agentleFS
Baba01hacker666Baba01hacker666/dummyskills/skills/step-by-step-tutorial/SKILL.md

step-by-step-tutorial

Skill0 starsChanged 2 months agoMITView on GitHub

Writes a practical, reproducible tutorial for a single workflow with runnable commands and expected outputs.

  • Installs packages

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 14
  2. Very specific:

    Do not use for high-level repository documentation.

    line 20
  3. Very specific:

    Do not use for autonomous task execution plans.

    line 21
  4. Very specific:

    If prerequisites are not specified: list minimum standard tools (e.g.

    line 29
  5. Very specific:

    Never write incomplete code snippets with placeholders like // TODO: implement logic.

    line 30
  6. Distinctive:

    If an API key or token is needed: instruct reader to set environment variable, never hardcode.

    line 31
  7. Distinctive:

    Follow these numbered actions:

    line 34
  8. Distinctive:

    If a command can fail due to permissions: prepend guidance on non-root execution or virtual environments.

    line 47
  9. Very specific:

    Always provide copy-pasteable commands without leading $ prompts inside code blocks if multi-line.

    line 48
  10. Distinctive:

    Stop and ask the user when:

    line 108

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Step-by-Step Tutorial

Authors an instructional, end-to-end tutorial for a specific technical task. Every step provides complete, runnable code and expected output screenshots/text.

1. Purpose

Enable a developer to successfully complete a single goal from start to finish without getting stuck. A "Tutorial" is a guided journey with prerequisites, sequential numbered actions, and self-checks.

2. When to Use

Use this skill when:

  • Writing "Getting Started with Feature X" or "How to deploy Y" documentation.
  • Explaining an onboarding workflow to developers.
  • User requests: "Write a tutorial on how to do X."

3. When Not to Use

  • Do not use for high-level repository documentation; use readme-writer.
  • Do not use for autonomous task execution plans; use step-decomposer.

4. Required Inputs

  • tutorial_topic: What the reader will build or achieve (string).
  • prerequisites: Required tools, software versions, and existing credentials.
  • verified_steps: Concrete sequence of actions to perform.

5. Missing-Input Behavior

  1. If prerequisites are not specified: list minimum standard tools (e.g. terminal, Git, current LTS runtime).
  2. Never write incomplete code snippets with placeholders like // TODO: implement logic.
  3. If an API key or token is needed: instruct reader to set environment variable, never hardcode.

6. Procedure

Follow these numbered actions:

  1. Action 1: Define Goal & Outcome
    • State what the user will achieve in 1 paragraph.
  2. Action 2: State Prerequisites
    • List required software, OS compatibility, and background knowledge.
  3. Action 3: Write Sequential Steps
    • Each step has: Context, Code/Command block, and Expected Terminal Output.
  4. Action 4: Add Verification Step
    • Provide a final test or curl command to verify success.
  5. Action 5: Emit Tutorial
    • Format using Section 8.

7. Decision Rules

  • If a command can fail due to permissions: prepend guidance on non-root execution or virtual environments.
  • Always provide copy-pasteable commands without leading $ prompts inside code blocks if multi-line.

8. Output Format

Emit the tutorial using this template:

# How to: [Tutorial Title]

[Brief explanation of what will be built and time required.]

## Prerequisites
- [Prerequisite 1]
- [Prerequisite 2]

---

### Step 1: [Action Title]
[Short context explaining what this step does.]

```bash
[Command to run]

Expected Output:

[What the reader should see]

Step 2: [Action Title]

[Complete code block]

Verification

Run the following check to verify your setup:

[Verification command]

Expected result: [Expected return]

Next Steps

  • [Pointers to advanced configuration or related skills]

## 9. Verification Checklist
- [ ] Prerequisites list all required tools.
- [ ] Every code snippet is syntactically complete.
- [ ] Expected output is provided for every execution step.
- [ ] Final verification step tests the end-to-end workflow.

## 10. Common Failures and Recovery
| Failure Symptom | Cause | Recovery Action |
| :--- | :--- | :--- |
| Reader gets stuck on missing dependency | Unstated prerequisite | Add explicit installation command in Step 1. |
| Code block fails to run | Missing imports | Include all required import/require statements in snippets. |

## 11. Stop or Escalation Conditions
Stop and ask the user when:
- The tutorial workflow involves paid services or proprietary internal tools not documented.

## 12. Examples

### Example 1: Successful Execution
**Input:**
```text
Topic: Setting up Express with TypeScript
Audience: Junior developer
Steps: npm init, install express + ts-node + typescript, write basic server, run with ts-node.

Output:

# How to Set Up an Express Server with TypeScript

In this tutorial, you will create a minimal, type-safe Express HTTP server from scratch.

## Prerequisites
- Node.js >= 20.0.0
- A terminal with bash or zsh

---

### Step 1: Initialize the Project
Create a new directory and initialize package configuration:

```bash
mkdir express-ts-demo && cd express-ts-demo
npm init -y

Step 2: Install Dependencies

Install Express and the TypeScript developer tooling:

npm install express
npm install -D typescript @types/node @types/express ts-node

Step 3: Create Server Entry File

Create src/server.ts with the following code:

import express, { Request, Response } from 'express';

const app = express();
const PORT = 3000;

app.get('/health', (req: Request, res: Response) => {
  res.json({ status: 'ok' });
});

app.listen(PORT, () => {
  console.log(`Server listening on http://localhost:${PORT}`);
});

Step 4: Verification

Start the server using ts-node:

npx ts-node src/server.ts

In a second terminal, verify with curl:

curl http://localhost:3000/health

Expected Output:

{"status":"ok"}

Next Steps

  • Add a tsconfig.json using npx tsc --init.
  • Configure a production build script using tsc.

### Example 2: Ambiguous or Missing Input
**Input:**
```text
Write a tutorial about coding.

Output:

### Tutorial Generator: Halted - Ambiguous Topic

- **Status**: Halted

"Coding" is too broad for a step-by-step tutorial. Please specify:
1. The exact workflow or feature (e.g., "How to authenticate users with JWT in Python").
2. The framework or technology stack.
3. The reader's skill level.

Example 3: Expected Final Output

Output:

# How to Parse JSON in Python

Learn how to safely read and parse a JSON string using Python's standard library.

## Prerequisites
- Python >= 3.8

---

### Step 1: Write the Parsing Script
Create `parse_example.py`:

```python
import json

raw_data = '{"name": "Alice", "score": 95}'
parsed = json.loads(raw_data)

print(f"User: {parsed['name']}, Score: {parsed['score']}")

Verification

Run the script:

python3 parse_example.py

Expected Output:

User: Alice, Score: 95

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.

Reviews can't be read right now.

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.