Claude desktop manual

Skill ThanhNguyxnOrg/blendops/bundles/claude-desktop-manual

AI-native Blender workflow and skill pack for non-Blender users, built around official Blender MCP, Claude Blender Connector, and Blender CLI.

Install

npx -y skills add ThanhNguyxnOrg/blendops --skill claude-desktop-manual

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Claude Desktop-facing BlendOps router skill for planning, runtime readiness, evidence truth, and non-Blender-user outputs using bundled references.

SKILL.md

2.7 KB, as published. Nobody here has run it

BlendOps Claude Desktop Router Skill

Purpose

Provide one main Claude Desktop-facing skill entrypoint that routes to the correct BlendOps reference summary while preserving runtime/artifact truth.

How to use this router

Classify user intent (help/routing, planning, runtime readiness, evidence, handoff, communication).
Consult references/skill-map.md to choose the relevant subskill summary.
Apply law summaries from references/laws/ before final output.
Keep runtime/artifact states explicit.

Reference-first routing

Use these references as needed:

skill routing: references/skill-map.md
runtime stacks: references/runtime-stacks.md
evidence policy: references/evidence-rules.md
install/runtime boundary: references/install-boundary.md
concise subskill summaries: references/skills/*.md
concise law summaries: references/laws/*.md
pack summary: references/packs/product-hero-v0.md

Do not duplicate all subskills in this router. Route and apply the relevant reference file(s).

Runtime and artifact truth

Always state:

Runtime status: Not Run | Attempted | Produced | Verified | Failed
Artifact status: Not Produced | Produced | Verified | Failed

Do not claim preview/render/GLB artifacts without evidence.

Runtime path policy

Preserve the 2-path + CLI appendix runtime model (replaces older 3-stack and 4-route drafts that mis-described how the Anthropic Connector relates to Blender Lab MCP):

Path 1 — Official Blender Lab MCP (Lab add-on + Lab server in Blender 5.1+, hosted from either (a) Anthropic Blender Connector in Claude Desktop, or (b) any other MCP client configured manually). Anthropic Connector is not standalone — Anthropic's tutorial step 2 tells you to install the Lab add-on inside Blender. The 5.1+ floor applies regardless of host option.
Path 2 — Community ahujasid/blender-mcp (different addon.py + server via uvx blender-mcp, mature 21K+ stars third-party, Blender 3.0+).
CLI fallback (appendix) — direct blender --background --python, no MCP. Documented upstream as a first-class Blender CLI surface; no in-repo evidence file yet.

Single-bridge constraint: Blender accepts one MCP bridge session per Blender instance. Do not run Path 1 + Path 2 concurrently against the same Blender instance.

Output template

## BlendOps response

- Chosen route:
- References consulted:
- Runtime status:
- Artifact status:
- Evidence used:
- Caveats:
- Next safe action: