iwsdk-debug
Debug continuous behavior in WebXR scenes — physics, animations, collisions, game loops, or any real-time interaction that happens too fast for an agent to observe. Uses ECS pause/step/snapshot/diff to freeze time and inspect state frame by frame.
73
91%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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.
This is a strong, highly specific description that clearly communicates a narrow and well-defined capability. The domain (WebXR), the problem space (continuous/real-time behavior debugging), and the technique (ECS pause/step/snapshot/diff) are all clearly articulated. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user needs to debug real-time WebXR behavior such as physics glitches, animation bugs, collision issues, or game loop problems that are too fast to observe directly.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: debug continuous behavior, physics, animations, collisions, game loops, real-time interaction. Also specifies concrete techniques: ECS pause/step/snapshot/diff, freeze time, inspect state frame by frame. | 3 / 3 |
Completeness | Clearly answers 'what' (debug continuous behavior in WebXR scenes using ECS pause/step/snapshot/diff) but lacks an explicit 'Use when...' clause. The 'when' is implied by the context but not explicitly stated with trigger guidance. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a user would say: 'WebXR', 'physics', 'animations', 'collisions', 'game loops', 'real-time', 'debug', 'frame by frame', 'ECS', 'pause', 'snapshot'. These are terms developers naturally use when encountering these issues. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche: WebXR + continuous behavior debugging + ECS frame-by-frame inspection. This is unlikely to conflict with general debugging skills, general WebXR skills, or general animation skills due to its very specific combination of domain and technique. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that efficiently teaches a complex debugging technique. The core workflow provides a clear mental model, the tool reference is compact and complete, and the domain-specific patterns add genuine value with specific component names and diagnostic steps. The content respects Claude's intelligence while providing the non-obvious details (exact delta values, snapshot limits, pause-before-trigger insight) that make the difference between success and failure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It assumes Claude understands real-time systems, ECS architecture, and physics concepts without explaining them. Every section earns its place — the tool reference table is compact, the patterns section provides domain-specific tips without over-explaining, and the notes section covers only non-obvious gotchas. | 3 / 3 |
Actionability | The skill provides concrete tool calls with exact parameter syntax (e.g., `ecs_step({"count":N,"delta":SECONDS})`), specific delta values for common framerates, specific component names to check in diffs (`PhysicsBody._linearVelocity`), and clear diagnostic steps for common failure modes. Every pattern includes actionable checks rather than vague descriptions. | 3 / 3 |
Workflow Clarity | The core workflow is a clearly numbered 10-step sequence with explicit validation checkpoints (screenshot after stepping, diff to verify changes, repeat loop). The key insight about pausing BEFORE triggering is called out prominently. Each domain pattern builds on the core workflow with specific sequencing. The feedback loop (steps 5-8 repeat) is explicit. | 3 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized with clear sections: core workflow first, then tool reference table, stepping guidelines, domain-specific patterns, and notes. The structure progresses from general to specific, and the patterns section uses headers for easy navigation to relevant domains. No content feels misplaced or in need of extraction. | 3 / 3 |
Total | 12 / 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
b3d1162
- 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.