blender-agent-core

Solid

Core discipline for ANY Blender/bpy work — contract-first, purpose-first (render-only / print / both), knowledge routing, execute-verify-refine loop with the AGENT_OK/AGENT_FAIL sentinel contract, numeric-first verification, Form gate before delivery media, production gate before delivery. Activate for every task that touches Blender, before any domain skill.

AI & Automation 66 stars 17 forks Updated 2 days ago MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
61
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Blender Agent Core This skill is a ROUTER + procedure. The deep knowledge lives in `knowledge/` — load exactly the file you need, do not recall it from memory. The root operating rules are in `AGENTS.md` (precedence: `.project-agent.md` > `AGENTS.md` > this skill). The `.agents/skills/` copy is the source; `.claude/skills/` is a mirror that must be kept in sync. ## 0. Routing by task | Task | Also load | |---|---| | Task starts and the deliverable **purpose** is not stated | Ask once — render-only / 3D print / both, recommendation **both**; record `purpose:` in `state.md` (`AGENTS.md` loop 0b) | | Purpose `print`/`both`, phase 2 (form + interfaces) is complete | **Form gate** before any material/studio/**delivery-media** work: temporary bake → [spec from measurement](references/recipes.md#spec-from-measurement) → `production-gate.py` exit 0; **final gate** at delivery; waiver = `GATE WAIVED <time> "<owner words>"` in `state.md`. Verification imagery (ladder rungs 2–6, clay renders) is exempt | | Part will be printed/manufactured, needs exact dimensions/standards | [Production contract](references/recipes.md#production-contract) → `specs/README.md` | | Execute via MCP/headless, read errors | [Explicit execution context](references/recipes.md#explicit-execution-context) | | Reference image available | Skill `blender-image-to-3d` | | Joints, hands, manipulation, animation tasks | [Articulated task](references/recipes.md#articulated-task) | | Assembly/exploded view | [Assembl...

Details

Author
jangtrinh
Repository
jangtrinh/design-os-3d-blender
Created
5 days ago
Last Updated
2 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

agent-builder

Generate role-specific agent system prompts, tool permissions, and self-review checklists from organizational design artifacts — saved to $HOME/.ai-first-kit/ with optional framework-specific configuration for Claude Code, OpenAI Agents SDK, Anthropic Agent SDK, CrewAI, or custom frameworks. Reads the organizational genome, governance, gates, and role definitions to produce agent configurations that embody a specific role in the organization. Use when the user says 'create agent instructions', 'build an agent', 'agent system prompt', 'configure an agent', 'agent for this role', 'OpenAI agent', 'CrewAI agent', 'create agent config', 'deploy an agent', or 'what tools should this agent have'. Also use when the user has completed role-value-mapper and wants to actually deploy agents that follow the organizational genome, or when they ask 'how do I make an agent follow our rules' or 'how do I create an OpenClaw agent for our org' — even if they don't use the word 'builder'. This skill MUST be consulted because it

6 Updated today
synaptiai
AI & Automation Listed

agentloop-core

Master agentloop orchestration for coding and product tasks. Use when the user wants harness mode, full autonomy with gates, or to enter agentloop.

0 Updated 1 months ago
edenbuilds
AI & Automation Listed

agent-builder

Build, implement, review, or harden a SINGLE production-grade agent — its contract, schemas, tools and permission tiers, durable state, guardrails, traces, and evals. Use when the user wants to create one agent (not a multi-agent product), implement an agent runner, add tools/memory/evals to an existing agent, or review whether one agent is production-ready. For multi-agent products, orchestration, or framework selection, use the agentic-product-architect skill instead. The full operational standard this skill applies is AGENT_STANDARD.md (bundled with this skill); copy-paste artifacts are in templates/.

14 Updated 1 months ago
Moai-Team-LLC