trust-wallet-sdk
Trust Wallet open-source libraries — Wallet Core (HD wallets, address derivation, tx signing in Swift/Kotlin/TypeScript/Go for 140+ chains), Web3 Provider (dApp connection for Ethereum/Solana/Cosmos/Bitcoin/Aptos/TON/Tron), deep linking, browser extension integration, WalletConnect, token assets repository, and Barz ERC-4337 smart wallet. Use when working with trustwallet/wallet-core, @trustwallet/wallet-core, trust-web3-provider, Trust Wallet deep links, token logos/metadata from trustwallet/assets, or Barz account abstraction.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that thoroughly enumerates the specific Trust Wallet libraries and their capabilities, includes natural trigger terms like package names and repository paths, and provides an explicit 'Use when...' clause. It is highly distinctive and would be easy for Claude to correctly select from a large pool of skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and components: HD wallets, address derivation, tx signing, dApp connection, deep linking, browser extension integration, WalletConnect, token assets repository, and Barz ERC-4337 smart wallet across specific languages and chains. | 3 / 3 |
Completeness | Clearly answers both 'what' (Trust Wallet libraries with specific capabilities) and 'when' with an explicit 'Use when...' clause listing specific package names, repo paths, and use cases that serve as clear triggers. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'trustwallet/wallet-core', '@trustwallet/wallet-core', 'trust-web3-provider', 'Trust Wallet deep links', 'token logos/metadata', 'Barz account abstraction', plus chain names (Ethereum/Solana/Cosmos/Bitcoin/Aptos/TON/Tron) and language names (Swift/Kotlin/TypeScript/Go). | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — focuses specifically on Trust Wallet's open-source ecosystem with named repositories and packages. Unlikely to conflict with generic crypto or wallet skills due to the specificity of 'trustwallet/wallet-core', 'trust-web3-provider', and 'Barz ERC-4337'. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted routing/index skill that efficiently directs Claude to the appropriate reference file based on the user's task. Its strength is excellent progressive disclosure and extreme conciseness. Its weakness is that the skill body itself contains no executable guidance — it relies entirely on the referenced files for actionable content, which means if those references are missing or incomplete, the skill provides no fallback.
Suggestions
Consider adding a minimal quick-start example (e.g., a 3-line wallet-core address derivation snippet) so the skill provides some immediate actionable value even before reading references.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — just a one-line description and a routing table. No unnecessary explanation of what wallets are, what HD derivation means, etc. Every token earns its place. | 3 / 3 |
Actionability | The routing table clearly directs Claude to the right reference file based on keywords, which is actionable for navigation. However, the skill itself contains zero executable code, commands, or concrete examples — all actionable content is deferred to references. | 2 / 3 |
Workflow Clarity | This is essentially a single-step routing skill: identify the user's task, then read the matching reference. The table makes the decision process unambiguous with clear keyword triggers. No multi-step destructive operations are involved. | 3 / 3 |
Progressive Disclosure | Textbook progressive disclosure — a concise overview with a well-structured table pointing to five clearly-labeled, one-level-deep reference files. Navigation is intuitive with both task descriptions and keyword triggers. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- trustwallet/tw-agent-skills
- Commit
6f8671f
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.