dojo-model
Create Dojo models for storing game state with proper key definitions, trait derivations, and ECS patterns. Use when defining game entities, components, or state structures.
83
75%
Does it follow best practices?
Impact
100%
1.07xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/dojo-model/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 well-crafted description that clearly identifies a specific niche (Dojo framework game state modeling with ECS patterns) and includes an explicit 'Use when' clause. The main weakness is that trigger terms could be broader to capture more natural user phrasings, particularly around Starknet/onchain gaming terminology and common synonyms for model/schema definitions.
Suggestions
Expand trigger terms to include common variations like 'struct', 'schema', 'Starknet game', or 'onchain game state' to improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating Dojo models, storing game state, defining key definitions, trait derivations, and ECS patterns. These are concrete, domain-specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create Dojo models with proper key definitions, trait derivations, and ECS patterns) and 'when' (use when defining game entities, components, or state structures) with an explicit 'Use when' clause. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'Dojo models', 'game state', 'ECS patterns', 'entities', 'components', but misses common variations users might say such as 'struct', 'schema', 'world state', 'Starknet game', or 'onchain game'. The terms are somewhat niche and technical. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific Dojo framework context combined with ECS patterns and game state modeling. Unlikely to conflict with generic coding skills or other game development skills not targeting Dojo. | 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, actionable skill with excellent concrete code examples covering the major Dojo model patterns. Its main weaknesses are some unnecessary meta-sections (When to Use, What This Skill Does, Quick Start interactive mode) that consume tokens without adding value, and the lack of validation/verification steps in the workflow. The content organization is adequate but could be tightened.
Suggestions
Remove the 'When to Use This Skill', 'What This Skill Does', and 'Quick Start' sections — they describe meta-information that doesn't help Claude generate models and waste tokens.
Add a brief validation step after model creation, such as 'Run `sozo build` to verify models compile correctly' and what common errors look like.
Consider moving the Field Types reference and detailed Model API sections to a separate reference file, keeping SKILL.md focused on patterns and essential usage.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary sections like 'When to Use This Skill' and 'What This Skill Does' which describe meta-information Claude doesn't need. The 'Quick Start' interactive/direct mode section also adds little value. The core model patterns and API sections are well-written and lean. | 2 / 3 |
Actionability | The skill provides fully executable Cairo code examples throughout, covering all major patterns (player-owned, composite keys, singletons, ECS composition). Import statements, read/write operations, and field type references are all concrete and copy-paste ready. | 3 / 3 |
Workflow Clarity | The skill clearly presents model patterns and API usage, but lacks validation checkpoints. There's no guidance on verifying models compile correctly, no error recovery steps, and the 'Next Steps' section is just a list of other skills rather than a validated workflow. For a model creation skill that affects on-chain state, some validation guidance would be valuable. | 2 / 3 |
Progressive Disclosure | The skill references related skills (dojo-system, dojo-test, etc.) at the end, which is good. However, the content is somewhat monolithic — the imports section, model patterns, API reference, and field types could benefit from being split or better signaled. The inline content is borderline too long for a single file but not egregiously so. | 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.