emblem-ai-agent-wallet
Connect to EmblemVault and manage wallet-aware workflows via EmblemAI with review-first, operator-controlled actions. Supports Solana, Ethereum, Base, BSC, Polygon, Hedera, and Bitcoin. Also use when the user needs Emblem's auth model explained: one browser auth flow can log a user in with wallets, email/password, or social sign-in, while agent mode can auto-provision a profile-scoped wallet with no manual setup.
84
80%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/emblem-ai-agent-wallet/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description establishes a clear niche around EmblemVault/EmblemAI wallet management across multiple chains and provides explicit 'when to use' guidance, which is a strength. However, it lacks specificity in concrete actions (what exactly can be done with wallets?) and misses common user trigger terms like 'crypto,' 'tokens,' 'NFT,' 'send,' or 'balance.' The auth model explanation is well-articulated but the core wallet operations remain vague.
Suggestions
Add specific concrete actions such as 'check balances, send tokens, view transaction history, manage NFTs' to improve specificity.
Include natural user trigger terms like 'crypto,' 'tokens,' 'NFT,' 'balance,' 'transfer,' 'send crypto,' or 'connect wallet' that users would commonly say when needing this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (EmblemVault, wallet-aware workflows) and mentions some actions like 'manage wallet-aware workflows' and 'auto-provision a profile-scoped wallet,' but it doesn't list multiple concrete actions (e.g., send tokens, check balances, swap). 'Review-first, operator-controlled actions' is more of a design philosophy than a specific capability. | 2 / 3 |
Completeness | The description answers both 'what' (connect to EmblemVault, manage wallet-aware workflows, support multiple chains, auth model) and 'when' (explicitly states 'Also use when the user needs Emblem's auth model explained' and implicitly triggers on wallet/chain-related requests). The 'Use when' guidance is present and explicit. | 3 / 3 |
Trigger Term Quality | Includes relevant keywords like 'EmblemVault,' 'EmblemAI,' specific chain names (Solana, Ethereum, Base, BSC, Polygon, Hedera, Bitcoin), 'wallet,' and 'auth model.' However, it misses common user-facing terms like 'crypto,' 'tokens,' 'NFT,' 'balance,' 'transfer,' or 'send' that users would naturally say when needing wallet management. | 2 / 3 |
Distinctiveness Conflict Risk | The description is highly specific to EmblemVault/EmblemAI with named product references and a distinct niche (multi-chain wallet management with a specific auth model). It is unlikely to conflict with generic coding or document skills, and the product-specific terminology creates clear differentiation. | 3 / 3 |
Total | 10 / 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-structured skill with strong actionability and excellent progressive disclosure. The workflows are clear with appropriate safety checkpoints for financial operations. The main weakness is moderate verbosity — some sections explain things Claude already knows or repeat safety guidance that could be consolidated, though the financial nature of the skill partially justifies the extra caution in documentation.
Suggestions
Consolidate the repeated safety/review-first warnings into a single authoritative section rather than restating them in Quick Start, Permissions, and Security — reference that section elsewhere.
Trim the Prerequisites section (Claude knows what Node.js is) and the exhaustive list of supported wallet providers in Browser Auth — a brief 'supports EVM wallets, Solana wallets, OAuth, email, and fingerprint auth' suffices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately verbose. There's useful content throughout, but sections like 'Prerequisites', the lengthy auth method explanations, and the repeated safety warnings could be tightened. Some information (e.g., explaining what terminal color support means, listing every OAuth provider) is unnecessary for Claude. The 'Communication Style' section is valuable but the overall document could be ~30% shorter. | 2 / 3 |
Actionability | The skill provides concrete, executable CLI commands throughout — installation, profile management, agent mode invocations, auth workflows, backup/restore, and logout procedures are all copy-paste ready with specific command examples and step sequences. | 3 / 3 |
Workflow Clarity | Multi-step workflows are clearly sequenced with numbered steps (First Run, auth workflows, backup/restore). The review-first safety model provides explicit validation checkpoints — transactions require operator approval before broadcasting, and the fail-closed rule for multi-profile scenarios prevents ambiguous wallet selection. Auth resolution orders are explicitly documented. | 3 / 3 |
Progressive Disclosure | The skill has a clear overview structure with well-signaled one-level-deep references to authentication.md, commands.md, security.md, capabilities.md, and troubleshooting.md. The main file covers quick start and essential workflows while appropriately deferring detailed documentation to reference files. Cross-skill references (prompt examples, React integration) are also clearly linked. | 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
- EmblemCompany/Agent-skills
- Commit
2e138ef
- 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.