Skip to main content
skill CX Codex

Learn · wrg32786 — Claude Code skill for learning notes

The Learn Claude Code skill turns research on a repo, talk, or tool into a structured note. It records an assessment and, for HOLD decisions, a condition for reviewing it again.

MIT ★ 26 updated 2026-11-16

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add wrg32786/aigent-os --skill learn -a claude-code
Open on GitHub

What Learn does

Learn assesses a tool, idea, or repository and saves the result as a note. It needs a subject, a source, and a 2–5 sentence snapshot; if any part is missing, it asks one focused question.

The skill places the subject in the Modern AI Infrastructure Stack and assigns ADOPT, HOLD, REJECT, or MONITOR. For HOLD, it records an observable reason to reconsider. It writes vault/concepts/learning/<subject-slug>.md and adds an entry to vault/concepts/learning/INDEX.md.

Layer placement relies on the Modern AI Infrastructure Stack note. Without that reference, the skill cannot place the subject in the stack.

What it helps with

  • record a decision after exploring a repository or talk
  • save why a tool was adopted or rejected
  • define an observable condition for revisiting a HOLD decision
  • look up an earlier assessment in the learning index

Example prompts for the agent

  • Record what I learned from the aigent-os repository and assess whether to use it.
  • I evaluated tool X. Save the source, your assessment, and a condition for reconsidering the decision.
  • What did we decide about tool Y? Find its learning note in the index.

How to install Learn

1Skills CLI (Vercel)

npx skills add wrg32786/aigent-os --skill learn -a claude-code

2Manually: put the files in place

~/.claude/skills/learn/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/learn/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about Learn

How do I install Learn in Claude Code?

Run npx skills add wrg32786/aigent-os --skill learn -a claude-code. The skill file is at ~/.claude/skills/learn/SKILL.md.

What does Learn do?

It creates a structured assessment note for a tool, idea, or repository, including its stack placement and decision status. A HOLD assessment also gets a condition for reconsideration, and the learning index is updated.

What information does Learn need?

Provide the subject, its source, and a 2–5 sentence snapshot. The skill uses the Modern AI Infrastructure Stack note to place the subject in the stack.

Source text

SKILL.md · MIT
---
name: Learn
description: "Capture structured learning notes in the vault with relevance and reconsideration triggers. Use when reading a repo, watching a talk, or learning a tool."
---

# Learn

The learning compounding skill. Most principals lose the value of a learning sweep within 48 hours — they read three repos, watch one talk, evaluate two tools, and a week later can't remember what they decided about any of them. `/learn` captures the structured outcome of every such sweep.

## When to use

- The principal has just read a repo, paper, talk, or tool description
- The principal is evaluating something but doesn't have an immediate need
- The principal asks "should I be using X?" or "what did we decide about Y?"
- After any session where the input was *learning*, not *doing*
- Use on prompts like: "/learn", "I just read", "evaluating", "looked into", "should I use", "what did we decide about", "captured this", "interesting tool", "considered tool"

## How to execute

### Step 1 — Take the input

The principal provides:
- **Subject:** the thing being evaluated (tool, technique, concept, repo, paper, idea)
- **Source:** where it came from (URL, talk title, conversation, repo name)
- **Snapshot:** 2-5 sentences on what the thing is and what it claims to do

If any field is missing, ask one focused question to get it.

### Step 2 — Locate it on the modern AI stack

Reference [[Modern AI Infrastructure Stack]]. Place the subject at the right layer:
- Application
- Persistence
- Messaging
- Isolation
- Compute
- Observability
- Orchestration

If it doesn't fit cleanly on the stack, it's either a doctrine concept (note that explicitly) or an artifact-of-AI-trends category (e.g., "agent framework", "prompt-engineering pattern").

### Step 3 — Assess relevance

Three categories:

- **ADOPT** — fits an actual current bottleneck. Action follows.
- **HOLD** — could fit in a future state, but no current bottleneck. Capture the trigger condition.
- **REJECT** — wrong category, wrong scale, or violates a load-bearing constraint. Capture the reasoning.
- **MONITOR** — interesting but no clear path. Re-evaluate next quarter.

### Step 4 — Capture reconsideration triggers (for HOLD only)

What specific change in circumstances would flip the decision?
- "When the framework starts spawning >10 parallel agents, reconsider isolation tools."
- "When a downstream user can't sandbox safely, reconsider authority gates."
- "When the principal hits the 10K-note vault size, reconsider semantic search alternatives."

The trigger has to be observable. "When we have more time" isn't a trigger. "When DECISION_OUTCOMES.md shows 5+ failed Authority Level 1 actions in a quarter" is.

### Step 5 — Write the note

File: `vault/concepts/learning/<subject-slug>.md`

Format:

```markdown
---
title: {Subject}
tags:
  - learning
  - {category}
status: ADOPT | HOLD | REJECT | MONITOR
stack-layer: {layer or N/A}
created: YYYY-MM-DD
last-reviewed: YYYY-MM-DD
source: {URL or reference}
---

# {Subject}

## What it is

{2-5 sentences from the input}

## Stack location

{One paragraph on where it sits in the modern AI stack and what category it competes in}

## Verdict

**{ADOPT | HOLD | REJECT | MONITOR}**

{1-3 sentences on the reasoning}

## Reconsider when

{Trigger condition, only for HOLD; for REJECT, "Never (fundamental rejection)"; for ADOPT, this becomes "Adopted on YYYY-MM-DD; re-evaluate annually"; for MONITOR, "Re-evaluate next quarter"}

## Connects to

{Wikilinks to related vault notes — other tools in the same category, doctrine that applies, relevant projects}
```

### Step 6 — Update the index

Append a one-line entry to `vault/concepts/learning/INDEX.md`:

```
- [[{subject-slug}]] — {category} — {ADOPT|HOLD|REJECT|MONITOR} — {YYYY-MM-DD}
```

The INDEX.md is the principal's external memory of considered tools. When they hit a real problem and need to remember "did I look at X?", the index answers in one read.

