iwsdk-planner
IWSDK project planning and best practices guide. Use when planning new IWSDK features, designing systems/components, reviewing IWSDK code architecture, or when the user asks about IWSDK patterns, ECS design, signals, or reactive programming in this codebase.
57
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/starter-assets/claude-injections/skills/iwsdk-planner/SKILL.mdQuality
Discovery
89%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 skill description that clearly identifies its niche (IWSDK project guidance) and provides explicit trigger conditions. Its main weakness is that the 'what' portion is somewhat vague—'planning and best practices guide' doesn't convey specific concrete actions the skill enables. The trigger terms are well-chosen and project-specific, making it highly distinctive.
Suggestions
Replace the vague 'planning and best practices guide' with specific concrete actions, e.g., 'Provides architectural patterns for ECS entities, guides signal/reactive programming implementation, reviews component design for IWSDK compliance.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (IWSDK) and mentions some relevant concepts like ECS design, signals, and reactive programming, but doesn't list concrete actions beyond vague terms like 'planning', 'designing', and 'reviewing'. It describes categories of activity rather than specific capabilities. | 2 / 3 |
Completeness | Clearly answers both 'what' (project planning and best practices guide for IWSDK) and 'when' with an explicit 'Use when...' clause listing multiple trigger scenarios: planning features, designing systems, reviewing architecture, or asking about specific patterns. | 3 / 3 |
Trigger Term Quality | Includes several natural keywords a user working in this codebase would use: 'IWSDK', 'ECS design', 'signals', 'reactive programming', 'code architecture', 'patterns'. These are terms a developer would naturally mention when seeking guidance on this specific project. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the project-specific name 'IWSDK' and the combination of domain-specific terms (ECS design, signals, reactive programming). Unlikely to conflict with generic coding or architecture skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides exceptionally actionable and concrete guidance for IWSDK development with excellent executable code examples and comprehensive API coverage. However, it is severely over-long and monolithic — duplicating content (asset loading appears twice), inlining extensive reference material that should be in separate files, and consuming far more tokens than necessary. The workflow sections lack validation checkpoints for error recovery.
Suggestions
Split the monolithic file into a concise SKILL.md overview (~150 lines) with references to separate files: COMPONENTS.md, SYSTEMS.md, XR_INPUT.md, ASSET_GUIDE.md, ANTI_PATTERNS.md
Remove duplicated content — Asset Loading (section 14) is nearly identical to the AssetManager section under 'What IWSDK Provides'; consolidate into one location
Remove explanatory text Claude doesn't need (e.g., 'These are useful when you need to position an object in world space but it's nested under transformed parents') and let the code examples speak for themselves
Add validation/verification steps to workflows — e.g., after World.create(), check that expected systems are registered; after enabling locomotion, verify collision geometry exists
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~800+ lines. There is massive duplication (e.g., Asset Loading appears twice with nearly identical code, XR input is covered in multiple sections). Many sections explain concepts Claude already knows (what enums are, what TypedArrays are). The component reference table, systems reference table, and reinvention risk table all add significant token cost. Much of this could be condensed by 50-70% without losing actionable information. | 1 / 3 |
Actionability | The skill excels at actionability with fully executable TypeScript code examples throughout, specific API signatures, concrete component configurations, and copy-paste ready patterns. Every section includes real code with correct imports and realistic parameter values. | 3 / 3 |
Workflow Clarity | The 'When Planning a New Feature' checklist provides a clear sequence, and the Post-Creation Initialization Sequence is well-ordered. However, there are no validation checkpoints or feedback loops for error recovery in the workflows. The Feature Decision Matrix is helpful but lacks explicit 'if this fails, do X' guidance. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files for detailed content. The entire API reference, all component docs, asset selection guides, and anti-patterns are all inlined in a single massive file. Categories like the full XR input API, physics shapes, audio enums, and the Kenney asset catalog guide should be split into separate referenced files. | 1 / 3 |
Total | 7 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (1468 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- facebook/immersive-web-sdk
- Commit
b3d1162
- 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.