases (calendar, email, messaging).
  • Notification-driven re-engagement (within reasonable limits).
  • Ritual integration (a morning reading habit, a daily check-in).
  • Deliberate first-week onboarding that brings users back.

The retention pattern is consistent: repeated exposure in the first week predicts long-term retention.

Designing for early exposure

Reduce friction to return. The lowest-friction return is no friction at all — push notifications, email reminders, or other prompts. The next-lowest is one-tap return (an icon on the home screen, a saved tab). Anything that requires effort to return reduces return frequency.

Give users a reason to return. New content, updated information, social interaction, scheduled events, recommendations. Each return has to deliver something; otherwise the exposure cost outweighs the benefit.

Make first sessions complete enough to return for. A user who completes a meaningful task on first session has a positive memory to return to. A user who didn't complete anything has no positive baseline.

Build in natural use cycles. Daily check-in, weekly review, morning catch-up — habits that align with users' existing routines.

Leverage notifications carefully. Notifications can drive return but can also build resentment. The right level of notification varies by product and user; over-notification is the most common failure mode.

What "low friction" means

Friction in this context is anything that costs the user time or attention to return to the product:

  • High friction: open a browser, type a URL, log in, navigate to the relevant section.
  • Medium friction: open a saved tab or bookmarked link, then navigate.
  • Low friction: open the app from the home screen.
  • Very low friction: tap a notification that takes you directly to the relevant content.
  • Negative friction: the relevant content surfaces ambient (a watch face, a widget, a daily email).

Each step down the friction ladder dramatically increases the return rate. The exposure effect needs return; whatever friction you can eliminate from return makes the effect work harder for you.

Worked examples

A meditation app's first-week design

A meditation app onboards users with:

  • Day 1: 5-minute introductory session; immediate value.
  • Day 2: notification reminder; another 5-minute session.
  • Day 3: notification with a curated session matching the user's first-day choice.
  • Day 4: a celebration of "3 days in a row" with a slightly longer session.
  • Day 5–7: continued reminders and varied content.

By day 7, the user has had 5–7 exposures, has formed a small habit, and has experienced the product's value repeatedly. The exposure effect has operated; the user now likes the app more than they would after a single session.

This pattern (reminders + valuable content + habit cues) is common across successful habit-forming apps.

A productivity tool that fails to onboard for return

A productivity tool gets users to sign up. They complete onboarding. They use the tool for an hour, find some value. Then they don't return for 3 weeks; when they do, they've forgotten how it works. They get frustrated and stop using it.

The failure: no mechanism to bring users back in the first week. Without repeated early exposure, the familiarity didn't consolidate; the next session felt like starting over; the product never became part of the user's routine.

The fix: notification campaigns in the first week reminding users of the value; weekly digest emails; integration with calendar / email so the product surfaces in existing workflows.

A reading app with daily content

A reading app delivers a curated article to users daily. Users open the app each morning to read the day's article. The content delivery is the return mechanism; the exposure effect operates through the daily ritual.

Over weeks and months, users develop strong preference for the app. Even if a competitor launched with technically better features, the daily-habit familiarity would keep users with the original.

Show full SKILL.md (437 more words)Show less
Notifications that backfire

A new social app sends 5–10 notifications per day to new users to drive engagement. Initial engagement is high. After a week, users are exhausted; many uninstall the app or disable notifications.

The mechanism: too much exposure, the wrong kind. The notifications became an annoyance rather than a positive prompt. The exposure effect requires positive or neutral experiences; pestering users creates negative association.

The fix: calibrate notification frequency. Send fewer notifications; make each one more valuable. Let users control the cadence.

A B2B SaaS with weekly value

A B2B analytics tool delivers a weekly summary email of insights from the user's data. Users open it once a week to see what's interesting. The email has a one-click path back to the full product.

This pattern works for tools that don't need daily use but benefit from weekly check-ins. The weekly cadence is enough to maintain familiarity; the weekly email is the return mechanism.

Anti-patterns

Onboarding without ongoing engagement. A great onboarding experience that ends after day 1. The user has been introduced to the product but isn't being brought back.

Over-notification. Too many or too irrelevant notifications. Builds resentment rather than habit. The most common failure mode in product growth.

Friction at the return path. A login required every time; an app that takes 10 seconds to load; a path to relevant content that takes 5 navigation steps. Each friction reduces return rate.

Generic re-engagement. Notifications that don't show the user that the product has paid attention. "Come back to the app!" without specifics is less effective than "Your weekly summary is ready" or "John commented on your post."

Assuming users will come back on their own. Most users won't. Without active re-engagement, the early-week exposure won't happen.

Deferring monetization until familiarity exists, but then not building familiarity. Strategy of "we'll monetize later" only works if you actually build the user base; without exposure-driven retention, there's nothing to monetize later.

Heuristic checklist

When designing for early exposure, ask: What's the first-week return frequency we're targeting? Be specific. What's the mechanism for return? Notifications, email, habit, ritual. Is the friction to return low enough? Each step costs return rate. Does each return deliver something specific? Generic "come back" isn't enough. Are we calibrated to avoid annoyance? Over-notification is the most common failure.

  • exposure-effect — parent principle on the mere-exposure phenomenon.
  • exposure-redesign-risk — sibling skill on managing accumulated familiarity during redesigns.
  • feedback-loop — early feedback supports the value that brings users back.
  • mental-model — the mental model is built through exposure.
  • hierarchy — first sessions should foreground the value; bury complexity.

See also

  • references/onboarding-cadences.md — patterns for first-week onboarding cadences.

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/aesthetics-and-emotion-principles/skills/exposure-onboarding of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/onboarding-cadences.md

Open the folder on GitHubat commit 3e1456a

Compare with similar skills

Exposure Onboarding next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Exposure Onboarding compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Exposure Onboarding this skillhashgraph-online/awesome-codex-plugins1.3k—~2.1kAutomated safety check: PassApache-2.0
Agent Browserquran/quran.com-frontend-next1.9k40 repos~3.3kAutomated safety check: PassNone
Dependency Watchtelegramdesktop/tdesktop33k1 repos~2.2kAutomated safety check: PassGPL-3.0
Perform Tasktelegramdesktop/tdesktop33k2 repos~3kAutomated safety check: PassGPL-3.0
Brave Searchbadlogic/pi-skills2.6k5 repos~592Automated safety check: PassMIT
Garden Inboxpaperclipai/paperclip99k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Agent Browser

    quran/quran.com-frontend-next

    Automates browser interactions for web testing, form filling, screenshots, and data extraction.

    1.9k GitHub starsUsed in 40 repos~3.3k tokens
    Productivity & AutomationAuto-check passed
  • Dependency Watch

    telegramdesktop/tdesktop

    Audit Telegram Desktop dependencies on freshly fetched origin/dev for releases and security fixes, including upstream lag and backport candidates in patched forks.

    33k GitHub starsUsed in 1 repo~2.2k tokens
    Productivity & AutomationAuto-check passed
  • Perform Task

    telegramdesktop/tdesktop

    Resolve, start or resume, implement, review, test, and publish exactly one existing ai-tdesktop task by short slug or full dated id, including rare blocked retries and split-required results.

    33k GitHub starsUsed in 2 repos~3k tokens
    Productivity & AutomationAuto-check passed
  • Brave Search

    badlogic/pi-skills

    Web search and content extraction via Brave Search API. An agent skill from badlogic/pi-skills.

    2.6k GitHub starsUsed in 5 repos~592 tokens
    Productivity & AutomationAuto-check passed
  • Garden Inbox

    paperclipai/paperclip

    Scan a Paperclip user's Mine inbox, classify reversible archive candidates, request checkbox confirmation, and archive only accepted selections.

    99k GitHub stars~1.1k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Continue

    telegramdesktop/tdesktop

    Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.

    33k GitHub starsUsed in 2 repos~9.4k tokens
    Productivity & AutomationAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 716 skills in this repo
  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.3k GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.3k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.3k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.3k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Calle

    hashgraph-online/awesome-codex-plugins

    Use CALL-E from Codex through the calle CLI. An agent skill from hashgraph-online/awesome-codex-plugins.

    1.3k GitHub stars~2.9k tokensUpdated today
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.3k GitHub stars~618 tokensUpdated today
    Auto-check passed

Questions about Exposure Onboarding

What does Exposure Onboarding do?

Use the exposure effect deliberately in onboarding and habit formation — getting users to repeated, low-friction encounters with the product so familiarity builds and preference forms. Exposure Onboarding is an agent skill from hashgraph-online/awesome-codex-plugins. Use the exposure effect deliberately in onboarding and habit formation — getting users to repeated, low-friction encounters with the product so familiarity builds and preference forms.

When should I use Exposure Onboarding?

Exposure Onboarding fits situations like: designing onboarding flows; planning feature introductions; building user habits; evaluating why users churn after first use.

How do I install Exposure Onboarding in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill exposure-onboarding -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/aesthetics-and-emotion-principles/skills/exposure-onboarding in hashgraph-online/awesome-codex-plugins) into .claude/skills/exposure-onboarding in your project. Claude Code loads it when a task matches its description.

How do I install Exposure Onboarding in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill exposure-onboarding -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/aesthetics-and-emotion-principles/skills/exposure-onboarding in hashgraph-online/awesome-codex-plugins) into .agents/skills/exposure-onboarding in your project. Codex loads it when a task matches its description.

Can I use Exposure Onboarding in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill exposure-onboarding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/exposure-onboarding, .gemini/skills/exposure-onboarding, .github/skills/exposure-onboarding and .opencode/skills/exposure-onboarding in your project.

What does Exposure Onboarding need to run?

SKILL.md names no scripts, command-line tools or credentials: Exposure Onboarding is instructions for the agent only.

Does Exposure Onboarding access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Exposure Onboarding safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Exposure Onboarding use?

Exposure Onboarding is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Exposure Onboarding use?

About 2.1k tokens (SKILL.md is roughly 8.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Exposure Onboarding?

Skills that share tags, products or a category with Exposure Onboarding: Agent Browser (quran/quran.com-frontend-next, 1.9k stars), Dependency Watch (telegramdesktop/tdesktop, 33k stars), Perform Task (telegramdesktop/tdesktop, 33k stars) and Brave Search (badlogic/pi-skills, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Exposure Onboarding?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,267 GitHub stars. The repository holds 716 skills in this directory. The repository was last updated on October 10, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.