# Notenik as AI Agent Dashboard

**URL:** https://discourse.notenik.app/t/notenik-as-ai-agent-dashboard/902
**Category:** Community Discussion
**Created:** [September 20, 2026, 8:41pm UTC](https://discourse.notenik.app/t/notenik-as-ai-agent-dashboard/902 "2026-09-20T20:41:07Z")
**Posts on this page:** 5
**Page:** 1

<div class="post-metadata">

### Author: ![Malcolm](https://discourse.notenik.app/letter_avatar_proxy/v4/letter/m/e19b73/32.png) [@Malcolm](https://discourse.notenik.app/u/Malcolm)
#### Post date: [September 20, 2026, 8:41pm UTC](https://discourse.notenik.app/t/notenik-as-ai-agent-dashboard/902/1 "2026-09-20T20:41:07Z")

</div>

I’m reading the Claude documentation and wondering whether anyone is using Notenik creating a skills collection for claude projects.

It seems as though it could be a good match. The front matter has [a clearly defined set of fields](https://code.claude.com/docs/en/sub-agents#supported-frontmatter-fields).

Look at the example below and you can see what looks like a Notenik file. Having all of the front matter fields defined in a collection, with their options set as choices, seems like it would be a great tool for generating agentic tasks.

> ## More control over subagents
> 
> You get a lot of control over a custom subagent from its frontmatter. You can pick its model and effort, limit its tools, cap its turns, give it its own worktree or memory
> 
> ```auto
> .claude/agents/log-scanner.md
> ---
> name: log-scanner
> description: Scans CI logs for the first failing step and reports it
> model: sonnet
> effort: low
> memory: project
> omitClaudeMd: true
> ---
>  
> Find the first failing step in the log you are given and report the command, the error and the file it points to.
> 
> ```

---

<div class="post-metadata">

### Author: ![ThePrinter](https://discourse.notenik.app/user_avatar/discourse.notenik.app/theprinter/32/579_2.png) [@ThePrinter](https://discourse.notenik.app/u/ThePrinter)
#### Post date: [September 21, 2026, 9:40pm UTC](https://discourse.notenik.app/t/notenik-as-ai-agent-dashboard/902/2 "2026-09-21T21:40:05Z")

</div>

I don’t use agents but I don’t see why an agent wouldn’t be able to access an entire Notenik collection formatted like this. You could probably dictate an entire workflow from a collection.

---

<div class="post-metadata">

### Author: ![Malcolm](https://discourse.notenik.app/letter_avatar_proxy/v4/letter/m/e19b73/32.png) [@Malcolm](https://discourse.notenik.app/u/Malcolm)
#### Post date: [September 22, 2026, 3:17am UTC](https://discourse.notenik.app/t/notenik-as-ai-agent-dashboard/902/3 "2026-09-22T03:17:47Z")

</div>

I’m not using agents yet. I’m using Claude more and more and I expect that I’ll start to use agents at some point.

I’m imagining that it could go in the other direction too. The agents could be generating notes in a collection, making Notenik a reader, manager.

---

<div class="post-metadata">

### Author: ![ThePrinter](https://discourse.notenik.app/user_avatar/discourse.notenik.app/theprinter/32/579_2.png) [@ThePrinter](https://discourse.notenik.app/u/ThePrinter)
#### Post date: [September 22, 2026, 12:56pm UTC](https://discourse.notenik.app/t/notenik-as-ai-agent-dashboard/902/4 "2026-09-22T12:56:24Z")

</div>

After coming across [this Git repo](https://github.com/AminBlg/SimpleEnglish/tree/main/skills/simple-english) for a set of skills to simplify LLM output using [Simplified Technical English](https://en.wikipedia.org/wiki/Simplified_Technical_English) I’m even more sold on this idea.

> [@Malcolm](#):
>
> The agents could be generating notes in a collection, making Notenik a reader, manager.

This is something I’ve been skeptic of. But after reading [Andrej Karpathy’s explanation](https://x.com/karpathy/status/2039805659525644595) (ex-OpenAI/current Anthropic) in limited cases I can see how it can be useful.

> TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it’s the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

Between the periphrastic output and my waning interest in “chatting” with Claude an “LLM wiki” could be a decent alternative frontend.

---

<div class="post-metadata">

### Author: ![Malcolm](https://discourse.notenik.app/letter_avatar_proxy/v4/letter/m/e19b73/32.png) [@Malcolm](https://discourse.notenik.app/u/Malcolm)
#### Post date: [September 22, 2026, 8:52pm UTC](https://discourse.notenik.app/t/notenik-as-ai-agent-dashboard/902/5 "2026-09-22T20:52:40Z")

</div>

> [@ThePrinter](#):
>
> the periphrastic output

and the sycophancy.

🤕
