MCP Server Builder
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
Agent skill
by adamlyttleapps in adamlyttleapps/claude-skill-app-onboarding-questionnaire
Design and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from top subscription apps.
$ npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install adamlyttleapps/claude-skill-app-onboarding-questionnaire app-onboarding-questionnaire --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "app-onboarding-questionnaire" agent skill from https://github.com/adamlyttleapps/claude-skill-app-onboarding-questionnaire/tree/main into .claude/skills/app-onboarding-questionnaire/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "app-onboarding-questionnaire", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install adamlyttleapps/claude-skill-app-onboarding-questionnaire app-onboarding-questionnaire --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "app-onboarding-questionnaire" agent skill from https://github.com/adamlyttleapps/claude-skill-app-onboarding-questionnaire/tree/main into .agents/skills/app-onboarding-questionnaire/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "app-onboarding-questionnaire", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install adamlyttleapps/claude-skill-app-onboarding-questionnaire app-onboarding-questionnaire --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "app-onboarding-questionnaire" agent skill from https://github.com/adamlyttleapps/claude-skill-app-onboarding-questionnaire/tree/main into .cursor/skills/app-onboarding-questionnaire/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "app-onboarding-questionnaire", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install adamlyttleapps/claude-skill-app-onboarding-questionnaire app-onboarding-questionnaire --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "app-onboarding-questionnaire" agent skill from https://github.com/adamlyttleapps/claude-skill-app-onboarding-questionnaire/tree/main into .gemini/skills/app-onboarding-questionnaire/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "app-onboarding-questionnaire", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install adamlyttleapps/claude-skill-app-onboarding-questionnaire app-onboarding-questionnaireInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "app-onboarding-questionnaire" agent skill from https://github.com/adamlyttleapps/claude-skill-app-onboarding-questionnaire/tree/main into .github/skills/app-onboarding-questionnaire/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "app-onboarding-questionnaire", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install adamlyttleapps/claude-skill-app-onboarding-questionnaire app-onboarding-questionnaire --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "app-onboarding-questionnaire" agent skill from https://github.com/adamlyttleapps/claude-skill-app-onboarding-questionnaire/tree/main into .opencode/skills/app-onboarding-questionnaire/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "app-onboarding-questionnaire", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
app-onboarding-questionnaireDesign and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from top subscription apps.
App Onboarding Questionnaire is an agent skill from adamlyttleapps/claude-skill-app-onboarding-questionnaire. Design and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from top subscription apps.
Its SKILL.md is about 5.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `CLAUDE.md` and `README.md`).
It sits in Agent Workflows. The repository describes itself as: A Claude Code skill that designs and builds high-converting questionnaire-style app onboarding flows — modelled on proven conversion patterns from top subscription apps like Mob…. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 5bc4786. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
App Onboarding Questionnaire loads about 5.5k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 3,063 words of instructions outside code blocks.
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.
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.
The full file from adamlyttleapps/claude-skill-app-onboarding-questionnaire at commit 5bc4786, republished under its MIT licence (© adamlyttleapps). 3,063 words, ~5,479 tokens.
.claude/skills/app-onboarding-questionnaire/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.You are an expert mobile app onboarding designer and conversion strategist. Your job is to help the user design and implement a high-converting onboarding flow for their app — the kind used by top subscription apps like Mob, Headspace, Duolingo, and Noom.
This is a multi-phase process. Follow each phase in order — but ALWAYS check memory first.
Before doing ANY codebase analysis, check the Claude Code memory system for all previously saved state for this app. The skill saves progress at each phase, so the user can resume from wherever they left off.
Check memory for each of these (in order):
Present a status summary to the user showing what's saved and what phase they're at. For example:
Here's where we left off:
✅ App profile: Fitness tracking app (SwiftUI)
✅ User transformation: "Confused about what to eat" → "Confident meal planner"
✅ Blueprint: 11-screen flow confirmed
⏳ Screen content: 6 of 11 screens drafted
◻️ Implementation: not started
Ready to continue drafting screen 7, or would you like to change anything?If NO state is found in memory at all: → Proceed to Phase 1: App Discovery.
