agentleFS
NoaiRoxNoaiRox/specialist-agent/skills/learn/SKILL.md

learn

Skill2 starsChanged 9 months agoMITView on GitHub

Use when implementing a feature and want to understand the code as it's built - during onboarding, teaching, or learning a new pattern.

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-anydoc, add-clidash and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • TomGranotSkill

    add-anydoc

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    Also in 5 projects that use this

  • TomGranotSkill

    add-clidash

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    Also in 5 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 11 projects that use this

  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • MicrosoftSkill

    add-codex

    Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

    Also in 6 projects that use this

  • MicrosoftSkill

    add-deltachat

    Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

    Also in 6 projects that use this

  • +5 more from TomGranot
  • +1 more from microsoft

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 170 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before writing any code, explain:

    line 29
  2. Distinctive:

    When using a pattern, explain it:

    line 111
  3. Distinctive:

    Use analogies for complex concepts

    line 177
  4. Distinctive:

    Use jargon without defining it

    line 187
  5. Distinctive:

    Never skip the "why": - Every piece needs justification

    line 256

“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/learn - Learning Mode Implementation

Implement features while explaining concepts, patterns, and decisions along the way.

Target: $ARGUMENTS

What Makes This Different

Normal Implementation:
  "Here's the code" → Done

Learning Mode:
  "Here's WHY we do this" → "Here's HOW it works" → "Here's the code" → Done

Workflow

Step 1: Context Setting

Before writing any code, explain:

## What We're Building

[Feature name] is a [type of thing] that [what it does].

**Why it matters:**
[Business/technical reason]

**Where it fits:**
[Location in architecture]

**Concepts you'll learn:**
- Concept 1
- Concept 2
- Concept 3

Step 2: Architecture Explanation

## Architecture Deep Dive

In this codebase, we follow [pattern name].

┌─────────────┐ │ Component │ ← UI layer, handles display └─────┬───────┘ │ uses ┌─────▼───────┐ │ Hook │ ← Logic layer, manages state └─────┬───────┘ │ calls ┌─────▼───────┐ │ Service │ ← Data layer, API calls └─────────────┘


**Why this pattern?**
[Explanation of benefits]

Step 3: Incremental Implementation with Teaching

For each piece of code:

## Step N: [What we're doing]

**The concept:**
[Explain the pattern/concept being used]

**Why this approach:**
[Explain the decision]

**The code:**
```typescript
// This creates a [thing] that [does what]
// We use [pattern] because [reason]
export const myFunction = () => {
  // First, we [action] to [achieve goal]
  const result = doSomething();

  // Then we [action] because [reason]
  return transform(result);
};

What just happened:

  1. We created [thing]
  2. It does [action]
  3. This enables [capability]

Try it yourself:

  • What would happen if we [changed X]?
  • How would you add [feature Y]?

### Step 4: Common Patterns

When using a pattern, explain it:

```markdown
## Pattern: [Pattern Name]

**What it is:**
[One sentence explanation]

**When to use it:**
- Situation 1
- Situation 2

**Example in our code:**
```typescript
// Here's how we apply [pattern]
const example = ...;

Alternatives considered:

  • [Alternative] - didn't use because [reason]

### Step 5: Gotchas and Best Practices

```markdown
## Watch Out For

**Common mistake #1:**
```typescript
// ❌ Don't do this
const bad = wrongApproach();

// ✓ Do this instead
const good = correctApproach();

Why: [Explanation]

Common mistake #2: [...]


### Step 6: Summary and Next Steps

```markdown
## What You Learned

1. **[Concept 1]:** [Brief explanation]
2. **[Concept 2]:** [Brief explanation]
3. **[Concept 3]:** [Brief explanation]

## Practice Exercises

1. Try adding [feature] using the same pattern
2. What would you change if [scenario]?
3. How does this connect to [related concept]?

## Further Reading

- [Link or reference 1]
- [Link or reference 2]

Teaching Style Guidelines

Do:

  • Explain WHY before HOW
  • Use analogies for complex concepts
  • Show wrong approaches and why they're wrong
  • Build complexity incrementally
  • Ask thought-provoking questions
  • Connect to broader patterns

Don't:

  • Dump code without explanation
  • Assume prior knowledge
  • Skip over "obvious" concepts
  • Use jargon without defining it
  • Rush through complex topics

Output Format

──── /learn ────
Topic: [feature name]

## Concepts Covered
1. [Concept]
2. [Concept]
3. [Concept]

## Implementation
[Code with inline teaching]

## Key Takeaways
- [Takeaway 1]
- [Takeaway 2]

## Practice
- [Exercise 1]
- [Exercise 2]

Example Session

──── /learn ────
Topic: Creating a User Service

## What We're Building

A UserService that fetches user data from an API and handles
loading states, errors, and caching.

**Concepts you'll learn:**
- Service layer pattern
- TypeScript generics
- Error handling strategies

## Let's Start

### Step 1: The Types

Before any logic, we define our types. This is called
"types-first development" - we describe the shape of our
data before we write code that uses it.

```typescript
// Why interface over type?
// Interfaces are better for object shapes because they:
// 1. Have better error messages
// 2. Can be extended
// 3. Are more familiar to OOP developers

interface User {
  id: string;
  name: string;
  email: string;
}

[... continues with teaching ...]


## Rules

1. **Never skip the "why"** - Every piece needs justification
2. **Build incrementally** - Complex → Simple steps
3. **Use visuals** - Diagrams help understanding
4. **Ask questions** - Engage the learner
5. **Connect concepts** - Show the bigger picture

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.