test-locomotion

Test locomotion system (slide, snap turn, teleport, jump) against the locomotion example using the iwsdk CLI.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exceptionally actionable, concise test harness with clear sequencing and strong validation/recovery loops. The one weakness is progressive disclosure: it is a monolithic single file that could split reusable detail (the input-mapping table, suite templates) into reference files.

Suggestions

Extract the input-mapping reference table and per-suite command templates into a references/ file, keeping SKILL.md as a sequenced overview that links to it.

Factor the repeated screenshot→set-gamepad-state→assert pattern into a documented per-suite template to cut repetition and length.

Add a short 'Use when' pointer in the body so the trigger context matches the description.

Dimension	Reasoning	Score
Conciseness	Lean, command-driven procedural content with no conceptual filler (no explanation of XR or locomotion concepts); every token is a concrete command, assertion, or setup step that earns its place.	3 / 3
Actionability	Fully executable `npx iwsdk` commands with complete --input-json payloads, exact axis/button values, and precise timeouts — copy-paste ready, matching the highest anchor.	3 / 3
Workflow Clarity	A clearly sequenced Step 1→5 flow with explicit validation checkpoints (connectivity check, pre-test setup, per-suite assertions) and a Recovery feedback loop (stop → restart → re-setup → retry), plus fail-fast skip-to-Step-5 paths.	3 / 3
Progressive Disclosure	It is a single self-contained ~380-line file with no bundle/reference files and everything inline; sections are well-organized, but the monolithic structure misses the one-level-deep reference split the rubric rewards for content this size.	2 / 3
	Total	11 / 12 Passed

Description

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.

A concise, specific third-person description that clearly conveys the skill's concrete actions and domain. Its only gap is the absence of an explicit 'Use when...' trigger clause, which caps its completeness at 2.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when testing the iwsdk locomotion example or verifying slide, snap turn, teleport, or jump behavior.'

Optionally broaden trigger terms to catch paraphrases like 'movement', 'controller input', or 'XR navigation testing'.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('slide, snap turn, teleport, jump') tested against a specific target ('the locomotion example') via a specific tool ('iwsdk CLI'), matching the highest anchor.	3 / 3
Completeness	It clearly states what the skill does, but lacks any 'Use when...' trigger clause; per rubric guidelines a missing explicit trigger caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Natural domain keywords users would say — 'locomotion', 'slide', 'snap turn', 'teleport', 'jump' — give good coverage of the surface the skill covers.	3 / 3
Distinctiveness Conflict Risk	The narrow 'locomotion' niche plus the specific iwsdk locomotion example make it clearly distinguishable and unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: facebook/immersive-web-sdk
Commit: 42af866

Reviewed: 6 days 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.