Skip to content
Back to skills

Swarms

ASecurity

"Route Swarms users to the right single-agent, CLI, workflow, or

  • 247 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added September 9, 2026
ai-agentspythonrustgobashdockerdebuggingapibackend

Works with

  • cli
  • api
  • mcp

Security analysis

A96/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 20 files and shows the line behind each finding

Scanned September 9, 2026

npx -y skills add VectorSpaceLab/AREX-Skill --skill swarms --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Swarms?

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

Security grade badge for Swarms
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/vectorspacelab-swarms/badge)](https://www.skillsdirectory.com/skills/vectorspacelab-swarms)

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: swarms
description: "Route Swarms users to the right single-agent, CLI, workflow, or
  tool/MCP guidance."
metadata:
  disco-role: operating
disable-model-invocation: true
license: Apache 2.0
---

# Swarms

Use this repo skill for the `swarms` Python package when the task is about building,
routing, loading, or debugging Swarms agents and orchestrations.

## Start here

- If the user is creating or tuning one `Agent`, go to `sub-skills/single-agent/`.
- If the user is using the `swarms` CLI, YAML, or markdown loaders, go to `sub-skills/cli-loaders/`.
- If the user is combining many agents with a swarm, router, graph, debate, vote, or chat pattern, go to `sub-skills/multi-agent-workflows/`.
- If the user is converting callables to tools or connecting MCP servers, go to `sub-skills/tools-mcp/`.

## What this skill covers

- Single-agent construction, memory, skills, marketplace prompts, prompt caching,
  fallback models, and artifact handling.
- CLI commands and file-driven agent creation.
- Multi-agent orchestration patterns, routing, consensus, and collaboration.
- Tool schema conversion, BaseTool helpers, and MCP client/server workflows.

## What this skill does not cover

- Release automation, Docker packaging, or repo-maintenance scripts.
- Benchmark harnesses and expensive evaluation loops.
- Voice-agent demos and AOP demo trees.
- Private repo checkout paths or workflow instructions that depend on the original source tree.

## Quick install and smoke check

```bash
pip install swarms
swarms --help
python -c "from swarms import Agent; print(Agent.__name__)"
```

## Optional runtime signals

- `WORKSPACE_DIR` controls where agent memory and workspace files are stored.
- `SWARMS_API_KEY` is required for marketplace fetch/publish workflows.
- `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GROQ_API_KEY`, and similar provider keys are required only for live model-backed runs.
- `graphviz` and `rustworkx` are optional for graph-workflow variety.

## Read these next

- `references/overview.md` for the package map and route selection notes.
- `references/troubleshooting.md` for cross-cutting install, import, key, and backend issues.
- `scripts/smoke.sh` for a quick offline import and CLI check.

## Routing rule of thumb

Choose the narrowest sub-skill that owns the user-facing workflow. Use the root only when the request spans multiple families or is about the package as a whole.

- `single-agent` owns one-agent configuration and its direct support objects.
- `cli-loaders` owns command-line entry points and config/file loading.
- `multi-agent-workflows` owns swarm orchestration and routing patterns.
- `tools-mcp` owns tool schema helpers and MCP transport/auth workflows.

Files in this skill

  • SKILL.md2.7 KB
  • references/overview.md1.8 KB
  • references/repo-provenance.md754 B
  • references/repo-routing-metadata.json399 B
  • references/troubleshooting.md2.4 KB
  • scripts/smoke.sh405 B
  • sub-skills/cli-loaders/SKILL.md2.8 KB
  • sub-skills/cli-loaders/references/cli-reference.md2.9 KB
  • sub-skills/cli-loaders/references/troubleshooting.md1.3 KB
  • sub-skills/cli-loaders/references/workflows.md2 KB
  • sub-skills/cli-loaders/scripts/cli_smoke.sh1.2 KB
  • sub-skills/multi-agent-workflows/SKILL.md3.2 KB
  • sub-skills/multi-agent-workflows/references/api-reference.md3.7 KB
  • sub-skills/multi-agent-workflows/references/troubleshooting.md1.7 KB
  • sub-skills/multi-agent-workflows/references/workflows.md2.7 KB
  • sub-skills/multi-agent-workflows/scripts/workflow_smoke.py1.4 KB
  • sub-skills/single-agent/SKILL.md3.6 KB
  • sub-skills/single-agent/references/api-reference.md4.2 KB
  • sub-skills/single-agent/references/troubleshooting.md1.6 KB
  • sub-skills/single-agent/references/workflows.md2.7 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.