ClawHub

create-agents-wizard

v1.0.1

Guided creation of multiple OpenClaw agents and their workspace templates. Use when users ask to create agents in batch, configure new agents, or customize A...

⭐ 0· 248·0 current·0 all-time
by@zcxggmu
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 match the actual behavior: collecting agent metadata, drafting six workspace files (or two in fast mode), and optionally running the OpenClaw CLI. No unrelated credentials, binaries, or config paths are requested.
✓
Instruction Scope
SKILL.md confines actions to asking questions, drafting files, writing to the specified workspace, and optionally invoking 'openclaw' CLI. It does not instruct reading unrelated system files or sending data to external endpoints. The agent is instructed to write only after user confirmation.
✓
Install Mechanism
No install spec; instruction-only skill with one small included bash helper. The script performs only filesystem operations (mkdir, cp, cat) and contains no network downloads or execution of fetched code.
✓
Credentials
No environment variables, secrets, or external credentials are requested. The only external dependency referenced is the optional 'openclaw' CLI, which is coherent with the skill's purpose.
✓
Persistence & Privilege
always is false and the skill does not attempt to modify other skills or system-wide agent settings. Its runtime actions are limited to creating or copying files in user-provided workspace paths.
Assessment
This skill appears coherent and low-risk, but before running or granting autonomous use: inspect any proposed workspace path to avoid accidental overwrites, review the generated drafts before confirming writes, and verify the scaffold.sh source if you plan to run it locally (the script can create/overwrite files when --force is used). Be aware the workflow may call the 'openclaw' CLI if available — ensure that CLI is trusted and configured as you expect. If you want to restrict writes, ask for a docs-only run (the SKILL.md supports skipping CLI changes).

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

latestvk973c0jtdym521qx4gg0wdhtm182sgw1

License

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

Comments