aminet-browser
Aminet search and browse: full-text search, category tree navigation, architecture filtering, package detail, and curated…
Generates Blender Python scripts for infrastructure visualization and ffmpeg commands for video production and social media export.
Claude Code
$ npx -y skills add Tibsfox/gsd-skill-creator --skill creative-pipeline --agent claude-code
Codex
$ npx skills add Tibsfox/gsd-skill-creator --skill creative-pipeline -a codex -y
Cursor
$ npx skills add Tibsfox/gsd-skill-creator --skill creative-pipeline -a cursor -y
Gemini CLI
$ npx skills add Tibsfox/gsd-skill-creator --skill creative-pipeline -a gemini-cli -y
GitHub Copilot
$ npx skills add Tibsfox/gsd-skill-creator --skill creative-pipeline -a github-copilot -y
OpenCode
$ npx skills add Tibsfox/gsd-skill-creator --skill creative-pipeline -a opencode -y
Windsurf
$ npx skills add Tibsfox/gsd-skill-creator --skill creative-pipeline -a windsurf -y
name: creative-pipeline
version: 1.0.0
description: "Generates Blender Python scripts for infrastructure visualization and ffmpeg commands for video production and social media export."
user-invocable: true
allowed-tools: Read Grep Glob Bash
metadata:
extensions:
gsd-skill-creator:
version: 1
createdAt: "2026-02-27"
triggers:
intents:
- "Blender"
- "3D visualization"
- "infrastructure render"
- "bpy script"
- "pipe model"
- "equipment visualization"
- "camera path"
- "ffmpeg"
- "video export"
- "social media"
- "walkthrough"
- "animation"
- "coolant flow"
- "thermal visualization"
contexts:
- "infrastructure visualization"
- "data center rendering"
- "engineering animation"
- "stakeholder presentation"
domain: physical-infrastructure
tier: output
depends_on:
- blueprint-engine
safety: no-engineering-decisions
applies_to:
- skills/physical-infrastructure/**
- "*.blend"
- "*.py"Generate Blender Python (bpy) scripts for 3D infrastructure visualization and ffmpeg command sequences for video production and social media export — turning technical engineering designs into communication-ready visual deliverables.
**Activation:** After engineering design is verified and documented. InfrastructureRequest with outputFormat including 'render'. Stakeholder presentations, client deliverables, social media content creation.
**Output types:**
1. **Blender bpy scripts:** Python scripts that run in Blender's Scripting workspace to create pipe geometry, equipment meshes, materials, lighting, camera paths, and animations. 2. **ffmpeg commands:** Shell commands that assemble rendered frames into video and export to social media formats (YouTube, Instagram Reel, Twitter/X, thumbnail).
**Prerequisites:**
**Quick-start — Blender script generation:**
import bpy # Clear scene, set units to metric, configure Cycles renderer bpy.ops.object.select_all(action='SELECT') bpy.ops.object.delete() bpy.context.scene.unit_settings.system = 'METRIC' bpy.context.scene.render.engine = 'CYCLES'
**Quick-start — ffmpeg social media export:**
# Assemble rendered frames into video ffmpeg -framerate 30 -i render_%04d.png -c:v libx264 -pix_fmt yuv420p walkthrough.mp4 # Export for YouTube (1920x1080, 8 Mbps) ffmpeg -i walkthrough.mp4 -vf "scale=1920:1080" -b:v 8M youtube.mp4
**Quick routing:**
---
Every infrastructure visualization script begins with scene initialization:
import bpy import math # ── Clear default scene ────────────────────────────────────── bpy.ops.object.select_all(action='SELECT') bpy.ops.object.delete() # ── Set units to metric (millimeters for infrastructure) ───── bpy.context.scene.unit_settings.system = 'METRIC' bpy.context.scene.unit_settings.length_unit = 'MILLIMETERS' # ── Set render engine ──────────────────────────────────────── # EEVEE for fast preview, Cycles for photorealistic final render bpy.context.scene.render.engine = 'CYCLES' bpy.context.scene.cycles.samples = 128 # Preview: 128, Final: 256-512 # ── Set render resolution ──────────────────────────────────── bpy.context.scene.render.resolution_x = 1920 bpy.context.scene.render.resolution_y = 1080 bpy.context.scene.render.resolution_percentage = 100 # ── Set output format ──────────────────────────────────────── bpy.context.scene.render.image_settings.file_format = 'PNG' bpy.context.scene.render.filepath = '//renders/' # Relative to .blend file
Three standard lighting configurations for infrastructure visualization:
**Studio lighting (3-point):**
# Key light — main illumination at 45 degrees bpy.ops.object.light_add(type='AREA', location=(5, -5, 8)) key_light = bpy.context.active_object key_light.name = "Key_Light" key_light.data.energy = 1000 # Watts key_light.data.size = 3.0 # Soft shadow (larger = softer) # Fill light — reduce shadow harshness, opposite side at lower intensity bpy.ops.object.light_add(type='AREA', location=(-4, -3, 5)) fill_light = bpy.context.active_object fill_light.name = "Fill_Light" fill_light.data.energy = 400 # 40% of key light # Rim light — edge definition from behind bpy.ops.object.light_add(type='AREA', location=(0, 6, 6)) rim_light = bpy.context.active_object rim_light.name = "Rim_Light" rim_light.data.energy = 600
**HDRI environment (realistic ambient):**
# Load HDRI for realistic outdoor/sky lighting
world = bpy.context.scene.world
world.use_nodes = True
nodes = world.node_tree.nodes
links = world.node_tree.links
nodes.clear()
bg_node = nodes.new(type='ShaderNodeBackground')
env_node = nodes.new(type='ShaderNodeTexEnvironment')
output_node = nodes.new(type='ShaderNodeOutputWorld')
# Load HDRI file (download from polyhaven.com — free CC0)
env_node.image = bpy.data.images.load('//hdri/industrial_hall.hdr')
bg_node.inputs['Strength'].default_value = 1.0
links.new(env_node.outputs['Color'], bg_node.inputs['Color'])
links.new(bg_node.ouAn adaptive learning and coprocessor architecture for Claude Code, built as an extension to GSD (open-gsd)
Aminet search and browse: full-text search, category tree navigation, architecture filtering, package detail, and curated…
FS-UAE emulator configuration and launch: hardware profiles, ROM management, WHDLoad integration, config generation, and state…
Manages Aminet INDEX infrastructure: fetch, parse, cache, and incremental update of ~84,000-entry package database. Use when…
Aminet package installation: LhA/LZX extraction, Amiga filesystem mapping, dependency detection, install tracking, and scan gate…
Selective Aminet package mirroring: single-package fetch, integrity verification, mirror state tracking, bulk download, and sync…
Multi-layer virus scanning for Aminet packages. Signature-based detection, heuristic hunk analysis, boot block scanning,…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.