---
title: "Lauren Tan's skills"
description: "Lauren Tan (poteto) publishes skills in several repos: brainmaxxing for memory and skill improvement, noodle for skill-based orchestration, how for explaining a codebase, and a verification-skill example."
plain: "Lauren Tan publishes skills for memory, skill-based orchestration, explaining a codebase, and verification."
group: idea
terms:
  - "Lauren Tan's skills"
  - brainmaxxing
  - noodle
  - "verification skill"
sources:
  - url: https://github.com/poteto/brainmaxxing
    title: "GitHub - poteto/brainmaxxing: stupid simple persistent memory and skill improvement · GitHub"
    publisher: "GitHub poteto/brainmaxxing"
    note: "Memory repository; used for the vault and learning-loop skills."
    accessed: "2026-10-01"
  - url: https://github.com/poteto/noodle
    title: "GitHub - poteto/noodle: Orchestrate agents using skills · GitHub"
    publisher: "GitHub poteto/noodle"
    note: "Orchestration repository; used for scheduled markdown skills."
    accessed: "2026-10-01"
  - url: https://github.com/poteto/how
    title: "GitHub - poteto/how: skill for explaining architecture · GitHub"
    publisher: "GitHub poteto/how"
    note: "Architecture explanation skill; used for exploration and critique modes."
    accessed: "2026-10-01"
  - url: https://github.com/poteto/verification-skill-example
    title: "GitHub - poteto/verification-skill-example: Example: project-local verification skill + large-app feature map (fictional Atlas / Harbor Labs) · GitHub"
    publisher: "GitHub poteto/verification-skill-example"
    note: "Verification example; used for scoped skills and a behavior-level feature map."
    accessed: "2026-10-01"
---

# Lauren Tan's skills

> For agents: start with the [agent guide](https://ratstack.sh/llms.txt). Every page is Markdown by default; add `Accept: text/html` for HTML.

New on /news: [Foldkit 0.171.0 requires result Message schemas](/news).

Lauren Tan (poteto) ships skills across four repos. Her talk on verification and skills is on [Lauren Tan](/lore/lauren-tan) and [the Dune talk](/lore/poteto-lauren-tan-2500-prs-dune).

**[brainmaxxing](https://github.com/poteto/brainmaxxing/blob/ec4d8e43dee639d6f5d94aed3ca16af7b298ecfc/README.md)** is "stupid simple persistent memory for Claude Code". The agent reads its folder of Markdown memory files at session start and writes to it when it learns something. It ships 16 starter principles and six skills. `brain` supplies the vault workflow; `plan` and `review` support structured work.

Three form a learning loop:

- **`reflect`**: After sessions.
- **`ruminate`**: Over past conversations.
- **`meditate`**: Audit and prune.

The README says `/reflect` alone gets you most of the value. [Skills](https://github.com/poteto/brainmaxxing/tree/ec4d8e43dee639d6f5d94aed3ca16af7b298ecfc/.agents/skills)

**[noodle](https://github.com/poteto/noodle/blob/82d2921c52370f23f29086de81ccfb600939c037/INSTALL.md)** is "skill-based agent orchestration," built in Go. You write skills as markdown files. Noodle's loop schedules and runs them.

It adds one field to skill frontmatter, `schedule`. A skill with it becomes autonomous. The scheduler reads its value as prose. The minimum loop is a schedule skill and an execute skill.

The repo's [own skills](https://github.com/poteto/noodle/tree/82d2921c52370f23f29086de81ccfb600939c037/.agents/skills) include `adversarial-review`, `quality`, `execute`, and `schedule`.

**[how](https://github.com/poteto/how/blob/b1ef42969ea7a2bb50aa26c2480274828a0385e7/README.md)** is a Cursor plugin with one skill, `/how`. It explains how a subsystem or flow works. Critique mode runs critics across different models. For complex questions, it runs parallel explorer subagents and reconciles their findings.

**[verification-skill-example](https://github.com/poteto/verification-skill-example/blob/d5abe70d0d8c671672b6cef4069363f26c488feb/README.md)** is a fictionalized example of a project-local verification skill with a list of features and checks that verify their behavior. About 30 files cover one feature area each. Its README argues that a wiki is for humans. Agents pay for every token they reread.

It argues that a scoped skill plus feature map is cheaper to use and maintained as code. The README calls it a private reference and says the driver scripts are omitted.

Related: [Matt Pocock's skills](/lore/matt-pocock-skills).

## Sources

1. [GitHub - poteto/brainmaxxing: stupid simple persistent memory and skill improvement · GitHub](https://github.com/poteto/brainmaxxing)
   GitHub poteto/brainmaxxing. Memory repository; used for the vault and learning-loop skills. Accessed 2026-10-01.

2. [GitHub - poteto/noodle: Orchestrate agents using skills · GitHub](https://github.com/poteto/noodle)
   GitHub poteto/noodle. Orchestration repository; used for scheduled markdown skills. Accessed 2026-10-01.

3. [GitHub - poteto/how: skill for explaining architecture · GitHub](https://github.com/poteto/how)
   GitHub poteto/how. Architecture explanation skill; used for exploration and critique modes. Accessed 2026-10-01.

4. [GitHub - poteto/verification-skill-example: Example: project-local verification skill + large-app feature map (fictional Atlas / Harbor Labs) · GitHub](https://github.com/poteto/verification-skill-example)
   GitHub poteto/verification-skill-example. Verification example; used for scoped skills and a behavior-level feature map. Accessed 2026-10-01.

## Lore on this page

- [Lauren Tan](/lore/lauren-tan)

## Linked from

- Agent guide → An Effect stack so pure (aspirational) Kit Langton will blush. → [Read page](https://ratstack.sh/llms.txt)

- Change log → What changed in the files served here, newest first. → [Read page](https://ratstack.sh/log)

- Full agent guide → An Effect stack so pure (aspirational) Kit Langton will blush. → [Read page](https://ratstack.sh/llms-full.txt)

- Matt Pocock's skills → Matt Pocock's skills repo packages the agent skills he says he uses every day, built to be small, adaptable, and composable. → [Read page](https://ratstack.sh/lore/matt-pocock-skills)

- Rat Stack lore | rat-stack → Short, source-grounded notes on the ideas and decisions behind rat-stack. → [Read page](https://ratstack.sh/lore)

- Source change history (log.md) → The generated change log as Markdown. → [Read page](https://ratstack.sh/log.md)
