dojo-world

Manage world permissions, namespaces, resource registration, and access control. Use when configuring world ownership, setting up authorization policies, or managing resource permissions.

1.18x

Quality

66%

Does it follow best practices?

Impact

97%

1.18x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/dojo-world/SKILL.md

Quality

Content

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 with excellent actionability - providing concrete, executable examples across TOML config, CLI, and Cairo code. Its main weaknesses are verbosity (explaining concepts Claude already knows, redundant sections) and lack of validation checkpoints for potentially destructive permission operations like ownership transfers. The content would benefit from trimming explanatory sections and adding explicit verification steps.

Suggestions

Remove or drastically shorten the 'When to Use This Skill', 'What This Skill Does', and 'Permission Concepts' sections - Claude understands permission hierarchies and these consume tokens without adding actionable value.

Add explicit verification steps after permission changes, especially for the ownership transfer pattern (e.g., verify new owner has access before revoking old owner: `assert(world.is_owner(..., new_owner), 'grant failed')`).

Move Permission Events, Permission Patterns, and Common Scenarios into separate reference files to reduce the main skill's token footprint and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The skill is fairly comprehensive but includes some unnecessary sections like 'When to Use This Skill' with trivial examples, 'What This Skill Does' that restates the title, 'Permission Events' struct definitions that add limited value, and 'Next Steps' with generic advice. The permission concepts section explains things Claude likely already understands. Could be tightened significantly.	2 / 3
Actionability	Provides fully executable code examples across multiple contexts: TOML configuration, CLI commands (sozo auth grant/revoke/list), and Cairo runtime code. Examples are concrete with realistic resource names and clear patterns. Copy-paste ready for both configuration and runtime scenarios.	3 / 3
Workflow Clarity	While individual operations are clear, the skill lacks explicit validation checkpoints. For permission management (which can be destructive - revoking owner access incorrectly could lock out administrators), there are no verification steps after granting/revoking permissions. The 'Transfer Namespace Ownership' example is particularly risky without a validation step between grant and revoke. The troubleshooting section helps but doesn't constitute proper feedback loops.	2 / 3
Progressive Disclosure	The content is well-structured with clear headers and logical progression from concepts to configuration to runtime to patterns. However, at ~200+ lines, some sections (Permission Events, Common Scenarios, Permission Patterns) could be split into separate reference files. The 'Related Skills' section provides good cross-references but the main file is monolithic.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 structurally sound with both 'what' and 'when' clauses clearly present, earning full marks on completeness. However, the actions described are somewhat abstract and overlapping (permissions, access control, authorization policies are closely related concepts), and the trigger terms lean technical without covering natural user language variations. The 'world' qualifier adds some distinctiveness but could be clearer about what system or platform this applies to.

Suggestions

Add more concrete actions to improve specificity, e.g., 'create and delete namespaces, assign ownership roles, grant or revoke resource access, define authorization policies'.

Include more natural trigger terms users might say, such as 'who can access', 'grant access', 'roles', 'RBAC', or the specific platform/system name this skill applies to.

Dimension	Reasoning	Score
Specificity	Names the domain (permissions/access control) and lists several actions (manage permissions, namespaces, resource registration, access control), but these are somewhat abstract and overlapping rather than concrete distinct operations like 'create namespace', 'assign role', or 'revoke access'.	2 / 3
Completeness	Clearly answers both 'what' (manage world permissions, namespaces, resource registration, and access control) and 'when' (Use when configuring world ownership, setting up authorization policies, or managing resource permissions) with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes relevant terms like 'permissions', 'namespaces', 'access control', 'authorization policies', and 'resource registration', but these are somewhat technical/jargon-heavy. Missing more natural user phrases like 'who can access', 'grant access', 'roles', 'ACL', or 'RBAC'.	2 / 3
Distinctiveness Conflict Risk	The term 'world permissions' and 'world ownership' provide some distinctiveness suggesting a specific platform or system, but 'access control', 'permissions', and 'authorization policies' are generic enough to potentially overlap with other security or IAM-related skills.	2 / 3
	Total	9 / 12 Passed

Validation

90%

Warnings & errors only

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: 2 months ago

Table of Contents

Discovery Implementation Validation

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.