← Back to Skills Marketplace
Firm Agent Orchestration Pack
by
romainsantoli-web
· GitHub ↗
· v1.0.0
359
Downloads
0
Stars
2
Active Installs
1
Versions
Install in OpenClaw
/install firm-agent-orchestration-pack
Description
Multi-agent task orchestration pack. DAG-based parallel task execution and team status monitoring. 2 orchestration tools.
README (SKILL.md)
firm-agent-orchestration-pack
⚠️ Contenu généré par IA — validation humaine requise avant utilisation.
Purpose
Orchestrates multi-agent teams via directed acyclic graph (DAG) task execution. Supports dependency resolution, parallel execution, and real-time team status monitoring.
Tools (2)
| Tool | Description |
|---|---|
openclaw_agent_team_orchestrate |
DAG-based parallel task execution |
openclaw_agent_team_status |
Team execution status and progress |
Usage
skills:
- firm-agent-orchestration-pack
# Orchestrate a multi-agent task:
openclaw_agent_team_orchestrate tasks='[{"id":"1","agent":"cto","task":"review"}]'
openclaw_agent_team_status
Requirements
mcp-openclaw-extensions >= 3.0.0
Usage Guidance
This instruction-only skill is coherent with its description and requests no credentials, which is good. However: (1) the SKILL.md is minimal and AI-generated — ask the publisher for documentation on what the two tools actually do (inputs, outputs, side effects, permissions). (2) Verify the referenced dependency (mcp-openclaw-extensions >= 3.0.0) — inspect that package's implementation and permissions before installing or enabling. (3) Because the skill can orchestrate agents, test it in a controlled environment and consider restricting autonomous invocation until you understand its behavior. (4) The registry entry has no homepage and an unknown source; prefer skills with verifiable authorship or auditability before using in production.
Capability Analysis
Type: OpenClaw Skill
Name: firm-agent-orchestration-pack
Version: 1.0.0
The provided skill bundle files (`_meta.json` and `SKILL.md`) are purely descriptive and declarative. `SKILL.md` outlines the skill's purpose, lists two tools (`openclaw_agent_team_orchestrate`, `openclaw_agent_team_status`), and provides usage examples. There is no executable code, no instructions for prompt injection against the agent, no data exfiltration attempts, and no other indicators of malicious or suspicious activity within the analyzed content. The dependency on `mcp-openclaw-extensions` is a standard requirement declaration.
Capability Assessment
Purpose & Capability
Name, description, and the two declared tools (orchestrate and status) match: this is a pack for multi-agent DAG orchestration and monitoring. The only declared dependency (mcp-openclaw-extensions >= 3.0.0) is plausibly related to OpenClaw agent functionality.
Instruction Scope
SKILL.md is very short and only exposes tool names and a minimal usage example. It does not instruct the agent to read files, environment variables, or external endpoints, which is good, but it also provides no detail about what the tools actually do, their inputs/outputs, permissions, or side effects. The file warns 'AI-generated — human validation required.'
Install Mechanism
There is no install specification and no code files (instruction-only), so nothing is downloaded or written to disk by the skill itself — this is the lowest-risk install model.
Credentials
The skill declares no required environment variables, credentials, or config paths. There are no unexpected secrets or unrelated service keys requested.
Persistence & Privilege
always is false (normal). The skill enables orchestration of other agents; because autonomous invocation remains allowed by default, this capability increases blast radius compared with a read-only skill. That is not inherently malicious, but you should confirm what the underlying orchestration implementation can do before allowing autonomous runs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install firm-agent-orchestration-pack - After installation, invoke the skill by name or use
/firm-agent-orchestration-pack - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release — 2 tools: DAG task execution, team status
Metadata
Frequently Asked Questions
What is Firm Agent Orchestration Pack?
Multi-agent task orchestration pack. DAG-based parallel task execution and team status monitoring. 2 orchestration tools. It is an AI Agent Skill for Claude Code / OpenClaw, with 359 downloads so far.
How do I install Firm Agent Orchestration Pack?
Run "/install firm-agent-orchestration-pack" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Firm Agent Orchestration Pack free?
Yes, Firm Agent Orchestration Pack is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Firm Agent Orchestration Pack support?
Firm Agent Orchestration Pack is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Firm Agent Orchestration Pack?
It is built and maintained by romainsantoli-web (@romainsantoli-web); the current version is v1.0.0.
More Skills