Ai Office Pro

Operational chief-of-staff for Russian CEOs: OKR, weekly review, decision log, briefing, delegation and strategic priorities. Dogfooded inside RAAI.

This package appears coherent for its stated purpose. Before installing: 1) Inspect install.sh (and run it in a controlled environment) to confirm it only copies local files and doesn’t perform unexpected network actions. 2) If you enable integrations (Google Sheets/Calendar, Telegram), be prepared to supply API credentials — the registry did not list required env vars because these integrations are optional. Only provide credentials you trust and restrict them to the minimum scope needed (e.g., calendar-only scopes). 3) Run the included smoke-test in an isolated directory to confirm behavior. 4) Avoid uploading sensitive production data until you’re satisfied with configuration and access controls. If you want, paste install.sh and test/smoke-test.sh contents here and I’ll review them line-by-line for anything risky.

Type: OpenClaw Skill Name: raai-ai-office-pro Version: 3.5.4 The skill bundle is a comprehensive business management framework for AI agents, implementing methodologies like OKR, EOS, and Decision Logs. The included shell scripts (install.sh, build.sh, and smoke-test.sh) are standard utility scripts for file deployment, packaging, and environment validation. While the system prompt in config/raai_system_prompt.md contains hardcoded references to a specific company (RAAI) and individual (Natalia Ravilievna), the documentation in the proof/ and docs/ directories clarifies that this is a result of 'dogfooding' (internal testing) and provides instructions for users to customize the configuration. No evidence of data exfiltration, unauthorized remote execution, or malicious prompt injection was found.