CtrlK
BlogDocsLog inGet started
Tessl Logo

react-three-fiber-game

Build React-hosted 3D browser games with React Three Fiber. Use when the user wants pmndrs-based scene composition, shared React state, and 3D HUD integration inside a React app.

62

Quality

73%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/game-studio/skills/react-three-fiber-game/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

A well-organized, concise architectural-decision skill that defers implementation to one-level references. It would score higher with at least one inline starter snippet and clearer cross-references to verifiable bundle files.

Suggestions

Add one minimal inline R3F Canvas/starter snippet so the body has concrete, executable guidance rather than only directives.

Collapse the overlapping "Use This Skill When", "Do Not Use This Skill When", and "Best Fit Scenarios" sections into a single decision table to remove redundancy.

Verify the referenced files exist within the bundle (the ../../references/*.md and ../web-game-foundations/SKILL.md paths point outside it) and confirm each reference is reachable.

DimensionReasoningScore

Conciseness

The body is lean, directive, and does not explain concepts Claude already knows, but the "Use This Skill When", "Do Not Use This Skill When", and "Best Fit Scenarios" sections overlap somewhat and could be tightened.

4 / 5

Actionability

Concrete architectural directives and named packages ("Use @react-three/rapier for physics", "Keep simulation state outside render components") are present, but for a 3D-game-building skill there is no executable code or commands in the body — implementation detail is deferred entirely to references.

3 / 5

Workflow Clarity

The skill is structured as decision criteria and rules rather than a sequenced process; the numbered Core Rules give ordering but there are no validation checkpoints or a real procedural workflow, which fits anchor 3.

3 / 5

Progressive Disclosure

The body is a clean overview that pushes detail to one-level-deep, labeled references (e.g. "Rapier starter: ../../references/rapier-integration-starter.md"); the referenced bundle files are not present to verify, keeping it just below a 5.

4 / 5

Total

14

/

20

Passed

Description

85%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 strong, specific description with explicit what/when triggers and a clear niche. The main room for improvement is adding common synonyms (R3F, Three.js) and asset-format triggers.

DimensionReasoningScore

Specificity

Names the domain and several concrete capabilities — "Build React-hosted 3D browser games", "pmndrs-based scene composition, shared React state, and 3D HUD integration" — but the single verb "Build" plus abstract framings leave minor coverage gaps versus a comprehensive action list.

4 / 5

Completeness

Explicitly answers both what ("Build React-hosted 3D browser games with React Three Fiber") and when ("Use when the user wants pmndrs-based scene composition, shared React state, and 3D HUD integration inside a React app") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural terms users would say ("React Three Fiber", "shared React state", "3D HUD integration", "React app") but misses common synonyms/extensions like "R3F", "Three.js", or asset extensions such as ".glb".

4 / 5

Distinctiveness Conflict Risk

The "React Three Fiber" / "pmndrs-based" niche is distinct and unlikely to fire for the wrong skill; the React-hosted framing separates it cleanly from vanilla Three.js skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
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.