Yellow Network and Nitrolite (ERC-7824) development best practices for building state channel applications. Use when building apps with Yellow SDK, implementing state channels, connecting to ClearNodes, managing off-chain transactions, or working with application sessions.
83
77%
Does it follow best practices?
Impact
91%
1.82xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./data/skills-md/0xarcano/agent-skills/yellow-best-practices/SKILL.mdQuality
Discovery
89%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 a solid skill description that clearly identifies its niche domain (Yellow Network/Nitrolite state channel development) and provides explicit trigger guidance via a 'Use when' clause with multiple specific scenarios. The main weakness is that the 'what' portion could be more specific about concrete actions rather than listing general topic areas as 'best practices'. The strong domain-specific terminology makes it highly distinctive and unlikely to conflict with other skills.
Suggestions
Replace 'development best practices' with specific concrete actions like 'Opens and closes state channels, signs and validates off-chain states, deploys adjudicator contracts, and manages virtual channel funding' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (Yellow Network, Nitrolite/ERC-7824, state channels) and mentions some actions like 'building state channel applications', 'implementing state channels', 'connecting to ClearNodes', 'managing off-chain transactions', but these are more like topic areas than concrete specific actions (e.g., no mention of specific operations like 'open/close channels', 'sign states', 'deploy contracts'). | 2 / 3 |
Completeness | Clearly answers both 'what' (development best practices for building state channel applications with Yellow Network and Nitrolite) and 'when' (explicit 'Use when' clause listing five specific trigger scenarios: building with Yellow SDK, implementing state channels, connecting to ClearNodes, managing off-chain transactions, working with application sessions). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that a developer would use: 'Yellow SDK', 'state channels', 'ClearNodes', 'off-chain transactions', 'application sessions', 'ERC-7824', 'Nitrolite'. These cover the key terminology a user working in this domain would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with very specific niche terminology (Yellow Network, Nitrolite, ERC-7824, ClearNodes, Yellow SDK). These are unique enough that this skill would be very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides solid, actionable code examples for Yellow Network/Nitrolite development and has a reasonable structure with references to detailed rule files. However, it includes unnecessary explanatory content about core concepts that Claude already understands, and the multi-step authentication workflow lacks validation checkpoints and complete implementation details. The referenced rule files are not available in the bundle, making it impossible to verify the progressive disclosure structure.
Suggestions
Remove or drastically shorten the 'What is Yellow Network?' section and architecture diagram — Claude doesn't need conceptual explanations of state channels or chain abstraction.
Complete the authentication flow example: step 2 ('Handle auth_challenge and send auth_verify') should include actual executable code, not a comment placeholder.
Add explicit validation/error-checking steps to the connection→authentication→session workflow (e.g., verify JWT received, confirm session opened before proceeding).
Trim the DO/DON'T lists to only non-obvious, domain-specific rules (e.g., 'Don't use EIP-191 prefix' is valuable; 'Don't expose private keys' is not).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'What is Yellow Network?' section explains concepts Claude doesn't need spelled out (what state channels are, what chain abstraction means). The architecture diagram and bullet points add some value but the explanatory prose could be trimmed significantly. The DO/DON'T lists contain some obvious advice (don't expose private keys, don't skip error handling). | 2 / 3 |
Actionability | The skill provides executable JavaScript code for all key operations: WebSocket connection with reconnection logic, authentication flow, message signing, and application session creation. Code examples are concrete, use actual SDK imports, and are copy-paste ready. | 3 / 3 |
Workflow Clarity | The authentication flow shows numbered steps but step 2 is incomplete ('Handle auth_challenge and send auth_verify') and step 3 is vague. There are no validation checkpoints or error recovery feedback loops for the multi-step connection→auth→session workflow, which involves network operations that can fail. | 2 / 3 |
Progressive Disclosure | The skill references a `rules/` directory with 6 detailed rule files, which is good progressive disclosure structure. However, no bundle files were provided, so these references are unverifiable. The main file itself is fairly long with inline content that could be in referenced files (e.g., the SDK components table, the DO/DON'T lists). | 2 / 3 |
Total | 9 / 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.
aa009ea
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.