test-locomotion
Test locomotion system (slide, snap turn, teleport, jump) against the locomotion 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-locomotion/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, listing concrete locomotion actions (slide, snap turn, teleport, jump) and the specific tool (iwsdk CLI). Its main weakness is the lack of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. Adding trigger guidance would elevate this from good to excellent.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user asks to test locomotion features, movement systems, or run iwsdk locomotion tests.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'slide, snap turn, teleport, jump' as well as the tool used ('iwsdk CLI') and the testing context ('locomotion example'). These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' (test locomotion system features against the locomotion example 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 natural keywords a user would say: 'locomotion', 'slide', 'snap turn', 'teleport', 'jump', 'iwsdk CLI', and 'test'. These are domain-specific terms that users working with this system would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: testing a specific locomotion system with specific movement types using a specific CLI tool. Very unlikely to conflict with other skills. | 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 highly actionable and well-structured test procedure with excellent workflow clarity, explicit validation checkpoints, and copy-paste-ready commands throughout. Its main weakness is length — at ~250 lines it pushes the boundary of what should be in a single file, and some patterns (thumbstick release) are repeated. The recovery section and known issues demonstrate thoughtful error handling.
Suggestions
Consider extracting the 6 test suites into a separate TESTS.md file, keeping SKILL.md as an overview with setup, cleanup, and references to the detailed test procedures.
Reduce repetition of thumbstick release commands by defining a reusable pattern once (e.g., 'Release: run the neutral-axes command from the Input Mapping Reference') rather than repeating the full command each time.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~250 lines) but most content is necessary executable commands and assertions. Some sections like 'Known Issues & Workarounds' and the input mapping reference table add useful context. However, the overall length could be tightened slightly — some instructions are repeated (e.g., release thumbstick patterns) and the IMPORTANT callouts are somewhat redundant. | 2 / 3 |
Actionability | Every test step provides exact, copy-paste-ready CLI commands with full JSON arguments, specific assertions to check, and concrete expected values. The input mapping reference table is excellent. Commands include proper flags like --timeout and stderr redirection. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 numbered steps with explicit validation at each stage: connectivity checks before testing, pre-test setup with assertion on error logs, per-suite assertions, and a recovery section with retry logic. The feedback loop for server startup failure and per-suite retry policy are well-defined. | 3 / 3 |
Progressive Disclosure | The content is a monolithic document with no references to external files, which is understandable given no bundle files exist. However, at ~250 lines, the input mapping reference, known issues, and individual test suites could benefit from being split into separate files. The internal organization with clear headers and a summary table is good but the sheer length works against quick scanning. | 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.