forge-engineering
- Repo stars 0
- Author updated Live
- Author repo AGI_engineering_forge
- Domain
- Design
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @00000star · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- Python
- Permissions
-
- Read-only
- Write / modify
- Shell exec
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: forge-engineering
description: Run a complete engineering project through Forge's 8-phase autonomous pipeline. Decomposes any i…
category: design
runtime: Python
---
# forge-engineering output preview
## PART A: Task fit
- Use case: 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..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Quick Run (full project) / Manual Phase Execution / Output” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “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.”.
- **02** When the source has headings, the agent prioritizes “Quick Run (full project) / Manual Phase Execution / Output” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source mentions slash commands such as `/workspace`; use them first when your agent supports command triggers.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files, run shell commands.
Start with a small task and check whether the result follows “Quick Run (full project) / Manual Phase Execution / Output”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: forge-engineering
description: Run a complete engineering project through Forge's 8-phase autonomous pipeline. Decomposes any i…
category: design
source: 00000star/AGI_engineering_forge
---
# forge-engineering
## When to use
- Run a complete engineering project through Forge's 8-phase autonomous pipeline. Decomposes any idea into subsystems, a…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Quick Run (full project) / Manual Phase Execution / Output” and keep inference separate from source facts.
- read files, write/modify files, run shell commands; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "forge-engineering" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Quick Run (full project) / Manual Phase Execution / Output
rules -> SKILL.md triggers / order / output contract
runtime -> Python | read files, write/modify files, run shell commands | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}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 summaryproject_state.json— task graph and statusartifacts/— code, CAD files, schematics, plots
Decide Fit First
Design Intent
How To Use It
Boundaries And Review