CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

80%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/emblem-ai-agent-wallet/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

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 strong, well-structured skill for a complex domain (multi-chain crypto wallet management). It excels at actionability with concrete CLI commands throughout, has clear workflow sequences with safety checkpoints, and uses progressive disclosure effectively to keep the main file navigable while pointing to detailed references. The main weakness is moderate verbosity — some sections could be tightened (duplicate installation blocks, some explanatory text that could be trimmed), though much of the length is justified by the security-critical nature of the domain.

DimensionReasoningScore

Conciseness

The skill is fairly long (~300+ lines) with some sections that could be tightened. The auth methods section, credential handling rules, and prompt injection guidance are thorough but somewhat verbose. However, most content is genuinely useful for a complex multi-chain wallet skill. Some redundancy exists (e.g., installation appears in both Quick Start and Installation sections, security model is partially restated).

2 / 3

Actionability

The skill provides concrete, executable CLI commands throughout — installation, profile management, auth workflows, agent mode invocations, backup/restore procedures, and even piping output to jq. The communication style table with good/bad examples is directly actionable. Commands are copy-paste ready with specific flags and options.

3 / 3

Workflow Clarity

Multi-step workflows are clearly sequenced with explicit steps (First Run is numbered 1-5, auth workflows have clear step sequences). The review-first safety model serves as a validation checkpoint for all value-moving actions. The fail-closed rule for multi-profile scenarios, backup-immediately-after-creation guidance, and the prompt injection handling section with numbered guardrails all demonstrate strong workflow discipline with explicit verification steps.

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. Each reference includes a brief summary of what it covers. Cross-skill references to prompt-examples and react integration are also cleanly linked. The main SKILL.md stays at the right level of detail for an overview.

3 / 3

Total

11

/

12

Passed

Description

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 'when to use' guidance, which is a strength. However, it leans more toward describing architecture and design philosophy ('review-first, operator-controlled actions,' auth model details) rather than listing concrete user-facing actions the skill can perform. Adding specific actionable capabilities would improve its utility for skill selection.

Suggestions

Add concrete action verbs describing what the skill actually does, e.g., 'send tokens, check balances, manage NFTs, provision wallets' rather than the abstract 'manage wallet-aware workflows'.

Include natural user trigger terms like 'send crypto,' 'token transfer,' 'check balance,' 'NFT,' or 'connect wallet' that users would commonly say when needing this skill.

DimensionReasoningScore

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 across multiple chains) and 'when' with an explicit 'Also use when the user needs Emblem's auth model explained' clause, plus the implicit trigger of needing wallet management on the listed chains.

3 / 3

Trigger Term Quality

Includes relevant keywords like 'EmblemVault,' 'EmblemAI,' 'Solana,' 'Ethereum,' 'wallet,' 'auth,' and specific chain names that users might mention. However, it lacks common user-facing trigger terms like 'send crypto,' 'check balance,' 'NFT,' 'token transfer,' or 'connect wallet' that users would naturally say.

2 / 3

Distinctiveness Conflict Risk

The description is highly specific to EmblemVault/EmblemAI with named chains and a unique auth model explanation. It's unlikely to conflict with generic crypto or wallet skills due to the branded terminology and specific multi-chain scope.

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
EmblemCompany/Agent-skills
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.