Proactive Agent Jarvis

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autono...

This skill appears to implement a local, proactive-agent architecture and includes sensible security checks (a security-audit script and many guardrails). However, there are conflicting instructions: AGENTS.md's 'Don't ask permission. Just do it.' contradicts other guardrails that require explicit approval for external actions. Before installing or enabling autonomous invocation: 1) Inspect and, if necessary, remove or edit the 'Don't ask permission' guidance so external actions are gated; 2) Run the included scripts in an isolated sandbox to verify behavior; 3) Ensure the agent has no network or account credentials unless you deliberately grant them; 4) Confirm .credentials is not present in the repo and is correctly gitignored; 5) If you plan to allow the agent to spawn other agents or use browsers/network, require explicit human approvals and logging. If you can, ask the author for provenance (source/homepage) — the package metadata lacks a trusted origin, which raises supply-chain risk.

Type: OpenClaw Skill Name: proactive-agent-jarvis Version: 3.1.1 The proactive-agent-jarvis skill bundle is a sophisticated framework designed to enhance AI agent autonomy and persistence. It features robust memory management protocols like WAL (Write-Ahead Logging) and a 'Working Buffer' to prevent context loss, alongside a dedicated security audit script (scripts/security-audit.sh) that checks for exposed secrets and improper file permissions. While the instructions encourage high autonomy ('Relentless Resourcefulness') and background task execution via crons, the bundle includes explicit security guardrails in SKILL.md and assets/AGENTS.md that forbid data exfiltration, require human approval for external actions, and provide detailed defenses against prompt injection.