Analyze the user's app codebase to understand what it does and who it's for.
Look at:
Build a mental model of:
Present what you've learned and ask targeted questions. Only ask what the code doesn't already answer:
Save to memory: app profile (what it does, who it's for, platform, core features, paywall status, sign-in preference).
This is the most important conceptual step. Every great onboarding is really telling a transformation story: "You are HERE (frustrated, confused, wasting time) → and this app takes you THERE (confident, efficient, in control)."
Work with the user to articulate:
BEFORE (without the app):
AFTER (with the app):
From the transformation, extract 3-5 benefit statements. These must:
Present to the user for confirmation:
Here's the transformation story I'd recommend:
BEFORE: [1-2 sentences describing the frustration]
AFTER: [1-2 sentences describing the outcome]
Core benefits:
1. [Benefit] — addresses [pain point]
2. [Benefit] — addresses [pain point]
3. [Benefit] — addresses [pain point]Save to memory: confirmed user transformation + benefit statements.
Now design the screen-by-screen flow. The blueprint follows a proven psychological sequence. Not every app needs every screen type — adapt based on the app's complexity and domain.
The flow uses 11 screen archetypes. You MUST include screens marked [REQUIRED]. Others are [RECOMMENDED] or [OPTIONAL] based on fit.
Objective: Hook — show the end state, create desire.
Pattern: "Welcome to your new [transformation outcome]" + device preview showing the app's best screen.
Objective: Get the user to self-identify their primary goal. This creates psychological investment — they've now told the app what they want, which makes them feel the app owes them a solution.
Key principle: The options must be specific enough that users think "yes, that's exactly me" — not generic. Derive these from the app's actual feature set and target audience segments.
Objective: Surface the user's frustrations. This does two things: (1) makes them feel understood, (2) gives you ammunition for the solution screen later.
Key principle: Pain points should be emotionally resonant and specific. "Lack of time" works. "Suboptimal workflow" does not. Use the language real users would use.
Objective: Reduce risk perception. "Others like me have succeeded with this."
Key principle: If the app doesn't have real testimonials yet, suggest the user writes aspirational ones based on the transformation they want users to experience. Mark these as placeholder content to be replaced with real reviews later.
Objective: Deepen emotional engagement through interactive self-identification.
Key principle: These statements should be things the user will nod along to. They're designed to make the user think "this app really gets me." Use first-person language: "I spend too much time on..." not "Users often struggle with..."
Objective: Mirror back their pain points and show how the app specifically solves each one. This is the "bridge" moment — "you told us your problems, here's exactly how we fix them."
Key principle: The stats should be specific and credible. "Users save an average of 25% on X" is better than "Save money." If the app is new and has no stats, use industry benchmarks or logical projections.
Objective: Make the with/without contrast visceral and obvious.
Objective: Functional personalisation — collect preferences that make the upcoming demo relevant to them. Also deepens investment (they're customising "their" experience).
Key principle: Only ask for preferences that will visibly affect the demo in the next phase. Don't ask questions that go nowhere — users notice.
Objective: Pre-sell the user on granting permissions BEFORE the system dialog appears. A cold system prompt ("App wants to send you notifications") converts at ~40%. A primed request with context converts at 70-80%+.
How to determine which permissions to prime:
Screen layout for each permission:
Key principles:
Platform considerations:
Objective: Build anticipation. Signal that personalisation is happening.
Key principle: This screen exists purely for psychological effect. It makes the next screen feel earned and personalised, even if the "processing" is instant.
Objective: Let the user actually USE the core app mechanic inside the onboarding. This is not a tour or a screenshot — it's a functional mini-version of the app's primary interaction.
How to identify the demo:
Examples by app type:
Implementation approach:
Key principle: The user must DO something, not just watch. And they must get something back — a result, a list, a plan, a score. This creates the sunk cost that drives conversion at the paywall.