## Anti-patterns this prevents

- Learning sweeps that produce no captured artifact, then are forgotten
- Re-evaluating the same tool from scratch six months later
- Not knowing whether a tool was rejected or just unread
- Reconsider triggers that exist in the principal's head but aren't written down (so they never fire)
- Adopting a tool because it's "cool" without locating it on the stack or assessing fit

## Connects to

- [[Modern AI Infrastructure Stack]] — the layer map used for placement
- [[What I Am Not Building]] — REJECT entries from `/learn` graduate here when worth permanent doctrine
- [[Bio-hacking Posture]] — `/learn` is the supplements-and-restriction-evaluation skill
- `vault/concepts/learning/INDEX.md` — the running index this skill maintains

© wrg32786 · MIT · wrg32786/aigent-os

Similar skills

SKILL.md skills catalog →

Learn by other authors comes first.

learn rohitg00 learn is a Claude Code skill that teaches the AI Engineering from Scratch course in the terminal, section by section, quizzes at the end, and records progress. CX Codex +1 5,200installs learn tw93 learn — a six-phase research workflow that turns source material into notes, an outline, or a publish-ready draft. Use it for unfamiliar domains and multi-source work. CX Codex +1 13,600installs learn giuseppe-trisciuoglio learn analyzes a codebase to discover architectural patterns and conventions, then creates rule files in .claude/rules/. Useful when joining a new codebase. CX Codex +1 3,500installs learn Claude Code Academic Workflow learn extracts non-obvious fixes and workflows from your session into persistent skills. Useful when an undocumented workaround needs to be reused across future runs. CX Codex +1 ★ 1,729repo stars learn SethGammon learn turns completed campaigns or evolve cycles into structured project wiki entries. Use it to carry decisions and recurring patterns into future sessions. CX Codex +1 ★ 937repo stars caveman-learn JuliusBrussee This skill reads Caveman learn reports, proposes token-cost reductions, and asks for consent before each edit. Use it for heavy CLAUDE.md files or repeated context. CX Codex +1 130,900installs learn-taste emilkowalski learn-taste — a Claude Code skill turns design feedback into rules and records the reasoning behind them. It reviews session corrections and proposes which ones should carry into later work. CX Codex +1 13,700installs learn-codebase thedotmack learn-codebase — a skill for Claude Code, Codex, Cursor and other AI coding platforms that reads every source file in the project from start to finish. Runs when the user asks to learn, read or prime the codebase. CX Codex +1 5,800installs learn-agent-skills rohitg00 Interactive tutor for the Agent Skills Engineering track. Teaches one lesson per call, guides hands-on labs, and logs evidence to AGENT-SKILLS-LEARNING.md. CX Codex +1 3,700installs learn-mcp rohitg00 learn-mcp is a Claude Code skill that guides learners through Model Context Protocol lessons and records progress with observed evidence. It covers MCP clients, servers, and security. CX Codex +1 3,700installs scikit-learn K-Dense-AI A skill for Python machine learning tasks: classification, regression, clustering, preprocessing, and building ML pipelines with scikit-learn 1.9.1. CX Codex +1 2,400installs

From the same set58

The whole set →
nightly-ledger-capture The nightly-ledger-capture Claude Code skill stages candidates for honesty, trust-decay, failure-mode, and decision-outcome records. It gathers local evidence from logs and Git; a human gate controls writes. CX Codex +1 ★ 26repo stars nightly-close-parity This skill for Claude Code runs a project’s nightly close-parity maintenance. It checks the local route first, then follows the protocol stored in the project. CX Codex +1 ★ 26repo stars meta-improve A Claude Code skill applies operator-approved Dream candidates through a gated change process. Run it with /meta-improve-vault before building the change. CX Codex +1 ★ 26repo stars memory-bridge The memory-bridge Claude Code skill connects explicit memory requests to Hindsight and Jev. Ask it to retain, recall, or reflect on a note to trigger the bridge. CX Codex +1 ★ 26repo stars learn-from-failure The learn-from-failure Claude Code skill classifies failures and checks whether their causes have appeared before. Repeated problems lead to a durable artifact meant to prevent another recurrence. CX Codex +1 ★ 26repo stars impeccable The impeccable Claude Code skill guides frontend design, helps establish a project’s visual direction, and can extract components and design tokens. It needs context about users, their tasks, and the brand’s tone. CX Codex +1 ★ 26repo stars humanize-docs humanize-docs is a Claude Code skill that transforms robotic documentation into natural prose. It rewrites technical docs and README files by removing repetitive checklists and rigid section structures. CX Codex +1 ★ 26repo stars Honesty Check The Honesty Check Claude Code skill builds an honesty ledger for completed work. It runs before an agent reports a task as done or prepares it for review. CX Codex +1 ★ 26repo stars

Project sponsors

Companies that keep this analytics open