CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

1.82x
Quality

78%

Does it follow best practices?

Impact

91%

1.82x

Average score across 3 eval scenarios

SecuritybySnyk

—

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./data/skills-md/0xarcano/agent-skills/yellow-best-practices/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body offers solid executable patterns and appropriately concise domain context, but two structural weaknesses hold it back: the referenced rules/ files that are supposed to hold the detailed guidance are missing from the bundle, and the critical authentication flow is left as comments. There is also no explicit sequenced workflow with validation checkpoints.

Suggestions

Ship the referenced rules/ files (01-connection.md through 06-error-handling.md) or inline the essential content — every detailed-guidance link is currently dead.

Complete the authentication pattern with real code for the auth_challenge/auth_verify exchange and JWT storage instead of placeholder comments.

Add an explicit end-to-end workflow (connect → authenticate → create session → transact → close) with validation checkpoints, e.g., verify auth success before creating a session.

DimensionReasoningScore

Conciseness

The body is mostly lean with compact, purposeful code blocks, and the 'What is Yellow Network?' section conveys genuinely new domain knowledge rather than restating known concepts. It is not a 5 because the feature bullets ('Up to 100,000 transactions per second') and the ASCII architecture diagram are trimmable marketing-flavored padding.

4 / 5

Actionability

Most patterns give executable code — the reconnection class, the EIP-712 signer, and the app-session creation are copy-paste ready. It is not a 5 because Essential Pattern #2 (authentication, marked Critical) is only comments ('// 2. Handle auth_challenge and send auth_verify') with no actual code, and the signing example uses ethers v5 internals that may not run on current ethers versions.

4 / 5

Workflow Clarity

The sections imply a rough order (connect → authenticate → create session → transact → close) but never lay out an explicit end-to-end sequence, and there are no validation or verification checkpoints (e.g., confirming auth success before creating a session, checking challenge state before closing). Not a 2 because the individual patterns do present coherent internal steps.

3 / 5

Progressive Disclosure

The body links to six rules files ('rules/01-connection.md' through 'rules/06-error-handling.md') as the destination for detailed guidance, but none of these files exist in the skill bundle — every reference is dead, and no references/, scripts/, or assets/ directories are present. The overall disclosure structure is therefore broken rather than merely imperfectly organized.

2 / 5

Total

13

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it names a distinct niche, lists multiple concrete capabilities, and includes an explicit multi-trigger 'Use when' clause. Minor room for improvement in adding synonyms for variant user phrasing and covering the auth/signing actions.

Suggestions

Add a couple of natural synonyms such as 'payment channels' or 'Yellow Network apps' to broaden trigger coverage.

Mention one or two additional concrete actions (e.g., 'authenticating with ClearNodes' or 'signing off-chain messages') to round out capability coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions — 'building apps with Yellow SDK, implementing state channels, connecting to ClearNodes, managing off-chain transactions, or working with application sessions' — going beyond naming the domain. It falls short of a 5 because the head noun 'development best practices' is generic and key actions (authentication, message signing, session closure) are not mentioned.

4 / 5

Completeness

It explicitly answers both 'what' ('development best practices for building state channel applications') and 'when' with an explicit 'Use when building apps with Yellow SDK, implementing state channels, connecting to ClearNodes...' clause containing five concrete triggers. This matches the anchor-5 pattern of both what and when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good coverage of natural domain terms users would say ('Yellow SDK', 'state channels', 'ClearNodes', 'off-chain transactions', 'application sessions'). Not a 5 because there are no synonyms or broader lay phrasings (e.g., 'payment channels', 'Yellow Network apps') that would catch variant user wording.

4 / 5

Distinctiveness Conflict Risk

The niche is highly distinct — 'Yellow Network and Nitrolite (ERC-7824)', 'ClearNodes' are specific to this protocol and unlikely to collide with other skills' triggers. Conflict risk is minimal.

5 / 5

Total

18

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 6 missing

Warning

Total

15

/

16

Passed

Repository

NeverSight/learn-skills.dev

Path

data/skills-md/0xarcano/agent-skills/yellow-best-practices/SKILL.md

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.