yellow-best-practices
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.
86
81%
Does it follow best practices?
Impact
91%
1.82xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
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 state updates, deploys adjudicator contracts, and manages channel funding'
| 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
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides strong actionable code examples and excellent progressive disclosure with clear references to detailed rule files. However, it includes unnecessary explanatory content about Yellow Network concepts that Claude already understands, and the multi-step authentication workflow lacks explicit validation checkpoints and error recovery patterns.
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 to use the SDK.
Complete the authentication flow with executable code for all three steps, including error handling and a validation checkpoint after auth_verify.
Add an explicit end-to-end workflow sequence (connect → authenticate → create session → transact → close session) with validation checkpoints at each stage.
Trim the DO/DON'T lists to only non-obvious, domain-specific rules (e.g., keep 'Don't use EIP-191 prefix' but remove 'Don't expose private keys').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The 'What is Yellow Network?' section explains concepts Claude doesn't need spelled out (what state channels are, what 'non-custodial' means). The architecture diagram and bullet points add some value but the explanatory prose is unnecessary padding. The DO/DON'T lists also contain some obvious advice (don't expose private keys, don't skip error handling). | 2 / 3 |
Actionability | The skill provides fully executable JavaScript code examples for connection, authentication, message signing, and app sessions. Import statements are included, code is copy-paste ready, and specific SDK function names and WebSocket URLs are provided. | 3 / 3 |
Workflow Clarity | The authentication flow shows steps 1 and 2 but step 3 is just a comment ('Store JWT token for reconnection') with no code. The overall workflow from connection → auth → session creation → usage → session closure is implied but not explicitly sequenced with validation checkpoints. No feedback loops for error recovery are shown. | 2 / 3 |
Progressive Disclosure | Excellent structure with a clear overview in the main file and well-signaled one-level-deep references to the rules/ directory with descriptive labels and priority levels. The SDK components table and additional resources section provide good navigation without nesting references deeply. | 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- NeverSight/skills_feed
- Commit
e437c3c
- 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.