dojo-init
Initialize new Dojo projects with proper directory structure, configuration files, and dependencies. Use when starting a new Dojo game project or setting up the initial project structure.
80
70%
Does it follow best practices?
Impact
100%
1.47xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/dojo-init/SKILL.mdQuality
Discovery
75%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 well-structured with a clear 'Use when' clause and targets a distinct niche (Dojo game projects), making it strong on completeness and distinctiveness. However, it could be more specific about the concrete actions performed and include more natural trigger terms that users might use when requesting this skill.
Suggestions
Add more specific concrete actions, e.g., 'Generate Scarb.toml, scaffold contracts and systems directories, configure world manifest'
Include additional trigger terms users might naturally say, such as 'scaffold', 'bootstrap', 'create Dojo project', 'Starknet game', or 'new Scarb project'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Dojo projects) and some actions (initialize, directory structure, configuration files, dependencies), but doesn't list specific concrete actions like 'create Scarb.toml', 'scaffold contracts directory', or 'configure world manifest'. | 2 / 3 |
Completeness | Clearly answers both 'what' (initialize new Dojo projects with proper directory structure, configuration files, and dependencies) and 'when' (Use when starting a new Dojo game project or setting up the initial project structure) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'Dojo', 'project', 'directory structure', 'configuration files', and 'dependencies', but misses common variations users might say such as 'scaffold', 'bootstrap', 'new game', 'Starknet', 'Scarb', 'setup', or 'create project'. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche—Dojo game project initialization—which is unlikely to conflict with other skills. The combination of 'Dojo', 'game project', and project initialization creates a clear, distinct trigger profile. | 3 / 3 |
Total | 10 / 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 reasonably well-structured initialization skill with strong actionability — concrete commands and complete configuration files make it immediately usable. However, it's somewhat verbose with redundant sections (What This Skill Does vs Project Structure, Starter Template Contents describing boilerplate), and the workflow lacks validation checkpoints for error recovery. The progressive disclosure to related skills is good but inline content could be trimmed.
Suggestions
Remove the 'What This Skill Does' section as it duplicates the Project Structure section, and trim 'Starter Template Contents' to a one-line summary since Claude can read the generated files directly.
Add validation checkpoints to the Development Workflow, e.g., 'Verify build succeeded before migrating' and 'If sozo migrate fails, check that Katana is running and dojo_dev.toml has correct account credentials.'
Remove the 'When to Use This Skill' section — these trigger phrases are metadata concerns, not actionable content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary sections like 'What This Skill Does' which largely repeats the project structure section, and 'Starter Template Contents' which describes boilerplate code Claude doesn't need explained. The 'When to Use This Skill' section with example prompts is also unnecessary padding. However, the configuration examples and project structure are useful reference material. | 2 / 3 |
Actionability | The skill provides fully executable commands (sozo init, katana, sozo build, sozo migrate, sozo execute, sozo test) and complete, copy-paste ready configuration files (Scarb.toml, dojo_dev.toml). The development workflow gives a concrete end-to-end sequence. | 3 / 3 |
Workflow Clarity | The development workflow has clear numbered steps with executable commands, but lacks validation checkpoints. There's no verification after initialization (e.g., checking the project was created correctly), no validation after build, and no error recovery guidance if sozo init or sozo migrate fails. | 2 / 3 |
Progressive Disclosure | The skill references related skills (dojo-model, dojo-system, etc.) which is good progressive disclosure, but the main content is somewhat monolithic — the full config file contents and starter template descriptions could be referenced rather than inlined. The 'Starter Template Contents' section describing models/systems/tests adds bulk that could live in a separate reference. | 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 | |
- Repository
- dojoengine/book
- Commit
093849a
- 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.