Agent Skills

blockbench-hytale

Create Hytale models and animations using Blockbench MCP tools. Use when working with Hytale character/prop formats, creating attachments, setting shading modes, using quads, or animating with visibility keyframes. Requires the Hytale Blockbench plugin to be installed.

Install

npx skills add https://github.com/jasonjgardner/blockbench-mcp-project --skill blockbench-hytale
SKILL.md

Blockbench Hytale

Create models for Hytale using Blockbench with the Hytale plugin.

Prerequisite: Hytale plugin must be installed in Blockbench.

Available Tools

Format & Validation

Tool Purpose
hytale_get_format_info Get format type, block size, node count
hytale_validate_model Check against Hytale constraints

Cube Properties

Tool Purpose
hytale_set_cube_properties Set shading_mode, double_sided
hytale_get_cube_properties Get Hytale cube properties
hytale_set_cube_stretch Set stretch values [x, y, z]
hytale_get_cube_stretch Get stretch values
hytale_create_quad Create 2D plane with normal

Attachments

Tool Purpose
hytale_list_attachments List attachment collections
hytale_set_attachment_piece Mark group as attachment piece
hytale_list_attachment_pieces List all piece groups

Animation

Tool Purpose
hytale_create_visibility_keyframe Toggle bone visibility in animation
hytale_set_animation_loop Set loop mode (loop/hold/once)

Resources

Resource URI Purpose
hytale-format hytale://format Format info
hytale-attachments hytale://attachments/{id} Attachment collections
hytale-pieces hytale://pieces/{id} Attachment pieces
hytale-cubes hytale://cubes/{id} Cubes with Hytale properties

Prompts

Prompt Arguments Purpose
hytale_model_creation format_type Character/prop modeling guide
hytale_animation_workflow animation_type Animation creation guide
hytale_attachments - Attachments system guide

Hytale Formats

Format Block Size Use Case
hytale_character 64px Humanoids, creatures
hytale_prop 32px Items, weapons, decorations

Constraints

  • Max nodes: 255 (groups + extra cubes)
  • Animation FPS: 60
  • UV size: Must match texture resolution

Shading Modes

Mode Effect
standard Normal lighting (default)
flat No lighting/shadows
fullbright Always fully lit (emissive)
reflective Reflective material

Quick Start

Check Format

hytale_get_format_info
# Returns: formatType, blockSize, nodeCount, features

Validate Model

hytale_validate_model
# Returns: valid, nodeCount, issues

Cube Properties

Set Shading Mode

hytale_set_cube_properties: cube_id="crystal", shading_mode="fullbright"

Enable Double-Sided

hytale_set_cube_properties: cube_id="cloth", double_sided=true

Set Stretch

hytale_set_cube_stretch: cube_id="arm", stretch=[1.2, 1.0, 1.0]

Quads (2D Planes)

Create single-face planes:

hytale_create_quad: name="leaf",
  position=[0, 16, 0],
  normal="+Y",  # +X, -X, +Y, -Y, +Z, -Z
  size=[8, 8],
  double_sided=true

Attachments

List Attachments

hytale_list_attachments

Mark as Attachment Piece

hytale_set_attachment_piece: group_name="hand_right", is_piece=true

This bone will attach to hand_right on the base model.

List Attachment Pieces

hytale_list_attachment_pieces

Animation

Visibility Keyframe

Toggle bone visibility during animation:

hytale_create_visibility_keyframe:
  bone_name="weapon_sheathed",
  time=0.5,
  visible=false

hytale_create_visibility_keyframe:
  bone_name="weapon_drawn",
  time=0.5,
  visible=true

Set Loop Mode

hytale_set_animation_loop: animation_id="walk", loop_mode="loop"
hytale_set_animation_loop: animation_id="attack", loop_mode="once"
hytale_set_animation_loop: animation_id="death", loop_mode="hold"

Common Workflows

Create Character Model

# 1. Create project (use bedrock format, Hytale format activates automatically)
create_project: name="goblin", format="bedrock"

# 2. Build bone hierarchy
add_group: name="root", origin=[0, 0, 0]
add_group: name="body", parent="root", origin=[0, 12, 0]
add_group: name="head", parent="body", origin=[0, 24, 0]
add_group: name="arm_left", parent="body", origin=[6, 22, 0]
add_group: name="arm_right", parent="body", origin=[-6, 22, 0]
add_group: name="hand_right", parent="arm_right", origin=[-8, 16, 0]

# 3. Add geometry
place_cube: elements=[{name: "torso", from: [-4, 12, -2], to: [4, 24, 2]}], group="body"

# 4. Set Hytale properties
hytale_set_cube_properties: cube_id="eyes", shading_mode="fullbright"

# 5. Validate
hytale_validate_model

Create Weapon Attachment

# 1. Create attachment structure
add_group: name="hand_right", origin=[0, 0, 0]

# 2. Add weapon geometry
place_cube: elements=[{name: "blade", from: [-0.5, 0, -0.5], to: [0.5, 24, 0.5]}], group="hand_right"

# 3. Mark as attachment piece
hytale_set_attachment_piece: group_name="hand_right", is_piece=true

# 4. Add glowing effect
hytale_set_cube_properties: cube_id="rune", shading_mode="fullbright"

Animate Weapon Draw

# Start with sheathed weapon visible
hytale_create_visibility_keyframe: bone_name="sword_sheathed", time=0, visible=true
hytale_create_visibility_keyframe: bone_name="sword_drawn", time=0, visible=false

# At draw point, swap
hytale_create_visibility_keyframe: bone_name="sword_sheathed", time=0.3, visible=false
hytale_create_visibility_keyframe: bone_name="sword_drawn", time=0.3, visible=true

Tips

  • Always run hytale_validate_model before export
  • Keep node count under 255
  • Use stretch instead of fractional cube sizes
  • Set group origins at joint/pivot points
  • Use fullbright shading for glowing elements
  • Mark equipment bones as is_piece=true for attachments
  • Use visibility keyframes for state changes (weapons, damage)
  • Animation runs at 60 FPS (time 1.0 = 60 frames)

Related skills

ai-image-generationgenmedia-labs713KGenerate and edit images on RunComfy via the `runcomfy` CLI — a smart router across the full image-model catalog: FLUX 2 (Klein 9B/4B, Pro, Dev, Flash, Turbo, Max), Google Nano Banana 2 / Pro, OpenAI GPT Image 2, ByteDance Seedream 5 / 4-5 / 4-0 and Dreamina 4-0, Alibaba Qwen Image and Z-Image Turbo, Wan 2-7. Covers both text-to-image (t2i) and image-to-image / edit (i2i) endpoints — the skill picks the right model for the user's actual intent (typography precision, photoreal portraits, sub-secoai-image-generation101-skills547KGenerate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stnano-banana-2prime-skills424KGenerate images with Google Nano Banana 2 (Gemini-family flash-tier text-to-image) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Nano Banana 2's strengths (rapid iteration, in-image typography rendering, predictable framing, optional web-grounded context), the resolution-tier pricing, the safety-tolerance dial, and when to route to Nano Banana Pro / GPT Image 2 / Flux 2 / Seedream insteimage-editprime-skills424KEdit images on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Nano Banana Edit (batch up to 20, identity-preserving default), OpenAI GPT Image 2 Edit (multilingual in-image text rewrite, multi-ref composition, layout precision), Flux Kontext Pro (single-ref high-fidelity local edit), or Z-Image Turbo Inpaint (mask-driven precise region edit). Bundles each model's documented prompting patterns so the skill gets sharper

Search skills and MCP servers

Fuzzy search across 23,137 skills and servers