genlayer-intelligent-contracts

Internet Court adapter for GenLayer Intelligent Contract supervision. Use to specify agent-performance rubrics, evidence schemas, decision outputs, and ERC-7710 connector expectations, while delegating actual GenLayer contract writing, linting, testing, deployment, and CLI interaction to the official GenLayer skills at https://skills.genlayer.com/.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./integrations/genlayer-intelligent-contracts/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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

The body is highly actionable and well-sequenced, with concrete schemas, a clear workflow, and a verification-inclusive checklist for its niche. The weaker dimensions are conciseness and progressive disclosure: heavy inline type definitions and only minimally signaled reference navigation leave room to move detail out of the main file.

Suggestions

Move the larger inline schemas (e.g., WalletSpendSnapshot, AgentPerformanceReviewInput) into a reference file and link to it from the relevant sections, keeping SKILL.md a lean overview.

Link the supervisor-contract reference contextually from the Core Model or Revocation Integration section instead of only the bare end-of-file path bullet, so navigation is signaled where it is needed.

Tighten the few explanatory prose passages (e.g., the x402/manager aside) to the essential caveat to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is information-dense, niche-specific, and avoids explaining basics Claude already knows, but three full multi-line TypeScript type definitions are inlined (notably the ~23-line WalletSpendSnapshot) plus explanatory prose that could be tightened or moved to a reference, fitting 'mostly efficient but could be tightened' rather than 'every token earns its place'.	2 / 3
Actionability	It provides concrete, copy-paste-ready TypeScript schemas (AgentPerformanceReviewInput, AgentReviewDecision, RevocationEffect), a specific 6-step workflow, a rubric-defaults list, and a 9-item output checklist — fully actionable guidance for the skill's specification scope.	3 / 3
Workflow Clarity	A clearly sequenced 6-step Workflow is paired with a 9-item Output Checklist that includes an explicit verification step (item 9 lists tests for continue/warn/constrain/revoke/missing-evidence/bad-relayer); as a design/specification workflow it is not subject to the destructive-ops feedback-loop cap.	3 / 3
Progressive Disclosure	The body is well-sectioned and the single reference (agent-supervisor-contract.md) is real, one-level-deep, and self-contained, but substantial schema content is inlined in SKILL.md and the reference is signaled only by a bare end-of-file path bullet rather than linked at the relevant sections, fitting 'some structure but could be better organized'.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific and clearly niched with concrete capability actions and good disambiguation from adjacent skills. Its main weakness is completeness/trigger quality: it relies on specialized jargon and an action-list 'Use to' framing rather than an explicit situational 'Use when...' trigger with natural-language variations.

Suggestions

Add an explicit 'Use when ...' situational trigger naming how a user would request this (e.g., 'Use when GenLayer is the judgment layer for reviewing agent performance, mandate compliance, or delegated-authority supervision').

Soften jargon with at least one common variation users would actually say (e.g., 'review or supervise an on-chain agent', 'agent performance review') alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'specify agent-performance rubrics, evidence schemas, decision outputs, and ERC-7710 connector expectations' — matching the anchor for listing several concrete actions, not just naming a domain.	3 / 3
Completeness	It clearly states what the skill does and its scope boundary, but the 'when' is folded into the action list ('Use to specify...') rather than an explicit situational 'Use when...' trigger, so per the guideline a missing explicit trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain keywords are present ('GenLayer Intelligent Contract supervision', 'ERC-7710 connector', 'evidence schemas') but they are specialized jargon and lack the common natural-language variations a user might say, fitting 'some relevant keywords but missing common variations' rather than broad coverage.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche ('Internet Court adapter for GenLayer Intelligent Contract supervision', 'ERC-7710 connector expectations') and explicitly distinguishes itself from the Intelligent Oracle and deployment skills, making wrong-skill triggering unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: internet-court/internet-court-skill
Path: integrations/genlayer-intelligent-contracts/SKILL.md
Commit: 6a6b81d

Reviewed: 12 days ago

Table of Contents

Discovery Implementation Validation

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.