Interactive hiring wizard to set up a new AI team member. Guides the user through role design via conversation, generates agent identity files, and optionally sets up performance reviews. Use when the user wants to hire, add, or set up a new AI agent, team member, or assistant. Triggers on phrases like "hire", "add an agent", "I need help with X" (implying a new role), or "/hire".
Security Analysis
medium confidenceThe skill's requested actions and instructions are consistent with an interactive 'hire an AI agent' wizard; no unrelated credentials or external installs are requested, though a few runtime actions (creating files, symlinks, and optional cron jobs or reading gateway config) have operational implications the user should review.
The name/description match the SKILL.md instructions: the skill guides an interview, picks a model, and generates agent identity files under agents/<name>/. All required actions (model discovery, role mapping, file generation) are appropriate for a hiring/setup wizard.
Instructions are largely scoped to interviewing the user, choosing a model via `openclaw models list` or the gateway config, and creating files under agents/<name>/. Potentially sensitive steps: (1) 'check the gateway config' may read platform configuration; (2) creating an optional cron job to trigger reviews implies creating scheduled system tasks (unclear where/how). The skill does not ask for unrelated files, env vars, or credentials.
Instruction-only skill with no install spec or code files — nothing is downloaded or written at install time. This is the lowest install risk.
No environment variables, credentials, or external tokens are requested. The operations described (model discovery, directory creation, symlinks) are proportional to the stated purpose.
always:false and autonomous invocation allowed (platform default). The skill writes files into agents/<name>/ and suggests symlinking shared USER.md and MEMORY.md; it also optionally creates cron jobs for periodic reviews. Those are normal for a generator but do create persistent artifacts and system-level scheduling changes if executed — confirm where jobs will be created and what filesystem paths are used.
Guidance
This skill appears coherent for creating and onboarding an AI agent. Before installing or running it, confirm: (1) where it will write files (agents/<name>/) and whether those paths and any symlink targets (../../USER.md, ../../MEMORY.md) are acceptable and don't expose sensitive data; (2) what 'check the gateway config' will read — ensure it won't disclose platform secrets; (3) how the optional periodic reviews are implemented (system crontab vs. platform scheduler) and whether you want the skill to create scheduled system jobs. If you want to be cautious, run it in a sandboxed workspace, review the generated files before applying any symlinks, and decline the cron-job option or implement scheduling yourself.
Latest Release
v1.0.1
Auto-update gateway config on hire
More by @larsderidder
Published by @larsderidder on ClawHub
