test-physics
Test Havok physics system (gravity, rigid bodies, static vs dynamic) against the physics example using the iwsdk CLI.
66
80%
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 ./.claude/skills/test-physics/SKILL.mdQuality
Discovery
82%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 strong in specificity and distinctiveness, clearly identifying the Havok physics system, specific physics concepts (gravity, rigid bodies, static vs dynamic), and the iwsdk CLI tool. Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill over others.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks to test or validate Havok physics behavior, run physics examples, or debug rigid body simulations with the iwsdk CLI.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: testing Havok physics system with specific aspects (gravity, rigid bodies, static vs dynamic), references a specific tool (iwsdk CLI), and mentions testing against a physics example. | 3 / 3 |
Completeness | Clearly answers 'what' (test Havok physics system aspects using iwsdk CLI), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'Havok', 'physics', 'gravity', 'rigid bodies', 'static', 'dynamic', 'iwsdk CLI', 'physics example'. These are domain-specific terms a user working with this system would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: Havok physics system testing via iwsdk CLI is very specific and unlikely to conflict with other skills. The combination of Havok, physics testing, and iwsdk CLI creates a unique fingerprint. | 3 / 3 |
Total | 11 / 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 strong, highly actionable test procedure skill with excellent workflow clarity including validation checkpoints, error recovery, and deterministic testing patterns. The main weakness is its length — while most content is necessary, some sections (Known Issues, repeated IMPORTANT notes) add verbosity. The progressive disclosure could benefit from splitting reference material into separate files for a document of this size.
Suggestions
Consider moving the 'Known Issues & Workarounds' section to a separate KNOWN_ISSUES.md file and referencing it from the main skill to reduce token footprint.
Remove or consolidate the repeated IMPORTANT callouts (e.g., 'run each command one at a time' and 'use sleep N') into a single upfront note to reduce redundancy.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is necessary for the 5 test suites. Some sections could be tightened (e.g., the Known Issues section explains concepts Claude could infer, and some IMPORTANT callouts are repeated). However, the bulk of the content is actionable commands and assertions. | 2 / 3 |
Actionability | Every step provides exact CLI commands with concrete arguments, specific assertion criteria (field names, expected values, comparison operators), and copy-paste ready bash commands. The placeholders like <sphere> and <floor> are clearly defined through a discovery step. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (install → start server → verify connectivity → run suites → cleanup) with explicit validation checkpoints at each stage, error recovery procedures, retry logic, and a feedback loop for transient failures. The pause/snapshot/step/diff pattern for deterministic testing is well-structured with validation gates. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headers and numbered steps, but it's a monolithic ~200-line document. The Known Issues section and Recovery section could potentially be split into separate reference files. However, with no bundle files provided, the single-file approach is acceptable for a test procedure, though it's on the long side. | 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 |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- facebook/immersive-web-sdk
- Commit
3a08b40
- 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.