threejs-debug-profiler

Debug and profile Three.js browser games. Combines scene debugging, render/runtime/loading/animation/resize/mobile input fixes, performance profiling, draw calls, triangles, textures, memory, shader/post-processing cost, bundle size, and mobile DPR/input issues.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/threejs-debug-profiler/SKILL.md

Quality

Content

85%Weight 40%Scale 1-3

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

The skill body is lean, well-sequenced with explicit verification steps, and uses clean one-level-deep references that all resolve to real files. The main gap is actionability: concrete execution detail lives in the referenced checklists rather than inline, so a reader of SKILL.md alone lacks copy-paste-ready commands or code.

Suggestions

Add one short inline executable example per workflow (e.g. a renderer-stats snippet or a `renderer.info` / `performance.now()` baseline command) so the body is actionable without opening the references.

Clarify the relationship between `debug-profile-checklists.md` and the three `checklists/*.md` files to avoid redundant navigation — note which is the entry point and which are subsets.

In the Debug Workflow, mention the specific verification commands/tools (e.g. DevTools Performance tab, `renderer.info.render.calls`) so the checkpoint step is concrete rather than descriptive.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no concept-explaining fluff (no "Three.js is a 3D library" preamble); every section delivers actionable guidance, matching the lean-and-efficient anchor.	3 / 3
Actionability	Concrete checklists and named techniques ("instancing, shared resources, culling, LOD, DPR cap") give specific direction, but the executable "how" is delegated to referenced files and there are no inline commands or code, leaving key details external.	2 / 3
Workflow Clarity	Two clearly numbered sequences include explicit validation checkpoints (Debug step 9 verify nonblank canvas/errors/broken path; Performance step 5 re-measure and verify visuals) plus a tracked reference ledger, matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	The body is a concise overview pointing to one-level-deep references (debug-profile-checklists.md, checklists/scene-debugging.md, performance-profile.md, mobile-input.md, prompt-templates.md) — all verified to exist and each tied to a specific use case, matching the well-signaled one-level-deep anchor.	3 / 3
	Total	11 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 specific and well-scoped to a clear niche, but it over-relies on technical metric jargon and omits any explicit 'Use when...' trigger guidance. Adding natural user-facing trigger terms and a usage clause would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when debugging or optimizing Three.js browser games, or when the user reports lag, low FPS, a blank canvas, or mobile input/render issues."

Replace some jargon ("shader/post-processing cost", "DPR") with natural user-facing terms ("slow/stuttering frame rate", "mobile scaling") alongside the technical terms.

Lead with the broadest natural triggers ("debug and profile Three.js / WebGL games") before the detailed metric list to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists many concrete capabilities ("scene debugging, render/runtime/loading/animation/resize/mobile input fixes", "draw calls, triangles, textures, memory, shader/post-processing cost, bundle size"), matching the multiple-specific-actions anchor rather than the partial domain-only anchor.	3 / 3
Completeness	Clearly states what the skill does, but lacks any "Use when..." trigger clause; per the rubric, a missing explicit trigger caps completeness at 2 rather than 3.	2 / 3
Trigger Term Quality	Includes some natural terms ("Three.js browser games", "debug", "profile") but is dominated by technical jargon ("DPR/input", "shader/post-processing cost") and misses common user phrasings like "lag", "low FPS", or "blank canvas".	2 / 3
Distinctiveness Conflict Risk	"Three.js browser games" is a narrow, clearly scoped niche unlikely to overlap with other skills, matching the clear-niche anchor rather than the somewhat-generic anchor.	3 / 3
	Total	10 / 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
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: majidmanzarpour/threejs-game-skills
Path: skills/threejs-debug-profiler/SKILL.md
Commit: 7221c1f

Reviewed: 13 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.