Official Verified productivity Safety 4/5

buddy-followup

Agents say "I'll follow up" — and then forget. This skill fixes that. When you kick off a long-running task (sub-agent, build, API call, script), set a timer before you move on. When it fires, you wake up with the original context on every configured channel and actually deliver the update you promised. If the task isn't done yet, set another timer and keep going. No hardcoded IDs — channels are read dynamically from OpenClaw config.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/baiyishr/buddy-followup

Download Source Code (.zip)

What This Skill Does

The buddy-followup skill is a proactive task-management utility for OpenClaw agents. It solves the common 'forgetfulness' issue where an agent promises to report back on a long-running process but fails to do so once the context is lost. By utilizing scheduled cron jobs that trigger across all active channels, this skill acts as an automated 'wake-up call.' When the timer expires, the agent is re-initialized with the original task context, allowing it to verify the status of ongoing operations like deployments, API calls, or sub-agent builds. It dynamically discovers your configured communication channels via OpenClaw settings, ensuring that updates are delivered where the user is actually listening without requiring manual hardcoded IDs.

Installation

To install this skill, ensure you have the OpenClaw gateway running and the CLI available in your system PATH. The recommended installation method is via ClawHub using the command: npx clawhub install buddy-followup. Once installed, the shell script located at ~/clawd/skills/buddy-followup/scripts/followup.sh becomes accessible to your agent's execution tools. Verify your configuration by running openclaw config get to ensure your Telegram or WhatsApp channels are correctly set up, as the script will broadcast follow-ups to all configured channels automatically.

Use Cases

This skill is essential for managing asynchronous workflows. Use it when initiating a sub-agent to generate a report, when triggering a long-running CI/CD build, or when waiting for an external API rate-limit to reset. It is particularly valuable for complex chains of reasoning where an agent must pause, wait for an external system's state to change, and then synthesize the final result for the user. It transforms a passive agent into an active project manager that tracks its own promises.

Example Prompts

"I'm kicking off a container build that usually takes 5 minutes. Please use buddy-followup to check back with me once it's finished and report the status."
"I've triggered the database migration script. Set a follow-up for 10 minutes to verify if the tables were successfully updated."
"The sub-agent is scraping the website now. Set a 30-second timer to check if it has captured the data; if not, just schedule another check."

Tips & Limitations

When using this skill, estimate your delay conservatively. If you are unsure, err on the side of a slightly longer duration to prevent excessive chatter. Remember that each timer creates individual cron jobs for every active channel, so avoid setting hundreds of concurrent timers to keep your system clean. If a task is still incomplete when the timer fires, simply re-run the script with a new delay to maintain the loop. The skill is designed for transient tasks; it is not a replacement for persistent long-term background daemon monitoring.

Read Full Documentation on GitHub

Metadata

Author@baiyishr

Stars4473

Updated2026-05-01

View Author Profile

AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill

Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-baiyishr-buddy-followup": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Related Skills

calling-agent-squad

Activate a multi-agent team (the Squad) to manage complex projects, business tasks, or development workflows. The squad includes a Manager, Architect, Coder, Reviewer, and Observer. Use when the user wants to "call a squad", "start a project", or "deploy squad" with specialized roles and quality control loops.

arbiger 4473