hive-12390 community on Hive

Skill: Morty's Mind Blowers

inertia — Tue, 07 Apr 2026 15:47:03 GMT

https://clawhub.ai/inertia186/mortys-mind-blowers

I made this skill to help find memories and recap them as a funny story. You just tell openclaw, "Let's do some Morty's Mind Blowers!" Then it goes through memory and recreates the memory as an anecdote.

I think this pairs well with the new /dreaming feature.

Skill: MAL*P

inertia — Mon, 30 Mar 2026 21:12:33 GMT

https://clawhub.ai/inertia186/malp

I explain it in the skill, but in a nutshell, it’s a scout sent to your local hard drive to monitor a folder. It creates a .malp folder with SUMMARY.txt and NOTES.txt. OpenClaw keeps these files updated with your notes for later sessions.

One thing I intentionally left out of the skill is the fact that having a .malp in your project works with non-OpenClaw systems like JetBrains AI, which focuses on IDE projects. You can tell your IDE about the .malp/NOTES.txt to get it up-to-speed without OpenClaw.

This means you’ll use your JetBrains AI token credits separately from OpenClaw, adhering to the JetBrains TOS.

Receive proactive alerts when your openclaw instance is unavailable

themarkymark — Sun, 29 Mar 2026 10:25:51 GMT

When openclaw breaks, it isn't always obvious right away. You might be waiting for a response, or just not actually doing anything at the time. It isn't like a typical web service where you can use uptime monitoring to see if the url is still up. You can monitor the gateway, but that monitors part of your openclaw infrastructure.

I use a heartbeat check to keep an eye on my openclaw instance and make sure it is all working. I am not referring to heartbeat.md, but this process will use that as well. Healthchecks.io is the best way to do these checks, a free account gets 20 checks. If you use Uptime Kuma, you can also use that.

A heartbeat check is the opposite of a typical up/down monitor, it expects a ping every so often, if it doesn't receive one, it will send an alert. This pattern is really good for backups and other scripts where you want to be notified when they don't run properly. If a heartbeat isn't detected in a certain time period, you know something is wrong.

Here is the pattern in action:

Openclaw will typically monitor heartbeat.md every 30 minutes, and run regular tasks that need to be run many times a day, like checking email. I rarely use heatbeat.md as cron is almost always a better choice. However for this job, heartbeat.md is a good choice.

How to set up monitoring

First you need to create a check in Healthchecks.io, you can use a free instance or run your own local install.

Once created, you will get a url that you need to visit every 30 minutes or the system will send an alert if it hasn't heard from anyone in an hour.

Then tell your agent to curl this url in heartbeat.md, no output is needed.

That's it!

If your openclaw is broken, or your LLM is not responding, or any configuration issue is present, it won't process this heartbeat and you will get an alert within an hour. You can also reduce the grace period to be 32 minutes, and be alerted a lot quicker on a single failure.

You will need to adjust the grace period based on your openclaw's heartbeat, which defaults to 30 minutes.

This is also a good way to make sure your heartbeats are firing properly. Using cron is also a perfectly valid option. In fact, I use cron exclusively as it is almost always a better choice and will drastically reduce your token usage.

Heartbeats run in your agents context where as cron jobs can run in main agent's context or in an isolated context. This subtle difference is massive for "token burn", as you can be sending tens of thousands or even hundred thousand tokens just to do a simple curl command when using a heartbeat. At 30 minutes, this means 48 events in your main agent's context window.

If you change your mind later, you can easily move it to an isolated cron job. Your agents should be able to handle this.

If you want to test your heartbeats are working as well as the rest of openclaw workflow, use heartbeat.md. If you want to optimize token burn, use an isolated cron job.

Skill: Unreliable Teleplay Lens

inertia — Tue, 24 Mar 2026 23:27:18 GMT

I have posted a skill on clawhub.ai:

https://clawhub.ai/inertia186/unreliable-teleplay-lens

It’s designed to reconcile various stories within the same cinematic universe over decades that may not always align. Some refer to it as a "headcanon," but I find that term rather unappealing.

As an openclaw skill, it provides the agent with the flexibility to develop characters or stories without adhering to a single authoritative narrative.

It's based on this idea:

https://peakd.com/fiction/@inertia/unreliable-teleplay

My two favorite Openclaw hacks

themarkymark — Mon, 16 Mar 2026 08:02:09 GMT

I use openclaw a lot, and I spent a good amount of time tweaking it to get it how I want it. A good part of this is creating skills that allow it to do things I need. While doing this, I have found many times it wasn't using the skills I want it to use. This happens a lot when setting up new skills and trying to get the description and trigger phrases ironed out so it uses the skill naturally.

I found myself asking my agents "What skills did you use?" all the time and it was getting annoying. With this line added to your TOOLS.md, you will never have to do this again.

Always Show Skills Used: When using any skill, include Skills Used: at the end of your response listing which skill(s) were used.

Now I never have to ask, and I also can see when it finds creative usages to the skills I make available.

Another problem I had that was solved in a similar way, is when files are edited and I wasn't aware of it.

Always Show Files Modified: When editing or creating files, always show files modified at the end. Files Files Modified:.

This simple addition to your TOOLS.md and you never have to guess!

I am impressed at how well my agents do this without being reminded. This is really handy when troubleshooting skills execution.

This is also very handy in harnesses and is not limited to openclaw.

If you are running openclaw, make sure you are updated.

themarkymark — Fri, 06 Mar 2026 03:59:51 GMT

This is a cross post of @themarkymark/if-you-are-running-openclaw-make-sure-you-are-updated by @themarkymark.

PSA

Some things I wish someone told me when I setup Openclaw

themarkymark — Fri, 06 Mar 2026 03:53:09 GMT

If you are not using Openclaw (previously clawdis, clawdbot, moltbot), you can just skip this post, it probably won't make a lot of sense.

Before you do anything with Openclaw, security should be your number one priority.

![untitled.gif](https://media.tenor.com/HloGNXrhi9wAAAAC/crazy-russian-hacker-shades-on.gif)

Lock down your gateway, NOW!

The first thing is to make sure you are not exposing your gateway to the Internet. If you want to access it remotely, use a VPN or something like Tailscale.

Openclaw is has more attack vectors than most software and users are connecting more and more private information to it so it can do it's thing. The core developer is aggressively addressing security issues at an amazing pace, but this is not software you want exposed directly to the Internet.

You can use a port scan from an external source to verify you are not exposing the gateway. By default, Openclaw will use port 18789 without SSL.

While you are at it, enabling SSL is a very good idea, this will protect your traffic against anything that may try to snoop it on your LAN. Look at traefik, nginx, or caddy to solve this problem.

Trust NO ONE!

One of the coolest things with Openclaw is skills. This allows you to bundle code and instructions into a repeatable skill that Openclaw can use. A good example is @asgarth's Hive skill.

There is a website call Clawhub that allows people to share skills they developed. In the early days these skills were frequently malicious and infected with malware and bad intent, in fact the number downloaded skill as the worst offender. This has been improved as the lead developer Peter Steinberger added many malware and security screenings to uploaded skills. This doesn't mean they are 100% safe, especially if you get them from somewhere other than Claw Hub.

You should review all skills you install, or at minimum have a quality LLM scan it.

You get what you pay for.

Low cost LLM that you can host yourself or are very cheap will give you very poor results. Especially at task execution and recalling memories. Unless you have 100GB+ of VRAM, I would recommend using a quality paid model. This can get very expensive if you are not using a paid subscription that is a one time cost.

If you have to run a local model, I recommend Qwen 3.5 models for under 100GB of ram and something like MiniMax M2.5 for larger GPU deployments like mine.

Otherwise, I would recommend ChatGPT, MiniMax, or Kimi coding subscription. These will give you the most value without breaking the bank. Do expect to spend at least $20 a month for a subscription/credits at minimum. I have seen many users spending hundred dollars a day in credits when not using a subscription.

Cron, Cron, Cron!

Openclaw has two methods of proactive and reoccurring tasks.

Heartbeat

This is typically run every 30 minutes.

Cron

This is your typical unix style scheduling and can be set to any schedule you want.

Cron is always the preferred method for anything with a predictable schedule, like once every day or every 4 hours. The big reason for this is every heartbeat is processed by your main agent and thus goes through your LLM. This can easily consume millions of tokens a day and can be a large portion of your token usage.

Heartbeat is good for tasks that have to be done very frequently, like check email.

Be a janitor

Openclaw can do some amazing things on it's own with the right direction. It can also do some stupid shit on a regular basis. You tell it to create a script for XYZ and it puts it in one location. Tomorrow you ask it to create another script for some other XYZ and it puts it in a totally different location. It will do things at times that will seem very stupid, but if you only use the gateway or channel (i.e. telegram/discord) you will never notice.

I recommend just giving the file system a manual look over once a month or even once a week depending on how active you are. Look over your workspace, look where scripts are being stored and make sure anything related to a specific skill is in the correct skill folder. Anything related to scripts are all in one scripts folder.

I like to keep my skills in .openclaw/skills so all agents can use them. Unless I am 100% sure it is only going to be used by one agent, this is how I roll. This works most of the time, but sometimes when you create a new skill through Openclaw it will put it in one agents workspace or even somewhere completely different. I like to fix these things every time I do a pass through.

Read the full post