Patterns

Community

tkellogg

patterns

Index of recurring problem shapes — environmental awareness (world-scanning, OS event hooks, browser automation), communication (messaging, multi-agent handoff, async waits), coordination between parallel things (avoiding collisions, oscillation, double-work), and self-correction (circuit-breaker, try-harder). Use when designing a non-trivial workflow, when the same shape just happened twice, or when the answer to "what should I do here?" isn't obvious. Don't read on every turn.

Overview

Publisher	tkellogg
Repository	`open-strix`
Skill name	`patterns`
Stars	95
Forks	21
Bundled files	16
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
16 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by tkellogg on GitHub. Read the source before you install it.

Installation

Install the Patterns AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/tkellogg/open-strix/tree/main/open_strix/builtin_skills/patterns
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/tkellogg/open-strix.git /tmp/open-strix
mkdir -p .claude/skills
cp -r /tmp/open-strix/open_strix/builtin_skills/patterns .claude/skills/patterns

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Patterns in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Patterns on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Patterns is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Having problems that look like this?

Out-of-date info — world-scanning.md
Awareness of surroundings — world-scanning.md
Getting ahead of problems — world-scanning.md
Sending information or messages between computers — messaging.md
Notifying another agent that something happened — messaging.md
Reacting when the user opens their laptop, locks the screen, plugs in a USB, joins Wi-Fi, etc. — os-events-macos.md / os-events-windows.md / os-events-linux.md
Hooking into anything the operating system already knows about — os-events-{macos,windows,linux}.md
Scraping a site that has no API, especially behind a login wall — browser-automation.md
Driving a SaaS dashboard to click a button or download a file — browser-automation.md
Personal-data dashboards from services that don't expose one — browser-automation.md
Need to wait for a human action (click, login, file drop) without burning tokens — async-tasks.md
"Wake me up when X happens" where X is a one-shot event — async-tasks.md
Pausing this conversation across an indeterminate wait without losing context — async-tasks.md
Handing work to another agent (sub-agent, peer, fresh self) — multi-agent-handoff.md
What survives across a fresh-context turn (async wake-up, schedule fire, compaction) — context-boundaries.md
How to write journal entries that future-you / introspection-you will actually find useful — journal-as-breadcrumbs.md
Picking the right temporal primitive (poller / schedule / loop / async-block / OS cron) — scheduling.md
Building redundancy into channels, scrapers, sources without overengineering — fallback-chains.md
Recognizing your own loops / runaway behavior and stopping yourself — circuit-breaker.md
Stuck on something — what to do instead of grit (edit blocks, edit checkpoint.md, find conflicts) — try-harder.md
The instinct to "try harder" / "do better" / "be more careful" — try-harder.md (almost always the wrong move)
Two parallel things stepping on each other (schedules colliding, pollers in storm, double-messaging, oscillating state files) — coordination.md
"It worked fine for weeks then suddenly two of X happened" — coordination.md (S2 collision)
No durable place to track what you've noticed, committed to, or finished — interest-backlog.md
"I should remember to look into X" / "that was weird but I don't have time now" — interest-backlog.md (log it, drain it later)

Two rules worth pulling forward

These show up repeatedly in the sub-pages but are easy to miss if you only skim the index.

The artifact of trying harder is a diff someone else can verify, not a resolution someone else has to trust. If your "fix" is a commitment to do better, it dies the moment your turn ends. See try-harder.md.
Journal entries should have handles, not prose. j_abc123 and /tmp/rl.md survive a context boundary; "I spawned a job and will check on it" doesn't. See journal-as-breadcrumbs.md.

It's worth running a five-why's on your problem to see if some of this info applies.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Patterns AI skill do?

Why use Patterns on TypingMind?

Because you install it once and use it with any model. Patterns is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Patterns in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tkellogg/open-strix/tree/main/open_strix/builtin_skills/patterns. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Patterns?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Patterns?

As many as you like. As long as a model supports skills, you can use Patterns with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Patterns AI skill free?

Yes. It is published on GitHub by tkellogg under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Refactor Docs

openclaw

OrganizationPopular

Refactor an existing OpenClaw docs page with source-audited preservation, restructuring, and verification.

Openclaw Repair Sweep

openclaw

OrganizationPopular

Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

Openclaw Test Performance

openclaw

OrganizationPopular

Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.

Openclaw Testing

Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Two rules worth pulling forward

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now