Openclaw Coworker Prompts

100+ expert prompts to turn OpenClaw into an AI coworker across 44 professions. Instantly deploy agents for tech, business, healthcare, legal, media, and more.

This package is a coherent prompt collection and does not include code, installers, or required secrets — that reduces the immediate attack surface. Before installing/using: 1) Review individual prompts and remove or adapt any that ask agents to handle sensitive data (PHI, payroll, legal case material) unless you control a secure environment. 2) When you create agents from these prompts, avoid granting powerful tools (exec, file read/write, web_fetch) unless strictly necessary; test agents in an isolated environment first. 3) Do not provide real credentials or production data to agents created from these prompts; instead use sanitized examples. 4) Note provenance is limited (no homepage and contact via Telegram); if you require stronger provenance or support, seek packs with maintained repos and clear authorship. 5) Verify license terms and any payment method before purchasing or donating.

Type: OpenClaw Skill Name: openclaw-coworker-prompts Version: 1.0.1 The skill bundle is a collection of over 100 role-play prompts designed to configure OpenClaw agents for various professional tasks across 44 industries. While the bundle requests high-risk permissions such as 'exec' and 'web_search' in SKILL.md, these capabilities are aligned with the stated objectives of roles like DevOps Incident Responder and Security Vulnerability Scanner. No evidence of data exfiltration, malicious code execution, or prompt injection attacks was found within the prompt library (prompts_full.json) or the documentation.