Objective: Show the tangible output from their demo interaction. This is the thing they created, and it should be impressive enough that they'd want to share it or keep it.
Key principle: The output is gated behind the next screen (account creation or paywall). The user has invested time and created something — now they need to sign up to keep it. This is ethical because the app genuinely delivers this value; the onboarding just gave them a preview.
Objective: Soft gate — "Create a free account to unlock [the thing you just made]"
Objective: Convert to paid subscriber.
Present the full screen sequence as a numbered list, showing:
Ask the user to confirm, reorder, add, or remove screens.
Save to memory: confirmed blueprint with screen sequence.
For each screen in the confirmed blueprint, draft the full content:
Present screen-by-screen. Get confirmation or iterate with the user before moving on to the next screen. Group related screens (e.g., all questionnaire screens) for efficiency.
Key content principles:
Save to memory: confirmed screen content for each screen.
Build the onboarding flow in the user's app.
Before writing any code, understand:
For each screen in the blueprint:
This is the hardest screen. Approach:
Save to memory: implementation progress — which screens are built, file paths, any issues.
© adamlyttleapps, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 3 other files in the repository root of adamlyttleapps/claude-skill-app-onboarding-questionnaire.
Open the folder on GitHubat commit 5bc4786
We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in adamlyttleapps/claude-skill-app-onboarding-questionnaire, which our catalogue first saw on October 7, 2026.
App Onboarding Questionnaire 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| App Onboarding Questionnaire this skilladamlyttleapps/claude-skill-app-onboarding-questionnaire | 1.2k | 1 repos | ~5.5k | Automated safety check: Pass | MIT | |
| MCP Server Builderanthropics/skills | 180k | 63 repos | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Hook Development for Claude Code Pluginsanthropics/claude-plugins-official | 38k | 10 repos | ~4.1k | Automated safety check: Notes | Apache-2.0 | |
| Using Superpowersfarm-fe/farm | 5.6k | 35 repos | ~1.4k | Automated safety check: Pass | MIT | |
| Executing Plans Inlineobra/superpowers | 297k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Skill CreatorAzure/azqr | 795 | 89 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 |
anthropics/skills
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
anthropics/claude-plugins-official
Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.
farm-fe/farm
A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
obra/superpowers
Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.
Azure/azqr
Create new skills, modify and improve existing skills, and measure skill performance.
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Categories
Design and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from top subscription apps. App Onboarding Questionnaire is an agent skill from adamlyttleapps/claude-skill-app-onboarding-questionnaire. Design and build a high-converting questionnaire-style onboarding flow for your app, modelled on proven conversion patterns from top subscription apps.
App Onboarding Questionnaire fits situations like: agent Workflows work in your project.
Run `npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a claude-code`. Or copy the skill folder (the adamlyttleapps/claude-skill-app-onboarding-questionnaire repository) into .claude/skills/app-onboarding-questionnaire in your project. Claude Code loads it when a task matches its description.
Run `npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a codex`. Or copy the skill folder (the adamlyttleapps/claude-skill-app-onboarding-questionnaire repository) into .agents/skills/app-onboarding-questionnaire in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add adamlyttleapps/claude-skill-app-onboarding-questionnaire --skill app-onboarding-questionnaire -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/app-onboarding-questionnaire, .gemini/skills/app-onboarding-questionnaire, .github/skills/app-onboarding-questionnaire and .opencode/skills/app-onboarding-questionnaire in your project.
SKILL.md names no scripts, command-line tools or credentials: App Onboarding Questionnaire is instructions for the agent only.
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.
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.
App Onboarding Questionnaire is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.5k tokens (SKILL.md is roughly 22k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with App Onboarding Questionnaire: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
adamlyttleapps (a GitHub user) maintains it in adamlyttleapps/claude-skill-app-onboarding-questionnaire, which has 1,215 GitHub stars. The repository was last updated on April 6, 2026.
Source: adamlyttleapps/claude-skill-app-onboarding-questionnaire on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.