← Back to Skills Marketplace
Proactive Agent Skill
by
fangkelvin
· GitHub ↗
· v1.0.0
18354
Downloads
10
Stars
225
Active Installs
1
Versions
Install in OpenClaw
/install proactive-agent-skill
Description
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Includes WAL Protocol, Working Buffer, Autono...
Usage Guidance
Install only if you are prepared to configure it narrowly. Before enabling it, decide exactly what may be remembered, which accounts or folders may be checked, whether any cron jobs may run after the session, and how to review, disable, and delete saved memory. Do not allow it to store credentials, tokens, regulated personal data, or confidential business content without explicit controls.
Capability Assessment
Purpose & Capability
The stated proactive-agent purpose coherently matches memory, heartbeat, and cron guidance, but the artifact also promotes broad ongoing access to email, calendar, system status, files, backups, and long-term logs without defining safe boundaries.
Instruction Scope
The runtime guidance describes logging exchanges, curating long-term memory, and creating autonomous cron jobs, but does not require explicit opt-in, account or directory scoping, dry-run behavior, confirmation for risky actions, or disable/removal steps.
Install Mechanism
The package contains only SKILL.md, declares no required binaries, and includes no executable install script; the risk comes from the instructions an agent or user may implement after installation.
Credentials
Recurring checks of email, calendar, weather, system health, file organization, and backup verification can be proportionate for a proactive assistant only with least-privilege scoping and user control, which the artifact does not provide.
Persistence & Privilege
The skill explicitly promotes working buffers, daily raw logs, MEMORY.md long-term storage, automatic compaction/archiving, and scheduled OpenClaw runs, but lacks clear redaction, retention, audit, or deletion controls.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install proactive-agent-skill - After installation, invoke the skill by name or use
/proactive-agent-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of proactive-agent skill (v1.0.0).
- Implements core WAL Protocol for state persistence and recovery.
- Introduces working buffer for critical context logging and memory compaction.
- Adds support for proactive heartbeats and autonomous/prompted cron automation.
- Provides configuration templates and best practices for proactive, self-improving agent design.
Metadata
Frequently Asked Questions
What is Proactive Agent Skill?
Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Includes WAL Protocol, Working Buffer, Autono... It is an AI Agent Skill for Claude Code / OpenClaw, with 18354 downloads so far.
How do I install Proactive Agent Skill?
Run "/install proactive-agent-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Proactive Agent Skill free?
Yes, Proactive Agent Skill is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Proactive Agent Skill support?
Proactive Agent Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Proactive Agent Skill?
It is built and maintained by fangkelvin (@fangkelvin); the current version is v1.0.0.
More Skills