ClawHub

Multi Agent Roles

v1.0.0

Provides standardized, role-based AI agents for multi-agent systems with clear responsibilities across strategy, creative, technical, and management domains.

⭐ 0· 1.3k·9 current·9 all-time
by@xiulipan
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name, description, and files are all focused on role definitions, templates, and examples for multi-agent systems. There are no unexpected dependencies, credentials, or binaries required.
ℹ
Instruction Scope
SKILL.md contains only role definitions, JSON/Python examples, templates, and diagrams. It does reference example filesystem paths (e.g., /workspaces/..., /agents/...) but does not instruct reading arbitrary host files, exporting data to external endpoints, or accessing credentials. Note: some templates target sensitive domains (healthcare, finance) — the content itself is benign but using these templates with real sensitive data requires caution.
✓
Install Mechanism
No install spec and no code files to run; this is instruction-only so nothing is written to disk or downloaded at install time.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths — there is no disproportionate credential request.
✓
Persistence & Privilege
always is false and the skill is user-invocable. Autonomous invocation is allowed by default but there is no other requested persistent presence or modification of other skills/configs.
Assessment
This skill is a library of role templates and examples and doesn't request credentials or install code — technically low risk. Before using: (1) review any generated agent configurations (paths like /workspaces/... are examples) and do not point agents at real sensitive data stores unless you've audited them; (2) do not feed real patient, financial, or confidential data into agents produced from the healthcare/finance templates without appropriate governance; (3) if you plan to have agents act autonomously, enable appropriate guardrails and human review for decisions in sensitive domains.

Like a lobster shell, security has layers — review code before you run it.

latestvk97633drzrrwqnvktbsdtq467h819xb9

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments