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.
64
76%
Does it follow best practices?
Impact
—
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 and provides explicit trigger guidance, making it strong on completeness and distinctiveness. However, it lacks specificity about concrete user-facing actions (what can users actually do—send tokens, check balances, mint NFTs?) and misses common natural language trigger terms users would use when needing crypto wallet functionality.
Suggestions
Add specific concrete actions users can perform, e.g., 'check balances, send tokens, view transaction history, manage NFTs' to improve specificity.
Include natural user-facing trigger terms like 'crypto,' 'tokens,' 'NFT,' 'balance,' 'transfer,' 'send,' 'swap' that users would commonly say when needing wallet management help.
| 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' with an explicit trigger clause ('Also use when the user needs Emblem's auth model explained'). The opening implicitly covers the 'when' for wallet management tasks, and the explicit 'Also use when...' clause satisfies the trigger guidance requirement. | 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, which is a distinct product. The combination of the product name, multi-chain support list, and the specific auth model explanation creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%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, highly actionable skill with concrete CLI commands, clear multi-step workflows, and strong safety guardrails for financial operations. Its main weakness is length — several sections (prompt injection handling, detailed auth resolution orders, credential handling rules) could be moved to reference files to improve conciseness. The progressive disclosure structure is present but the main file carries too much inline detail for optimal token efficiency.
Suggestions
Move the 'Handling Untrusted Blockchain Data' section to references/security.md and summarize it in one sentence with a link — this would save ~40 lines of token budget.
Move the detailed 'Common Auth Workflows' section to references/authentication.md and keep only a brief summary with a link in the main skill file.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some unnecessary verbosity — e.g., the lengthy prompt injection section, the repeated explanations of the review-first model, and the detailed auth resolution order that could be in a reference file. The 'Communication Style' table and security trust model preamble add useful info but could be tighter. | 2 / 3 |
Actionability | The skill provides concrete, copy-paste-ready CLI commands throughout — installation, profile management, agent mode invocations, auth workflows, backup/restore, and logout procedures. Commands are specific with exact flags, menu option numbers, and file paths. | 3 / 3 |
Workflow Clarity | Multi-step workflows (first run, auth switching, backup/restore, logout) are clearly sequenced with numbered steps and explicit validation checkpoints. The 'fail closed rule' for multi-profile scenarios, the backup-immediately-after-creation instruction, and the review-first confirmation requirement for value-moving actions all serve as strong safety gates. | 3 / 3 |
Progressive Disclosure | The skill references multiple reference files (security.md, authentication.md, commands.md, capabilities.md, troubleshooting.md) with clear descriptions of what each contains, which is good. However, the main SKILL.md itself is quite long (~300+ lines) and inlines substantial detail about auth workflows, credential handling, and prompt injection that could be offloaded to reference files. No bundle files were provided to verify references exist, but the structure is reasonable. | 2 / 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.
- Repository
- EmblemCompany/Agent-skills
- Commit
2652244
- 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.