emblem-ai
One-shot user management for apps, multi-chain wallet authentication, an AI-powered assistant, and AI app introspection. Use when the user wants to let website users sign in with wallets, email/password, or social login and give each user a wallet-enabled account, then embed EmblemAI chat surfaces, connect plugins, or add Reflexive observability. Provides React components, TypeScript SDKs, session-based authentication, and pointers to the React and agent-wallet skills for specialized workflows.
63
75%
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/SKILL.mdQuality
Discovery
77%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 is detailed and comprehensive, clearly stating both what the skill does and when to use it with explicit trigger guidance. Its main weaknesses are the heavy reliance on product-specific jargon that users may not naturally use, and the broad scope covering multiple domains (auth, AI chat, observability) which increases potential overlap with more specialized skills. The description would benefit from more natural user-facing trigger terms and tighter scoping.
Suggestions
Add more natural trigger terms users would actually say, such as 'auth', 'login', 'user accounts', 'sign-up', 'SSO', 'chatbot', 'monitoring' alongside the product-specific terms.
Consider narrowing the scope or more explicitly delineating boundaries with related skills to reduce conflict risk — e.g., clarify that this is the 'getting started' or 'integration' skill vs. specialized React or agent-wallet workflows.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: user management, multi-chain wallet authentication, AI-powered assistant, AI app introspection, embedding EmblemAI chat surfaces, connecting plugins, adding Reflexive observability. Also mentions concrete deliverables like React components, TypeScript SDKs, and session-based authentication. | 3 / 3 |
Completeness | Clearly answers both 'what' (user management, wallet auth, AI assistant, introspection, React components, SDKs) and 'when' with an explicit 'Use when...' clause covering multiple trigger scenarios (sign in with wallets, email/password, social login, embed chat, connect plugins, add observability). | 3 / 3 |
Trigger Term Quality | Includes some natural keywords like 'sign in with wallets', 'email/password', 'social login', 'React components', 'TypeScript SDKs', but many terms are product-specific jargon (EmblemAI, Reflexive, agent-wallet) that users may not naturally use. Missing common variations like 'auth', 'login', 'user accounts', 'onboarding'. | 2 / 3 |
Distinctiveness Conflict Risk | The description covers a broad range of capabilities (auth, AI assistant, observability, wallet management) which could overlap with more specialized skills. It acknowledges this by pointing to 'React and agent-wallet skills for specialized workflows', but the breadth of scope increases conflict risk with authentication-focused or AI-assistant-focused skills. | 2 / 3 |
Total | 10 / 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 is a well-structured skill with strong actionability and excellent progressive disclosure across a complex multi-package ecosystem. Its main weaknesses are moderate verbosity (marketing-style descriptions, repeated cross-references, and sections explaining trust models that don't help Claude execute tasks) and missing validation/error-recovery workflows for authentication and session management operations.
Suggestions
Remove or significantly trim the 'Security & Trust Model' and 'What You Can Build' sections — these describe rather than instruct and consume tokens without adding actionable guidance.
Add error handling and validation checkpoints to the authentication workflow (e.g., what to check after openAuthModal(), how to handle session failures, what errors registerPlugin can throw).
Consolidate the repeated cross-references to sibling skills — the React skill and Agent Wallet skill are each referenced 3-4 times; a single clear pointer per skill would suffice.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-organized but includes some unnecessary explanation (e.g., 'Why this matters' marketing copy, the Security & Trust Model section explaining trust decisions Claude doesn't need, repeated reminders to 'point the user to' other skills). The 'What You Can Build' section is largely descriptive rather than instructive. Several sections repeat the same cross-references multiple times. | 2 / 3 |
Actionability | The skill provides fully executable code examples for React setup, vanilla JS/Node.js initialization, plugin registration, session management, and Reflexive usage. Code blocks are copy-paste ready with real import paths and realistic usage patterns. | 3 / 3 |
Workflow Clarity | The Quick Start provides clear Option A/B paths, but there are no explicit validation checkpoints or error recovery steps. For a skill involving authentication, wallet provisioning, and session management, there's no guidance on what to do when auth fails, sessions don't refresh, or plugin registration errors occur. The session management section lists events but doesn't show a complete error-handling workflow. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main skill, well-signaled one-level-deep references to dedicated reference docs and sibling skills. The 'More Examples and References' section provides a clean directory of all supporting files with brief descriptions. Cross-skill handoffs (React skill, Agent Wallet skill, Prompt Examples skill) are clearly signaled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- 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.