dojo-test
Write tests for Dojo models and systems using spawn_test_world, cheat codes, and assertions. Use when testing game logic, verifying state changes, or ensuring system correctness.
79
70%
Does it follow best practices?
Impact
99%
2.02xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/dojo-test/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.
This is a solid description that clearly identifies both what the skill does and when to use it, targeting the specific Dojo testing niche. Its main weakness is that the actions described are somewhat general ('write tests') rather than listing multiple concrete testing operations, and it could include more natural trigger term variations that users might employ.
Suggestions
Add more specific concrete actions such as 'set up test contracts, mock world state, validate component updates, test system dispatches'
Include additional trigger term variations users might say, such as 'unit test', 'Cairo test', '#[test]', 'test contract', or 'Katana testing'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Dojo testing) and some specific tools (spawn_test_world, cheat codes, assertions), but doesn't list multiple concrete actions beyond 'write tests'. The specific tools mentioned add some concreteness, but the actions themselves remain somewhat general. | 2 / 3 |
Completeness | Clearly answers both 'what' (write tests for Dojo models and systems using spawn_test_world, cheat codes, and assertions) and 'when' (use when testing game logic, verifying state changes, or ensuring system correctness) with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'tests', 'Dojo models', 'systems', 'spawn_test_world', 'cheat codes', 'game logic', 'state changes', and 'system correctness'. However, it misses common variations a user might say such as 'unit tests', 'integration tests', '#[test]', 'Cairo tests', or 'Katana'. | 2 / 3 |
Distinctiveness Conflict Risk | The description targets a very specific niche — Dojo framework testing with specific tools like spawn_test_world and cheat codes. This is unlikely to conflict with general testing skills or other framework-specific skills. | 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 solid, actionable skill with excellent executable code examples covering the full spectrum of Dojo testing patterns. Its main weaknesses are moderate verbosity from non-essential sections (interactive mode descriptions, 'What This Skill Does') and a monolithic structure that could benefit from splitting detailed patterns into separate files. The workflow is clear through examples but lacks explicit error recovery guidance.
Suggestions
Remove the 'When to Use This Skill', 'What This Skill Does', and 'Quick Start' interactive/direct mode sections — they consume tokens without adding actionable guidance for Claude.
Move the detailed cheat codes section and test patterns into a separate DOJO_TEST_PATTERNS.md reference file, keeping only a brief summary and link in the main skill.
Add a brief troubleshooting/error recovery note (e.g., common test failures like missing model registration or permission errors and how to fix them).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary sections like 'When to Use This Skill', 'What This Skill Does', and 'Quick Start' interactive/direct mode descriptions that don't add actionable value. The 'Next Steps' and 'Related Skills' sections also add padding. However, the core technical content is well-structured without over-explaining concepts. | 2 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Cairo code examples covering unit tests, integration tests, cheat codes, test patterns, and model read/write operations. The code is complete with proper imports and realistic assertions. | 3 / 3 |
Workflow Clarity | The test workflow is implicitly clear through examples (setup world → register resources → perform actions → assert), but there's no explicit validation checkpoint or error recovery guidance. For test generation, the sequence is mostly self-evident, but the 'Next Steps' section only lists commands without feedback loops (e.g., what to do when tests fail). | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a useful reference table, but it's quite long (~200+ lines of inline content) with detailed cheat code examples and multiple test patterns that could be split into separate reference files. The references to related skills are present but the skill itself is somewhat monolithic. | 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
- steebchen/proof-of-war
- Commit
44466c6
- 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.