blender-mcp

Drive Blender via the catalog blender MCP, with bpy recipes.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/creative/blender-mcp/SKILL.md

Quality

Content

92%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.

The content is a well-structured, executable skill body: tight code, clear sequenced workflow with verification, and clean one-level-deep references. Only minor conciseness trim is possible.

Dimension	Reasoning	Score
Conciseness	The body is lean, defers detail to references, and assumes Blender/bpy competence; minor padding (the restated intro and the inline Pitfalls duplicating references/pitfalls.md) keeps it just below anchor 5.	4 / 5
Actionability	It provides copy-paste-ready bpy snippets (clear scene, add mesh, material, keyframe, render), exact CLI commands, and a concrete tool table covering the common cases, matching anchor 5.	5 / 5
Workflow Clarity	The numbered Procedure has explicit validation checkpoints (get_scene_info first, screenshot between steps, render to absolute path and report) plus error-recovery guidance and a dedicated Verification section, matching anchor 5.	5 / 5
Progressive Disclosure	The body is a clear overview with a well-signaled one-level-deep reference table (bpy-api.md, recipes.md, pitfalls.md, all verified present), organized by topic for easy navigation, matching anchor 5.	5 / 5
	Total	19 / 20 Passed

Description

56%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.

The description is distinctive and correctly names its domain, but it is thin on concrete actions and lacks any "Use when" trigger guidance, which caps completeness and trigger coverage.

Suggestions

Add a "Use when..." clause naming natural triggers (e.g., "Use when the user wants to create or modify meshes, materials, lighting, animation, or renders in a running Blender instance").

Replace the generic "Drive Blender" with 2-3 concrete actions (e.g., "Create and modify meshes, materials, and animations in a live Blender session via the blender MCP").

Include common synonyms/extensions users say (3D, rendering, modeling, animation) so the description matches natural phrasing.

Dimension	Reasoning	Score
Specificity	It names the domain (Blender, MCP, bpy) but offers only one generic action verb ("Drive"); "recipes" is a noun, not a concrete action, so it lands at anchor 2 rather than the 1-2-action anchor 3.	2 / 5
Completeness	It gives a clear "what" (drive Blender via MCP with bpy recipes) but no "Use when"/trigger clause, so per the missing-trigger cap it stays at anchor 3 rather than 4.	3 / 5
Trigger Term Quality	"Blender", "bpy", and "MCP" are terms a Blender user would say, but it omits common natural variations (3D, modeling, animation, rendering) that the skill actually covers, fitting anchor 3 over 4.	3 / 5
Distinctiveness Conflict Risk	The narrow phrasing "Blender via the catalog blender MCP, with bpy recipes" carves a distinct niche with minimal overlap risk against any other skill, matching anchor 5.	5 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/creative/blender-mcp/SKILL.md
Commit: b9aa928

Reviewed: 10 days 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.