dojo-deploy
Deploy Dojo worlds to local Katana, testnet, or mainnet. Configure Katana sequencer and manage deployments with sozo. Use when deploying your game or starting local development environment.
90
88%
Does it follow best practices?
Impact
93%
1.36xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 strong skill description that clearly identifies the specific toolchain (Dojo, Katana, sozo), lists concrete actions (deploy, configure, manage), specifies target environments, and includes an explicit 'Use when' clause. The only minor note is the use of second person 'your game' in the trigger clause, but this is minimal and doesn't significantly detract from the description's effectiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: deploying Dojo worlds, configuring Katana sequencer, managing deployments with sozo, and specifies target environments (local Katana, testnet, mainnet). | 3 / 3 |
Completeness | Clearly answers both what ('Deploy Dojo worlds to local Katana, testnet, or mainnet. Configure Katana sequencer and manage deployments with sozo') and when ('Use when deploying your game or starting local development environment'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'deploy', 'Dojo', 'Katana', 'testnet', 'mainnet', 'sozo', 'local development environment', 'game'. These cover the key terms a Dojo developer would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with domain-specific terms like 'Dojo worlds', 'Katana sequencer', and 'sozo' that are unique to the Dojo/Starknet ecosystem, making conflicts with other skills very unlikely. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 deployment guide with clear workflows, executable commands, and good troubleshooting coverage. Its main weakness is length—it tries to be both an overview and a comprehensive reference, leading to redundancy and a monolithic feel. Trimming repeated commands, removing obvious sections (When to Use, What This Skill Does), and extracting Katana configuration and Slot deployment into separate files would significantly improve it.
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.
Extract the Katana Configuration section (mining modes, persistent storage, network forking, Cartridge Controller) into a separate KATANA_CONFIG.md reference file and link to it.
Deduplicate `katana --dev --dev.no-fee` which appears 4 times; define it once and reference it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy (e.g., `katana --dev --dev.no-fee` appears 4 times, the 'When to Use' and 'What This Skill Does' sections add little value, and the Quick Start section with quoted strings is unnecessary). The content could be tightened by ~30% without losing information. | 2 / 3 |
Actionability | Provides fully executable bash commands, complete TOML configuration examples, concrete sozo commands with arguments, and a detailed manifest JSON example. Commands are copy-paste ready with specific flags and URLs. | 3 / 3 |
Workflow Clarity | The deployment workflow is clearly sequenced (build → inspect → migrate → verify) with explicit validation checkpoints. The deployment checklist includes pre/during/post steps, and the troubleshooting section provides error recovery guidance. The local deploy script description includes health checking and cleanup on exit. | 3 / 3 |
Progressive Disclosure | The skill references other skills (dojo-config, dojo-indexer, etc.) and external docs, which is good. However, the file itself is quite long (~300 lines) with sections like Katana Configuration, Mining Modes, Network Forking, and Slot Deployment that could be split into separate reference files. The inline content is heavy for a SKILL.md overview. | 2 / 3 |
Total | 10 / 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.