r3f-physics

React Three Fiber physics with Rapier - RigidBody, colliders, forces, joints, sensors. Use when adding physics simulation, collision detection, character controllers, or creating interactive physics-based experiences.

Quality

82%

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

Quality

Content

72%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 highly actionable, code-dense reference with excellent executable examples and clean section structure. Its main weaknesses are the absence of an explicit workflow with validation checkpoints and a monolithic single-file layout that inlines material better suited to separate reference files.

Suggestions

Add a brief sequenced workflow (e.g. install -> wrap scene in Physics -> add RigidBodies -> tune colliders -> debug) with an explicit validation/check step such as enabling `debug` to confirm colliders match meshes before tuning.

Move the exhaustive API reference (full collider/joint catalog, RigidBody property list, attractor options) into separate reference files under ./references/ and link to them from SKILL.md, keeping only Quick Start and key examples inline to improve progressive disclosure.

Tighten a few verbose sections (e.g. duplicate Physics wrapper boilerplate repeated across examples) by referencing the canonical Quick Start setup once and trimming redundant Suspense/Canvas scaffolding.

Dimension	Reasoning	Score
Conciseness	Mostly lean: each section leads with executable code and brief inline comments rather than prose explaining concepts Claude already knows. The overall length stems from broad coverage, not padding, though a few sections could be tightened further.	4 / 5
Actionability	Nearly every section provides complete, copy-paste-ready TSX examples covering common cases (forces, joints, sensors, instancing, world access); imports and refs are shown concretely.	5 / 5
Workflow Clarity	The body is a topical reference catalog rather than a sequenced workflow; Quick Start gives a basic order but there are no explicit validation checkpoints or error-recovery loops. No destructive/batch cap applies, but multi-step guidance is only implicit.	3 / 5
Progressive Disclosure	Sections are clearly headed and well-organized, but ~820 lines of API reference (all collider/joint types, full property tables) are inlined entirely in SKILL.md with no bundle files; content that would benefit from separate reference files is not split out.	3 / 5
	Total	15 / 20 Passed

Description

92%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, well-constructed description: concrete capabilities, an explicit 'Use when' trigger clause, and a distinct niche. Third-person voice is maintained throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities and API entities ("RigidBody, colliders, forces, joints, sensors") plus concrete actions ("adding physics simulation, collision detection, character controllers"), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ("React Three Fiber physics with Rapier - RigidBody, colliders, forces, joints, sensors") and when ("Use when adding physics simulation, collision detection, character controllers...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural user-facing phrases like "physics simulation", "collision detection", and "character controllers"; good coverage, though a few common variations (e.g. "rigid body", "3D physics") are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (Rapier physics within React Three Fiber) with distinct triggers; minimal overlap risk with non-physics R3F skills.	5 / 5
	Total	19 / 20 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
skill_md_line_count	SKILL.md is long (826 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: AzizBelhassan/timeverse
Path: .agents/skills/r3f-physics/SKILL.md
Commit: 9dc2cb4

Reviewed: ~15 hours 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.