Configure Scarb.toml, dojo profiles, world settings, and dependencies. Use when setting up project configuration, managing dependencies, or configuring deployment environments.
83
75%
Does it follow best practices?
Impact
100%
1.31xAverage score across 3 eval scenarios
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/dojo-config/SKILL.mdQuality
Discovery
85%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 in the Dojo/Starknet ecosystem configuration space. It names specific artifacts and includes an explicit 'Use when' clause. The main weakness is that trigger term coverage could be broader to capture more natural user phrasings.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: configure Scarb.toml, dojo profiles, world settings, and dependencies. These are distinct, named configuration artifacts rather than vague abstractions. | 3 / 3 |
Completeness | Clearly answers both 'what' (configure Scarb.toml, dojo profiles, world settings, dependencies) and 'when' with an explicit 'Use when...' clause covering project configuration setup, dependency management, and deployment environment configuration. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Scarb.toml', 'dojo profiles', 'dependencies', and 'deployment environments', but misses common variations users might say such as 'toml config', 'Dojo project setup', 'world config', or 'Scarb configuration file'. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to domain-specific terms like 'Scarb.toml', 'dojo profiles', and 'world settings' which are specific to the Dojo/Starknet ecosystem and unlikely to conflict with generic configuration or dependency management 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.
This is a solid reference skill for Dojo configuration management with excellent actionability—every configuration scenario includes complete, copy-paste ready TOML examples. The main weaknesses are the length (could benefit from splitting detailed examples into separate files) and the lack of validation steps after configuration changes. Some introductory sections add unnecessary tokens without providing value to Claude.
Suggestions
Remove the 'When to Use This Skill', 'What This Skill Does', and 'Quick Start' sections—they add ~30 lines of low-value content that Claude doesn't need.
Add a validation step after configuration changes, e.g., 'Run `sozo build` to verify configuration is valid before proceeding to deployment.'
Move the full environment examples (Development and Production) and the detailed dependency examples into a separate CONFIGURATION_EXAMPLES.md file, keeping only the essential patterns inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary sections like 'When to Use This Skill' trigger phrases and 'What This Skill Does' summaries that repeat the description. The 'Quick Start' interactive/direct mode section adds little value. However, the configuration examples themselves are lean and well-structured. | 2 / 3 |
Actionability | The skill provides fully concrete, copy-paste ready TOML configuration blocks for every scenario: Scarb.toml, profile configs, dependencies, permissions, environment examples for dev and production. Commands like `sozo build --profile mainnet` are specific and executable. | 3 / 3 |
Workflow Clarity | The profile system and configuration steps are presented clearly, but there are no validation checkpoints. After editing configuration files, there's no step to validate the TOML syntax, verify the configuration works, or recover from errors. The troubleshooting section partially compensates but doesn't constitute a proper feedback loop. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and references to related skills at the bottom. However, the file is quite long (~200 lines of substantive content) with detailed environment examples and full configuration blocks that could be split into separate reference files. The inline content is heavy for a SKILL.md overview. | 2 / 3 |
Total | 9 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
093849a
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.