ClawHub

CrazeeOpenclawSkill

v1.0.1

OpenClaw任务分工协调skill，用于明确团队角色和CLI工具分工。当OpenClaw下发任务、分配工作、创建子任务、协调多Agent协作、或需要明确前后端分工和QA验收流程时使用此skill。

⭐ 0· 133·0 current·0 all-time
by@chenzhouming
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 describe coordinating OpenClaw, Claude, Gemini CLI and Codex CLI; SKILL.md contains routing rules, role definitions, and QA criteria. The declared requirements (none) are proportional to an instruction-only coordination skill.
ℹ
Instruction Scope
The instructions are limited to task analysis, routing to the appropriate CLI agent, progress monitoring, and Claude-led QA. They do not reference files, secrets, or unrelated system paths. However, the runtime steps are high-level and vague (e.g., '调用对应CLI Agent', '监控执行进度') with no concrete invocation details, so actual implementation may need additional integration configuration.
✓
Install Mechanism
No install spec and no code files — nothing will be written to disk by the skill itself. This is the lowest-risk install posture.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. There are no apparent requests for unrelated secrets or permissions.
✓
Persistence & Privilege
always is false and model invocation is allowed (the normal default). The skill does not request permanent presence or claim to modify other skills or system-wide settings.
Assessment
This skill is a lightweight, instruction-only coordinator and appears internally consistent. Before installing or using it, confirm how your agent will 'call' the Gemini/Codex/Claude CLIs in practice — the skill does not provide implementation details. Ensure those CLI tools (and any credentials they require) are from trusted sources and you control which agent can invoke them. If you plan to allow autonomous agent actions, restrict which system commands and external services the agent may use to avoid unintended access.

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

latestvk9726f1gscv3xxqtxg3qezvnxd83cxby

License

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

Comments