Skip to content
Back to skills

Tooling And Forge

ASecurity

"Use BaseTool, BaseResource, BasePrompt, Atomic Forge tool

  • 247 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 8, 2026
toolsapi

Works with

  • cli
  • api
  • mcp

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned September 8, 2026

npx -y skills add VectorSpaceLab/AREX-Skill --skill tooling-and-forge --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Tooling And Forge?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Tooling And Forge
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-tooling-and-forge/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-tooling-and-forge)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: tooling-and-forge
description: "Use BaseTool, BaseResource, BasePrompt, Atomic Forge tool
  packages, the atomic CLI, and tool-selection patterns safely."
disable-model-invocation: true
metadata:
  disco-role: operating
license: MIT
---

# Tooling and Forge

Use this subskill when a task is about Atomic Agents tool abstractions, Atomic Forge downloadable tools, the `atomic` CLI/TUI, or choosing between direct tool calls and LLM-selected tool routing.

## Read first

- `references/api-reference.md` for `BaseTool`, `BaseResource`, `BasePrompt`, and tool composition patterns.
- `references/cli-reference.md` for the `atomic` command and Atomic Assembler behavior.
- `references/forge-catalog.md` for the downloadable tool families and their dependency / credential notes.
- `references/troubleshooting.md` for CLI, download, dependency, and selection failures.
- `../../scripts/check_atomic_agents_env.py` from the root skill for a safe CLI/import smoke check.

## Owns

- `BaseTool`, `BaseToolConfig`, `BaseResource`, `BaseResourceConfig`, `BasePrompt`, and `BasePromptConfig`.
- Direct tool calls versus choice-agent orchestration patterns.
- Atomic Forge tool selection, download expectations, and dependency/credential caveats.
- Atomic Assembler / `atomic` CLI usage and common local setup mistakes.
- Tool authoring guidance when a task is about packaging a reusable tool.

## Does not own

- Core agent construction, history, prompts, hooks, or token counting; use `../agent-core/SKILL.md`.
- MCP transport and dynamic tool discovery; use `../mcp-integrations/SKILL.md`.
- Example project adaptation; use `../example-workflows/SKILL.md`.
- Repo editing / docs / release / CI; use `../repo-development/SKILL.md`.

## Common triggers

- "How do I create a tool?"
- "How do I use Atomic Forge tools?"
- "What does the `atomic` CLI download?"
- "How should I choose between a direct tool call and an LLM-selected tool?"
- "What dependencies or API keys does this tool family need?"

Files in this skill

  • SKILL.md2 KB
  • references/api-reference.md2.5 KB
  • references/cli-reference.md1.3 KB
  • references/forge-catalog.md2.2 KB
  • references/troubleshooting.md1.7 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.