CtrlK
BlogDocsLog inGet started
Tessl Logo

iwsdk-physics

Guide for implementing physics in IWSDK projects. Use when adding physics simulation, configuring rigid bodies, collision shapes, applying forces, creating grabbable physics objects, or troubleshooting physics behavior.

84

1.02x
Quality

77%

Does it follow best practices?

Impact

99%

1.02x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./packages/starter-assets/claude-injections/skills/iwsdk-physics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

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 with explicit 'Use when' triggers and domain-specific terminology that makes it highly distinctive. The main weakness is that the 'what' portion is somewhat high-level ('Guide for implementing physics') rather than listing specific concrete actions the skill enables. Overall it performs well across most dimensions.

Suggestions

Replace 'Guide for implementing physics' with more specific concrete actions, e.g., 'Configures rigid body components, sets up collision shapes, applies forces and impulses, and creates grabbable physics objects in IWSDK projects.'

DimensionReasoningScore

Specificity

The description names the domain (physics in IWSDK projects) and lists several actions like 'configuring rigid bodies, collision shapes, applying forces, creating grabbable physics objects,' but these read more like a topic list than concrete actions the skill performs. It says 'Guide for implementing' rather than listing specific outputs or transformations.

2 / 3

Completeness

Clearly answers both what ('Guide for implementing physics in IWSDK projects') and when ('Use when adding physics simulation, configuring rigid bodies, collision shapes, applying forces, creating grabbable physics objects, or troubleshooting physics behavior'). The explicit 'Use when' clause with multiple trigger scenarios is well-formed.

3 / 3

Trigger Term Quality

Includes strong natural trigger terms users would actually say: 'physics simulation', 'rigid bodies', 'collision shapes', 'forces', 'grabbable physics objects', 'troubleshooting physics behavior', and 'IWSDK'. These cover a good range of terms a developer working in this domain would use.

3 / 3

Distinctiveness Conflict Risk

The combination of 'IWSDK' and physics-specific terminology (rigid bodies, collision shapes, grabbable physics objects) creates a very clear niche that is unlikely to conflict with other skills. The domain is narrow and well-defined.

3 / 3

Total

11

/

12

Passed

Implementation

64%

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

This is a thorough and highly actionable physics system guide with excellent executable code examples covering all major use cases. Its main weaknesses are its monolithic length (could benefit from splitting reference material into separate files) and the lack of explicit validation/verification steps integrated into workflows. The troubleshooting section is strong but reactive rather than preventive.

Suggestions

Integrate validation checkpoints into workflows, e.g., 'Verify physics is active: check that world.getSystem(PhysicsSystem) returns a valid system before adding components' or 'After adding PhysicsShape + PhysicsBody, confirm _engineBody != 0 in the next frame.'

Split the detailed reference tables (dimensions by shape type, auto-detection mapping, GLXF configuration, material tuning) into a separate REFERENCE.md file, keeping only the most essential quick-reference in the main SKILL.md.

DimensionReasoningScore

Conciseness

The skill is comprehensive and mostly efficient, but it's quite long (~400+ lines) with some redundancy. The dimensions table is repeated in multiple forms, and the auto-detection mapping table, while useful, adds bulk. The material tuning guide and some explanatory comments could be tightened. However, most content is reference-worthy and not explaining things Claude already knows.

2 / 3

Actionability

Excellent actionability throughout. Every section includes fully executable TypeScript code with correct imports, concrete property values, and copy-paste ready examples. The complete playground example at the end ties everything together. Code examples cover all major use cases: dynamic objects, static colliders, kinematic platforms, grabbable objects, explosions, custom systems, and velocity reading.

3 / 3

Workflow Clarity

The 'Common Workflows' section provides clear step-by-step patterns with numbered comments in code, and the system priority order is well-documented. However, there are no explicit validation checkpoints or error recovery feedback loops. For physics setup (which can silently fail — objects falling through floors, etc.), the troubleshooting section helps but isn't integrated into the workflows as verification steps.

2 / 3

Progressive Disclosure

The content is well-organized with clear section headers and logical progression from basics to advanced patterns. However, this is a monolithic document with no references to external files. Given its length (~400+ lines), the API reference tables, GLXF configuration, material tuning guide, and complete example could reasonably be split into separate referenced files. As a standalone SKILL.md with no bundle, it's a wall of content.

2 / 3

Total

9

/

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.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (602 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

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.