Solana Onboarding logo

Solana Onboarding

Community
draaujpeg
solana-onboarding

Diagnoses and fixes the entry experience of Solana products, wallets, DEXs, aggregators and lending apps, using components calibrated on a heuristic study of 13 apps. Use when the user is designing, reviewing or implementing onboarding, wallet creation or import, transaction confirmations, error states, identity verification, or when they paste an error code or ask why users abandon a flow.

Overview

Publisherdraaujpeg
Repositorysolana-uiux-onboarding-kit
Skill namesolana-onboarding
Stars
4
Forks
0
Bundled files
44
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.

  • 44 bundled files

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

  • Open source

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

Installation

Install the Solana 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/draaujpeg/solana-uiux-onboarding-kit/tree/main/skills/solana-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/draaujpeg/solana-uiux-onboarding-kit.git /tmp/solana-uiux-onboarding-kit
mkdir -p .claude/skills
cp -r /tmp/solana-uiux-onboarding-kit/skills/solana-onboarding .claude/skills/solana-onboarding
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Solana 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 Solana 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 Solana 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.

Solana onboarding

This skill carries the components that answer each of those, and the rules for choosing between them. Both are calibrated on evidence: every rule exists because something was measured failing without it.

Components are copied into the user's project. They are not a dependency, there is nothing to keep updated, and the user owns and edits the result.

Output: either a diagnosis of what is missing, or components installed and wired into the project, with the wording agreed rather than assumed.

  • Read the reference for a pattern before proposing anything about it. The rules are not derivable from the components.
  • Propose copy and wait for the user to confirm, edit or replace it. Product wording is theirs, and a plausible guess survives review by looking finished.
  • Say when a screen should not exist. Confirming everything trains people to click through, which is what makes the one dialog that mattered invisible.
  • Run the project's build after installing anything, and fix what you broke.

Never:

  • Never invent a component. If nothing here fits, say so and describe what would.
  • Never add a copy-to-clipboard control for a recovery phrase.
  • Never assert the reason an identity verification was rejected. The reasoning is in components/kyc-rejection-causes.ts.
  • Never write a literal colour into a component. Everything paints with --so-* tokens, which is what lets a copied component adopt the host brand.

Step 1. Work out what is being asked

Route on what the user gave you, not on the words they used. People rarely name the pattern they need.

What arrivedWhere to go
An error string or code, or a screenshot of onereferences/error-codes.md
"Review our onboarding", a repository, a flow to critiqueAudit mode, below
"I need a confirmation for X", or a described screenImplement mode, below
A term the product uses without explainingreferences/glossary.md
Anything about creating, importing or social loginreferences/custody-paths.md first

If the request is broad, run the audit first. Implementing without diagnosing produces a well-built screen in the wrong place.

Step 2. Load only what the task needs

Every reference is written to be applied on its own.

FileHolds
references/patterns/One file per pattern: the gap it closes, when it applies, its rules, the copy to propose
references/risk-classification.mdWhether an action needs a confirmation, and which of the four
references/custody-paths.mdCreate, social login or import, and where the kit stops
references/error-codes.mdAn error code, to the component that answers it
references/glossary.mdThe terms the kit explains, and where the long version lives
references/copy-rules.mdHow to propose wording, and what is not yours to change
references/installing.mdCopying components into a project without breaking it
methodology/audit-grid.mdThe 30 questions the research scored, for audit mode

Audit mode

Diagnose before touching anything.

  1. Find the entry flow: wallet connection, account creation, the first transaction, and any gate between them. Ask if you cannot tell.
  2. Score it against methodology/audit-grid.md. Severity is calibrated by what a failure costs the user, not by how wrong it looks.
  3. Look for the two failures that hide well: an irreversible action with no confirmation, and a confirmation a level below the action it guards. The second is more common and harder to see, because the screen looks considered.
  4. Report gaps ordered by severity, each naming the pattern that closes it. Recommend, do not install.

Names in a codebase are candidates, not conclusions. Confirm before reporting.

Implement mode

  1. Identify the pattern. For a confirmation, run references/risk-classification.md first: it also answers "no dialog at all".
  2. Read the project. Framework, styling, whether shadcn tokens exist, where components live, and what the product actually does. The wording depends on that last one.
  3. Propose the copy and the blocks it needs. Say what you chose and why. Wait.
  4. Install, following references/installing.md.
  5. Build. Show it running if you can.

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 Solana Onboarding AI skill do?

Diagnoses and fixes the entry experience of Solana products, wallets, DEXs, aggregators and lending apps, using components calibrated on a heuristic study of 13 apps. Use when the user is designing, reviewing or implementing onboarding, wallet creation or import, transaction confirmations, error states, identity verification, or when they paste an error code or ask why users abandon a flow.

Why use Solana Onboarding on TypingMind?

Because you install it once and use it with any model. Solana 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 Solana Onboarding in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/draaujpeg/solana-uiux-onboarding-kit/tree/main/skills/solana-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 Solana 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 Solana Onboarding?

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

Is the Solana Onboarding AI skill free?

Yes. It is published on GitHub by draaujpeg 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 👇