mcpbeat Sign in

Unity Navmesh Agent Skill

Bake and query Unity NavMesh — bake/rebake navigation meshes, query paths, and configure bake settings. Use when setting up navigation, baking a NavMesh, testing agent paths, or tuning bake parameters, even if the user just says "导航网格" or "寻路". 烘焙与查询 Unity NavMesh(烘焙/重烘焙导航网格、查询路径、配置烘焙设置);当用户要搭建导航、烘焙 NavMesh、测试 agent 路径或调整烘焙参数时使用。

2k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1536
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/Besty0728/Unity-Skills --skill unity-navmesh

The instruction itself

14 sections, as written by the author

Bake / clear NavMesh data, calculate paths, sample positions, and configure NavMeshAgent / NavMeshObstacle components.

Operating Mode

  • Approval:查询类 skill(navmesh_calculate_path / navmesh_sample_position / navmesh_get_settings,源码标 SkillMode.SemiAuto)直接执行;变更类(navmesh_bake / navmesh_add_agent / navmesh_set_agent / navmesh_add_obstacle / navmesh_set_obstacle / navmesh_set_area_cost,标 SkillMode.FullAuto)需用户 grant,grant 后服务端一步执行返结果。
  • Auto / Bypass:所有未被禁列表拦截的 skill 直接执行。
  • 本模块含 Delete 类 skillnavmesh_clear 标记为 SkillOperation.Delete,会被 IsForbiddenInSemi 静态拦截 —— 仅 Bypass 模式或将其加入 Allowlist 才能调用。
  • navmesh_bake 同步阻塞主线程;大场景可能很慢,调用前提醒用户。

DO NOT (common hallucinations):

  • navmesh_create does not exist → use navmesh_bake to generate NavMesh
  • navmesh_add_agent_component / navmesh_set_agent_speed do not exist → use navmesh_add_agent + navmesh_set_agent (convenience wrappers), or component_add/component_set_property for full control
  • NavMesh must be re-baked after scene geometry changes

Routing:

  • For NavMeshAgent/NavMeshObstacle components → use component module
  • For path calculation → navmesh_calculate_path (this module)

Skills

Bake the NavMesh (Synchronous). Warning: Can be slow.

Parameters: None.

Clear the NavMesh data.

Parameters: None.

Calculate a path between two points.

Parameters:

  • startX, startY, startZ (float): Start position.
  • endX, endY, endZ (float): End position.
  • areaMask (int, optional): NavMesh area mask.

Returns: { status, valid, distance, cornerCount, corners }

  • status: NavMeshPathStatus string (PathComplete / PathPartial / PathInvalid)
  • valid: true only when status == "PathComplete"
  • distance: total path length (0 for invalid paths)
  • cornerCount: number of corner points in corners
  • corners: array of {x, y, z} waypoints (empty when no path)

Add NavMeshAgent component to an object.

| Parameter | Type | Required | Default | Description |

|-----------|------|----------|---------|-------------|

| name | string | No | null | GameObject name |

| instanceId | int | No | 0 | GameObject instance ID |

| path | string | No | null | GameObject hierarchy path |

Returns: { success, gameObject }

Set NavMeshAgent properties (speed, acceleration, radius, height, stoppingDistance).

| Parameter | Type | Required | Default | Description |

|-----------|------|----------|---------|-------------|

| name | string | No | null | GameObject name |

| instanceId | int | No | 0 | GameObject instance ID |

| path | string | No | null | GameObject hierarchy path |

| speed | float | No | null | Agent movement speed |

| acceleration | float | No | null | Agent acceleration |

| angularSpeed | float | No | null | Agent angular speed |

| radius | float | No | null | Agent radius |

| height | float | No | null | Agent height |

| stoppingDistance | float | No | null | Distance to stop before target |

Returns: { success, gameObject, speed, radius }

Add NavMeshObstacle component to an object.

| Parameter | Type | Required | Default | Description |

|-----------|------|----------|---------|-------------|

| name | string | No | null | GameObject name |

| instanceId | int | No | 0 | GameObject instance ID |

| path | string | No | null | GameObject hierarchy path |

| carve | bool | No | true | Enable carving |

Returns: { success, gameObject, carving }

Set NavMeshObstacle properties (shape, size, carving).

| Parameter | Type | Required | Default | Description |

|-----------|------|----------|---------|-------------|

| name | string | No | null | GameObject name |

| instanceId | int | No | 0 | GameObject instance ID |

| path | string | No | null | GameObject hierarchy path |

| shape | string | No | null | Obstacle shape (e.g. Box, Capsule) |

| sizeX | float | No | null | Obstacle size X |

| sizeY | float | No | null | Obstacle size Y |

| sizeZ | float | No | null | Obstacle size Z |

| carving | bool | No | null | Enable carving |

Returns: { success, gameObject, shape, carving }

Find nearest point on NavMesh.

| Parameter | Type | Required | Default | Description |

|-----------|------|----------|---------|-------------|

| x | float | Yes | - | Source position X |

| y | float | Yes | - | Source position Y |

| z | float | Yes | - | Source position Z |

| maxDistance | float | No | 10 | Maximum search distance |

Returns: { success, found, point: { x, y, z }, distance }

Set area traversal cost.

| Parameter | Type | Required | Default | Description |

|-----------|------|----------|---------|-------------|

| areaIndex | int | Yes | - | NavMesh area index |

| cost | float | Yes | - | Traversal cost value |

Returns: { success, areaIndex, cost }

Get NavMesh build settings.

Parameters: None.

Returns: { success, agentRadius, agentHeight, agentSlope, agentClimb }


Exact Signatures

Exact names, parameters, defaults, and returns are defined by GET /skills/schema or unity_skills.get_skill_schema(), not by this file.

Other skills for the same job

different authors, same section of the catalogue
Webapp Testing
by anthropics
vendor ×12

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

6k tokens scripts
Finishing A Development Branch
by ZhanlinCui
×7

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

1k tokens
Test Driven Development
by w95
×7

Use when implementing any feature or bugfix, before writing implementation code

2k tokens
Systematic Debugging
by ratacat
×7

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

10k tokens scripts
Verification Before Completion
by ZhanlinCui
×6

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

1k tokens
Backtest Expert
by BaggaT236
×3

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

15k tokens scripts
Adaptyv
by christophacham
×3

Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.

16k tokens
Aeon
by christophacham
×3

This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.

19k tokens

How to use it

Copy the folder

Take besty0728/unity-navmesh from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.