tool-fabricator
- 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
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- Python
- Permissions
-
- Read-only
- Write / modify
- 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: tool-fabricator
description: When no existing engineering tool fits the problem, the fabricator creates a new one from scratc…
category: design
runtime: Python
---
# tool-fabricator output preview
## PART A: Task fit
- Use case: 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..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Usage / What It Does / Examples of Tools It Can Create” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “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.”.
- **02** When the source has headings, the agent prioritizes “Usage / What It Does / Examples of Tools It Can Create” 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; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; 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. Choose the trigger
The source mentions slash commands such as `/workspace`; use them first when your agent supports command triggers.
Provide inputs and boundaries
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.
Validate with a small run
Start with a small task and check whether the result follows “Usage / What It Does / Examples of Tools It Can Create”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: tool-fabricator
description: When no existing engineering tool fits the problem, the fabricator creates a new one from scratc…
category: design
source: 00000star/AGI_engineering_forge
---
# tool-fabricator
## When to use
- When no existing engineering tool fits the problem, the fabricator creates a new one from scratch. Designs, writes, te…
- 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 “Usage / What It Does / Examples of Tools It Can Create” and keep inference separate from source facts.
- read files, write/modify files; 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. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "tool-fabricator" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Usage / What It Does / Examples of Tools It Can Create
rules -> SKILL.md triggers / order / output contract
runtime -> Python | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Tool Fabricator — The AGI Capability
When you need an engineering computation that no existing tool handles, the fabricator builds a new tool from first principles.
Usage
python3 /workspace/bridge.py fabricate 'DESCRIPTION OF WHAT THE TOOL NEEDS TO DO'What It Does
- Understands the engineering requirement
- Designs the computation from first principles
- Writes a working Python function
- Tests it
- Registers it in the tool registry for future use
Examples of Tools It Can Create
- Thermal simulation for specific geometries
- Fluid dynamics calculations for pipe networks
- Gear ratio optimization for drivetrain design
- Battery discharge curve modeling
- Antenna radiation pattern computation
- Any engineering computation that can be expressed as Python + numpy/scipy/sympy
When to Use
Use this when:
- No existing tool handles your specific calculation
- You need a specialized simulation that doesn't exist
- The problem requires a custom numerical method
- Standard tools don't have the right domain-specific formulas
Decide Fit First
Design Intent
How To Use It
Boundaries And Review