CtrlK
BlogDocsLog inGet started
Tessl Logo

test-physics

Test Havok physics system (gravity, rigid bodies, static vs dynamic) against the physics example using the iwsdk CLI.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

96%Weight 40%Scale 1-5

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

An exemplary operational skill: fully executable commands with explicit assertions, a clearly sequenced workflow with validation checkpoints, bounded retry logic, and a lean token budget with no padding. The only structural improvement is splitting detailed suite assertions or known-issues content into reference files to slim the always-loaded SKILL.md.

DimensionReasoningScore

Conciseness

The body is lean and operational throughout: exact CLI invocations with JSON payloads, terse 'Assert:' lines, and no explanations of concepts Claude already knows. Sections like 'Known Issues & Workarounds' carry non-obvious, project-specific facts ('PhysicsManipulation is automatically removed after forces are applied in a single frame'), so every token earns its place. A 4 would require some over-explanation to trim, which is absent.

5 / 5

Actionability

Every instruction is a copy-paste-ready command such as `npx @iwsdk/cli ecs step --input-json '{"count":50}'`, with explicit assertions on the expected JSON output fields (e.g. 'state: "DYNAMIC"', '_engineBody: > 0'). Placeholders like <sphere> are defined in the setup step ('Save the entity named Dynamic Sphere as <sphere>'), and edge cases (SKIP for no static body) are handled. This matches the fully-executable anchor.

5 / 5

Workflow Clarity

A five-step sequence (install, dev server, connectivity check, suites, cleanup) with explicit validation checkpoints: connectivity failure branches to 'report FAIL for all suites and skip to Step 5', each test has 'Assert:' lines, and a Recovery section provides a validate-restart-retry feedback loop bounded by 'Only give up after one retry attempt per suite.' This matches the anchor with explicit validation steps and error-recovery feedback loops.

5 / 5

Progressive Disclosure

No bundle files (references/, scripts/, assets/) exist; the entire skill is a single ~300-line SKILL.md. It is well-sectioned with clear headers (per-suite '### Suite N' sections, Recovery, Known Issues), so navigation is easy and there are no nested or buried references — above the 'some structure' anchor of 3. It falls short of 5 only because content that could live in separate reference files (e.g., the detailed component-registration assertions in Suite 4 and the Known Issues section) is inlined in the main file.

4 / 5

Total

19

/

20

Passed

Description

70%Weight 40%Scale 1-5

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 specific, well-scoped description that clearly states what the skill does and with which tools, with good natural trigger terms for the physics-testing domain. Its main gap is the absence of any explicit 'Use when...' trigger guidance, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to test or verify the physics example, gravity behavior, or rigid bodies in an IWSDK app.'

Broaden trigger-term coverage with natural variations users might say, such as 'physics testing', 'collision behavior', or 'verify gravity'.

Optionally name the test-report deliverable (summary table of suite PASS/FAIL results) so the 'what' is fully comprehensive.

DimensionReasoningScore

Specificity

The description names concrete capabilities — 'Test Havok physics system (gravity, rigid bodies, static vs dynamic) against the physics example using the iwsdk CLI' — listing several specific test areas plus the tool used. It falls short of a 5 because it doesn't comprehensively state what testing involves (assertions, suites, reporting), and is above 3 because more than 1-2 concrete actions are explicitly named.

4 / 5

Completeness

The 'what' is clear (test the Havok physics system's gravity, rigid bodies, static vs dynamic behavior against the physics example), but there is no 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 3. It is not a 4 because the 'when' is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'physics', 'gravity', 'rigid bodies', 'static vs dynamic', 'physics example'. Not a 5 because there are no synonyms or variations (e.g., 'physics testing', 'collision', 'Havok simulation') beyond the single phrasing; not a 3 because coverage of the domain's natural vocabulary is genuinely good rather than partial.

4 / 5

Distinctiveness Conflict Risk

The combination of 'Havok physics system', 'the physics example', and 'the iwsdk CLI' carves out a clear niche with minimal overlap risk against other skills. A 4 would require some minor overlap with closely related skills, which is not the case here.

5 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
facebook/immersive-web-sdk
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.