Trust Wallet CLI (`twak`) — install, create wallets, check balances, send tokens, swap, view history, set price alerts, DCA automations, limit orders, manage ERC-20 approvals, check token risk, browse trending/DApps, and run x402 micropayments. Use whenever the user wants to use the twak CLI, manage a crypto wallet from the terminal, send or swap tokens via command line, check portfolio, create price alerts, set up DCA, create limit orders, approve ERC-20 spenders, or interact with Trust Wallet from a shell. Also covers MCP server setup for AI agents.
89
86%
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 comprehensively lists specific capabilities, includes a well-structured 'Use whenever...' clause with abundant natural trigger terms, and is clearly distinguishable from other skills due to its focus on the Trust Wallet CLI tool. The description uses proper third-person voice throughout and balances thoroughness with clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists numerous specific concrete actions: install, create wallets, check balances, send tokens, swap, view history, set price alerts, DCA automations, limit orders, manage ERC-20 approvals, check token risk, browse trending/DApps, and run x402 micropayments. This is highly specific and comprehensive. | 3 / 3 |
Completeness | Clearly answers both 'what' (the first sentence listing all capabilities) and 'when' (the explicit 'Use whenever...' clause with detailed trigger scenarios). Both halves are thorough and well-articulated. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'crypto wallet', 'terminal', 'command line', 'send or swap tokens', 'check portfolio', 'price alerts', 'DCA', 'limit orders', 'ERC-20', 'Trust Wallet', 'shell', 'twak CLI', 'MCP server'. These cover both technical and casual user language. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — it targets a specific CLI tool ('twak') for Trust Wallet with clear niche triggers like 'Trust Wallet', 'twak CLI', 'ERC-20 approvals', and 'x402 micropayments'. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at conciseness and progressive disclosure, serving as an efficient routing layer to detailed reference files. Its main weakness is that the SKILL.md body itself contains almost no actionable content — not even a single quick-start example command — and lacks workflow guidance for multi-step or destructive operations like token transfers. Adding a minimal quick-start example and a brief workflow note for common multi-step tasks would significantly improve it.
Suggestions
Add 1-2 concrete quick-start command examples (e.g., `twak balance --chain ethereum` or `twak send ...`) so Claude can act on simple requests without needing to read a reference file first.
Include a brief multi-step workflow note for common dangerous operations (e.g., 'For sending tokens: always confirm chain, address, and amount before executing `twak send`; verify tx hash in history afterward') to improve workflow clarity and safety.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean — no unnecessary explanations, no descriptions of what crypto wallets are or how CLIs work. Every line serves a routing or setup purpose. The table format is efficient for conveying task-to-reference mappings. | 3 / 3 |
Actionability | The skill itself contains no executable commands or code examples beyond the install command. All actionable content is deferred to reference files. While the routing table is helpful, the SKILL.md body alone doesn't give Claude enough to act on any task without reading a reference file first. | 2 / 3 |
Workflow Clarity | The routing table provides clear task-to-reference mapping, and the note about reading setup.md alongside other references is useful. However, there's no explicit workflow for multi-step operations (e.g., install → create wallet → send tokens), no validation checkpoints, and no error recovery guidance for potentially destructive operations like sending tokens or swapping. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure structure — a concise overview with a well-organized table routing to one-level-deep reference files. Each reference is clearly signaled with both the file path and 'when to read' triggers, making navigation intuitive. | 3 / 3 |
Total | 10 / 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.
6f8671f
Table of Contents
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.