ワンクリックでManusで任意のスキルを実行

forge-engineering

Run a complete engineering project through Forge's 8-phase autonomous pipeline. Decomposes any idea into subsystems, assigns specialist agents, produces real artifacts (CAD, firmware, schematics, BOMs), and iterates until the design works.

Manusで実行

概要

インストールコマンド

npx skills add https://github.com/00000star/AGI_engineering_forge --skill forge-engineering

このコマンドをClaude Codeにコピー＆ペーストしてスキルをインストール

ソース

00000star/AGI_engineering_forge

スター0

フォーク0

更新日2026年3月26日 19:32

SKILL.md

readonly

name	forge-engineering
description	Run a complete engineering project through Forge's 8-phase autonomous pipeline. Decomposes any idea into subsystems, assigns specialist agents, produces real artifacts (CAD, firmware, schematics, BOMs), and iterates until the design works.
metadata	{"openclaw":{"emoji":"🏗️","requires":{"anyBins":["python3"]}}}

Forge Engineering Pipeline

When the user describes an engineering idea, run it through the full Forge pipeline.

Quick Run (full project)

cd /workspace && python run.py "USER'S IDEA HERE"

This launches the autonomous cognitive loop: Architect decomposes → Agents execute → Verifier checks → Architect replans on failure → Iterate until complete.

Manual Phase Execution

For step-by-step control, use the bridge to run individual tools:

# Structural analysis
python3 /workspace/bridge.py structural_analysis 'F=1000; L=2.0; E=200e9; I=moment_of_inertia_rect(0.05, 0.1); print(f"deflection={beam_deflection_simply_supported(F,L,E,I)*1000:.4f}mm")'

# Symbolic math
python3 /workspace/bridge.py sympy_math 'x=symbols("x"); print(integrate(x**2, x))'

# Circuit analysis
python3 /workspace/bridge.py circuit_analysis 'print(f"Vout={voltage_divider(12, 10e3, 20e3):.2f}V")'

# Generate CAD
python3 /workspace/bridge.py openscad 'cube([10,20,30]);'

# Run any Python computation
python3 /workspace/bridge.py python_executor 'import numpy as np; print(np.linalg.det([[1,2],[3,4]]))'

Output

All project artifacts are saved to forge/data/projects/<project_name>/:

summary.md — engineering summary
project_state.json — task graph and status
artifacts/ — code, CAD files, schematics, plots

このリポジトリの他の Skills

同じリポジトリ

cad-modeling

00000star/AGI_engineering_forge

Generate parametric 3D CAD models using OpenSCAD scripting language. Create cubes, cylinders, spheres, extrusions, boolean operations, and complex assemblies from code.

2026-03-260

circuit-design

00000star/AGI_engineering_forge

Analytical circuit design and simulation — voltage dividers, RC/RL/RLC filters, power calculations, impedance analysis, transfer functions. Uses sympy for symbolic analysis and numpy for numerical.

2026-03-260

flight-controls

00000star/AGI_engineering_forge

Design and simulate control systems — transfer functions, PID controllers, Bode plots, root locus, stability analysis, state-space modeling. Uses scipy.signal and sympy.

2026-03-260

structural-analysis

00000star/AGI_engineering_forge

Perform real structural engineering calculations — beam deflection, stress analysis, buckling, safety factors. Uses numpy and scipy with built-in helper functions.

2026-03-260

tool-fabricator

00000star/AGI_engineering_forge

When no existing engineering tool fits the problem, the fabricator creates a new one from scratch. Designs, writes, tests, and registers new computational tools at runtime. This is the AGI capability.

2026-03-260

ソース

00000star

00000star/AGI_engineering_forge

GitHub リポジトリを開く Creator のリポジトリを見る

インストールコマンド

ダウンロード

Manusで実行

役立つ用途SOC

機械エンジニア建築・工学職17-2141L4

name	forge-engineering
description	Run a complete engineering project through Forge's 8-phase autonomous pipeline. Decomposes any idea into subsystems, assigns specialist agents, produces real artifacts (CAD, firmware, schematics, BOMs), and iterates until the design works.
metadata	{"openclaw":{"emoji":"🏗️","requires":{"anyBins":["python3"]}}}

Forge Engineering Pipeline

When the user describes an engineering idea, run it through the full Forge pipeline.

Quick Run (full project)

cd /workspace && python run.py "USER'S IDEA HERE"

This launches the autonomous cognitive loop: Architect decomposes → Agents execute → Verifier checks → Architect replans on failure → Iterate until complete.

Manual Phase Execution

For step-by-step control, use the bridge to run individual tools:

# Structural analysis
python3 /workspace/bridge.py structural_analysis 'F=1000; L=2.0; E=200e9; I=moment_of_inertia_rect(0.05, 0.1); print(f"deflection={beam_deflection_simply_supported(F,L,E,I)*1000:.4f}mm")'

# Symbolic math
python3 /workspace/bridge.py sympy_math 'x=symbols("x"); print(integrate(x**2, x))'

# Circuit analysis
python3 /workspace/bridge.py circuit_analysis 'print(f"Vout={voltage_divider(12, 10e3, 20e3):.2f}V")'

# Generate CAD
python3 /workspace/bridge.py openscad 'cube([10,20,30]);'

# Run any Python computation
python3 /workspace/bridge.py python_executor 'import numpy as np; print(np.linalg.det([[1,2],[3,4]]))'

Output

All project artifacts are saved to forge/data/projects/<project_name>/:

summary.md — engineering summary
project_state.json — task graph and status
artifacts/ — code, CAD files, schematics, plots