ClawHub

clawteam-skill

v1.1.2

Multi-agent swarm coordination via the ClawTeam CLI. Use when the user wants to create agent teams, spawn multiple agents to work in parallel, coordinate tas...

⭐ 0· 340·0 current·0 all-time
by@xybio
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 require the 'clawteam' CLI and the SKILL.md exclusively documents using that binary and its commands. There are no unrelated env vars, installs, or opaque requirements.
ℹ
Instruction Scope
Instructions stay within the domain of running the clawteam CLI (team/task/spawn/board). The doc explicitly references filesystem repos (--repo /path/to/repo), tmux, git worktrees, and a 'spawn subprocess' backend that can execute arbitrary code — this is a legitimate capability of such an orchestration tool but is a high-impact action that requires user caution. The skill does not itself instruct reading unrelated system files or exfiltrating data.
✓
Install Mechanism
Instruction-only skill: no install spec and no downloads. User is asked to install/verify the clawteam binary externally, which is lower risk than bundling or auto-installing arbitrary code.
✓
Credentials
The skill declares no required secrets or env vars. It documents environment variables that clawteam injects for spawned agents (CLAWTEAM_AGENT_NAME, etc.), which is expected and proportional to its functionality.
✓
Persistence & Privilege
always is false and the skill is user-invocable. It does not request persistent system-wide privileges or modify other skills' configs. Autonomous model invocation remains permitted by platform defaults but is not granted any extra privilege by this skill.
Assessment
This skill is coherent but exercises a powerful orchestration tool: only install the clawteam CLI from a trusted, pinned release and verify its checksum/tag. Avoid using 'spawn subprocess' or pointing --repo at untrusted repositories (those modes can execute arbitrary code). Run initial tests in disposable repos/worktrees, and be cautious exposing 'board serve' (web dashboards) on public ports. If you need to allow this skill to run autonomously, restrict the environment it runs in and ensure the underlying clawteam binary is audited and up-to-date.

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

latestvk9790jb43ax4j8wa58trm4076h83fag4

License

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

Runtime requirements

Binsclawteam

Comments