openclaw多智能体创建向导
v0.1.0Guide beginners through OpenClaw multi-agent setup with a step-by-step wizard. Use when the user wants to create OpenClaw multi-agent setups, says things lik...
⭐ 0· 109·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description, SKILL.md, README, and included scripts all align: the skill's goal is a beginner-friendly wizard to create multi-agent OpenClaw setups and Feishu bindings. The helper scripts generate agent IDs, suggest persona kinds, write starter profile files, and render summaries — all expected for this purpose. There are no requests for unrelated credentials or external services in metadata.
Instruction Scope
Runtime instructions direct the agent to inspect the local environment (openclaw CLI, gateway, config, logs), create workspaces and starter files, and patch config minimally when needed. These actions are appropriate for setup but the wizard explicitly asks the user to paste Feishu App ID and App Secret into the conversation so the agent can configure OpenClaw — that is necessary for the task but is a sensitive operation (secrets delivered via chat). No instructions instruct the agent to send data to external endpoints beyond the local OpenClaw CLI/config or to exfiltrate secrets.
Install Mechanism
No install spec — instruction-only skill with local helper scripts. No downloads or remote installation steps are declared. Scripts are small, local Python utilities (no pip/npm installs or remote fetches). This is the lower-risk pattern for skills.
Credentials
The skill does not request environment variables, system-level config paths, or unrelated credentials in the registry metadata. It does, however, require the user to supply Feishu App ID and App Secret during the interactive flow (expected and proportionate to configuring a Feishu channel). Make sure you understand that those secrets will be placed into local OpenClaw channel config as part of the normal setup flow.
Persistence & Privilege
always:false and no special privileges are requested. The skill writes starter profile files and may patch OpenClaw config workspaces (expected behavior for a setup wizard). It does not claim to modify other skills or global agent settings beyond the local OpenClaw config. It does not try to enable permanent/force-included presence.
Assessment
This skill appears to do what it says, but a few practical checks are advised before you run it: 1) Review the included scripts (in scripts/) yourself — they only write local files and print summaries, but verify file paths they write to. 2) Be cautious when pasting secrets (Feishu App ID / App Secret) into a chat: prefer pasting them directly into your local shell/CLI or temporarily running the wizard in an isolated environment if you do not trust the source. 3) Back up your existing OpenClaw config before allowing this wizard to patch it (SKILL.md already recommends backups). 4) Ensure openclaw CLI is the version you expect and test commands manually (openclaw agents list, gateway status) if unsure. 5) If you want extra safety, run the scripts in a disposable VM/container first to observe their behavior. Overall the skill is consistent with its stated purpose and does not ask for unrelated secrets or remote installs.Like a lobster shell, security has layers — review code before you run it.
latestvk975bjygz9vpzkh6k896vkv831849a5q
License
MIT-0
Free to use, modify, and redistribute. No attribution required.