blockbench-use
MANDATORY prerequisite — invoke BEFORE any mcp__blockbench__* tool call that creates, modifies, or exports Blockbench content. Orchestrates the other blockbench-* skills (modeling, texturing, animation, PBR, Hytale, MCP overview). Trigger on: 3D model/texture/animation creation or edits in Blockbench; calls to mcp__blockbench__* tools; phrases like 'build a Minecraft model', 'paint a texture', 'animate this rig', 'export the model'. Dispatches to the right sub-skill(s), enforces pre-flight checks (project open, format, outline), wraps risky work in checkpoints, and ensures exports close the loop.
What this skill does
# Blockbench Use
Orchestrator for Blockbench MCP work. Load this **before** touching the 3D scene so the right sub-skills load and the right pre-flight checks run.
## Rule
Any request that will call an `mcp__blockbench__*` tool to create or modify content **must** go through this skill first.
Steps, in order:
1. **Classify the request** → pick one or more sub-skills (table below).
2. **Pre-flight** → confirm a project is open and the format is correct (see "Pre-flight checks").
3. **Load the sub-skill(s)** via the Skill tool.
4. **Checkpoint before risk** → call `save_checkpoint` for multi-step edits that might need rollback.
5. **Execute** the sub-skill's workflow.
6. **Close the loop** → screenshot, validate (Hytale), or export if the user asked for a deliverable.
## Skill routing table
Pick by primary intent. When the task spans domains, load **all** relevant skills before starting.
| User intent | Primary skill | Also load when… |
|---|---|---|
| Build cubes, meshes, groups, hierarchy | `blockbench-modeling` | needs texture → `blockbench-texturing` |
| Paint, fill, draw, brush, layers, UV | `blockbench-texturing` | channel-aware (normal/MER) → `blockbench-pbr-materials` |
| Keyframes, bone rigs, walk/idle/attack | `blockbench-animation` | bones need geometry first → `blockbench-modeling` |
| `.texture_set.json`, normal/height/MER | `blockbench-pbr-materials` | textures not yet drawn → `blockbench-texturing` |
| `.blockymodel`, `.blockyanim`, attachments, quads, stretch, shading modes | `blockbench-hytale` | modeling/animation parts → those skills |
| "What tools are available?" / unclear scope | `blockbench-mcp-overview` | — |
| Write a Blockbench JS plugin (not use MCP) | `blockbench-plugins` (from `blockbench-development/`) | — |
**Skip this skill** for pure research questions (API docs, "how does Blockbench work?"). Go straight to `blockbench-mcp-overview`.
## Pre-flight checks
Run before any mutation. One round of `list_outline` + `list_textures` is usually enough.
1. **Is a project open?** If no project, call `create_project` first (format from the routing table below).
2. **Is the format correct for the task?**
- Cube modeling (Minecraft) → `bedrock_block`, `java_block`, `bedrock`
- Mesh/freeform → `free`, `modded_entity`, `optifine_entity`
- Hytale character → `hytale_character` (64px)
- Hytale prop → `hytale_prop` (32px)
- Generic → `generic` or `free`
3. **What's already there?** Use `list_outline` (structure) + `list_textures` (materials). Prefer `find_elements_by_criteria` / `filter_by_material` over dumping the whole outline for large projects.
4. **Hytale project?** Run `hytale_validate_model` at the end; never silently exceed 255 nodes.
## Multi-skill workflow compositions
### "Create a Minecraft character with a walk cycle"
```
blockbench-modeling → bones + cubes
blockbench-texturing → skin texture
blockbench-animation → walk cycle keyframes
# finally:
capture_screenshot → preview
export_model: codec_id="project" → save .bbmodel
```
### "Make a Bedrock RTX block"
```
blockbench-modeling → single cube
blockbench-texturing → color map
blockbench-pbr-materials → normal + MER + texture_set.json
# finally:
hytale_validate_model → (skip — not Hytale)
capture_screenshot
```
### "Build a Hytale character with attachments"
```
blockbench-hytale → read first: format, node limits, pieces
blockbench-modeling → geometry in character format
blockbench-animation → optional keyframes (60 FPS)
# separately per attachment collection:
blockbench-hytale → hytale_set_attachment_piece on bones
# finally:
hytale_validate_model → node count, stretch, shading
export_model: codec_id="blockymodel"
```
### "Retexture an existing model"
```
# Pre-flight: find everything that uses the old texture
filter_by_material: texture="old_skin"
# Load:
blockbench-texturing → paint/create replacement
# Swap references:
apply_texture per match (from filter_by_material results)
```
## Safety & efficiency rules (apply in every session)
1. **Checkpoint before risk.** For any workflow of 3+ mutations, call `save_checkpoint: name="<descriptive>"` first. If the result is wrong, `undo: steps=N` back.
2. **Filter, don't dump.** Prefer `find_elements_by_criteria`, `filter_by_material`, or `select_all_of_type` over `list_outline` when you know the shape of what you want. Large outlines blow context.
3. **Respect the format.** Don't call Hytale tools on a non-Hytale project — they will error. Check `Format.id` via `risky_eval` or `hytale_get_format_info` if unsure.
4. **Screenshot after meaningful changes.** `capture_screenshot` confirms the model looks right. Do it at milestones, not every edit.
5. **Export only when the user asks for a deliverable.** Use `list_export_formats` first to pick the right codec, then `export_model` with a `path` (or content-only if the user just wants to see it).
6. **Never call `trigger_action: action="undo"` or `"redo"`.** Use the dedicated `undo` / `redo` tools — they return which actions were traversed.
7. **Name everything.** Descriptive names make `find_elements_by_criteria` and filtering work later.
## When to load `blockbench-mcp-overview`
Load it instead of a specialized skill when:
- The user's intent is ambiguous ("help me with this model")
- The tool call count will be small (<5) and spans multiple domains
- The user is asking about capabilities, not executing
Otherwise prefer the specialized skills — they have concrete examples and return shapes.
## What this skill does NOT cover
- **Blockbench plugin development** (writing `.js` plugins) → `blockbench-plugins`
- **MCP server development** (adding tools to this repo) → not in this skill set
- **General 3D theory / THREE.js / rendering internals** → out of scope
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.