Agent skill

Dev Guide Generator

by zebbern in zebbern/claude-code-guide

Generates complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting, and a final cheatsheet.

MITAuto-check: notesWriting & Content

Install Dev Guide Generator

skills CLI
$ npx skills add zebbern/claude-code-guide --skill dev-guide-generator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install zebbern/claude-code-guide dev-guide-generator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/zebbern/claude-code-guide.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/dev-guide-generator .claude/skills/dev-guide-generator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
dev-guide-generator
GitHub stars
4.6k
Token cost
~3.4k tokens
SKILL.md length
1,407 words
Files
2
Skills in repo
46
Repo updated
First seen
Licence
MIT

At a glance

Generates complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting, and a final cheatsheet.

  • Works in 8 steps: Topic Scoping & Audience Analysis → Prerequisites → Environment Setup → …
  • Requests to write a tutorial
  • SKILL.md covers Quick Start, SOP Workflow, Flow Control Rules and Use Cases
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Dev Guide Generator is an agent skill from zebbern/claude-code-guide. Generates complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting, and a final cheatsheet. Trigger on requests to write a tutorial, create a setup guide, organize steps for beginners, or keywords like step-by-step, quickstart, or how-to guide.

Its SKILL.md is about 3.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Writing & Content, covering Technical writing. The repository describes itself as: Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks from beginner to power user! The licence is MIT.

When your agent uses it

  • Requests to write a tutorial
  • Create a setup guide
  • Organize steps for beginners
  • Keywords like step-by-step

Example prompts

  • “Use the dev-guide-generator skill to generate complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting…”
  • “/dev-guide-generator”

Requirements

  • Node.js
  • Docker
  • A credential in YOUR_API_KEY

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Topic Scoping & Audience Analysis
  2. Prerequisites
  3. Environment Setup
  4. Core Steps
  5. Troubleshooting
  6. Advanced Topics
  7. Cheatsheet
  8. Document Assembly & Output

What it can do on your machine

Read from SKILL.md and the folder at commit 4698e3b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dev Guide Generator loads about 3.4k tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 1,407 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~77
When it runs · the whole SKILL.md, loaded when a task matches
~3.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteRuns commands with sudoSKILL.md:97
    sudo apt update && sudo apt install -y xxx

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zebbern/claude-code-guide at commit 4698e3b, republished under its MIT licence (© zebbern). 1,407 words, ~3,399 tokens.

Download SKILL.mdSave it as .claude/skills/dev-guide-generator/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
dev-guide-generator
description
Generates complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting, and a final cheatsheet. Trigger on requests to write a tutorial, create a setup guide, organize steps for beginners, or keywords like step-by-step, quickstart, or how-to guide.
license
MIT

Dev Guide Generator

One topic → complete technical tutorial: Through a structured SOP workflow, transform a technical topic into a comprehensive tutorial covering prerequisites, environment setup, core steps, common error troubleshooting, and advanced topics — all accompanied by a cheatsheet.

Quick Start

The user simply provides a technical topic or operational goal, and the Agent automatically generates a complete tutorial following this workflow:

User: Help me write a Docker beginner's tutorial
Agent: [Outputs complete technical tutorial + Cheatsheet following the SOP workflow]

SOP Workflow

Phase 1: Topic Scoping & Audience Analysis

Goal: Define the tutorial's technical subject, target audience, and scope boundaries.

Steps:

  1. Parse the topic: Identify the core technology, operational goals, and expected deliverables from the user's input
  2. Ask clarifying questions (up to 4 key questions):
    • What is the target audience's technical level? (Complete beginner / Some experience / Experienced developer)
    • What operating system will the reader be using? (macOS / Windows / Linux / Any)
    • What should the reader be able to do after completing the tutorial? (Specific deliverable)
    • Are there any version or tech stack constraints?
  3. If the user asks to skip clarification, proceed with these default assumptions:
    • Audience: Has basic programming experience but is unfamiliar with the topic technology
    • Environment: Cover both macOS and Linux (note Windows differences where necessary)
    • Goal: Be able to independently complete a minimal working example

Output: Tutorial metadata summary (topic, audience, objective, scope — no more than 150 words)


Phase 2: Prerequisites

Goal: List all knowledge and tools the reader needs before starting this tutorial, ensuring there are no knowledge gaps.

Steps:

  1. Dependency analysis:

    • List all technical concepts involved in this tutorial
    • For each concept, determine whether it should be "explained within the tutorial" or "assumed as prior knowledge"
    • Decision rule: If explaining it would digress more than 200 words from the main topic, classify it as a prerequisite
  2. Prerequisites checklist:

    • Categorize into "Must know" and "Nice to know" tiers

    • Attach a one-line explanation for each: "why you need it"

    • Format:

      **Must know**:
      - [Concept]: [Why you need it] (Recommended resource)
      
      **Nice to know**:
      - [Concept]: [What aspects of the tutorial it relates to]
  3. Self-check rules:

    • If prerequisites exceed 5 items, consider narrowing the tutorial scope or splitting into a series
    • Every prerequisite must have a publicly available learning resource

Output: Tiered prerequisites checklist


Phase 3: Environment Setup

Goal: Provide a reproducible environment configuration path so the reader is fully set up before starting the core steps.

Steps:

  1. Environment inventory: List all tools to install/configure with recommended versions

    • Format: Tool name Version requirement (e.g., >= x.y) | Purpose
    • Clearly distinguish "required" from "optional" installations
  2. Installation steps: Provide commands for each operating system

    • Precede each command with a one-line explanation of what it does

    • Use only officially recommended methods or mainstream package managers

    • Format:

      **macOS**:
      # Install xxx (via Homebrew)
      brew install xxx
      
      **Linux (Ubuntu/Debian)**:
      # Install xxx (via apt)
      sudo apt update && sudo apt install -y xxx
  3. Environment verification: Provide a verification command and expected output after each tool installation

    • Format:

      # Verify installation
      xxx --version
      # Expected output: xxx x.y.z
  4. Self-check rules:

    • All installation commands must come from official documentation or mainstream package managers — no third-party scripts
    • Never include real API keys, passwords, tokens, or other sensitive values
    • When configuration files are involved, use placeholders (e.g., YOUR_API_KEY) and explain how to obtain the real value

Output: OS-specific installation and configuration guide + verification commands


Phase 4: Core Steps

Goal: Walk the reader through the core operations in a progressive structure, where each step can be independently verified.

Steps:

  1. Step planning:

    • Break the entire operation into 5–10 steps (each focused on one sub-goal)
    • Order steps strictly by dependency
    • Each step includes: step number, title, and objective statement
  2. Step writing format:

    #### Step N: [Step Title]
    
    **Objective**: [What state is achieved after this step]
    
    **Actions**:
    [Code block or operational instructions]
    
    **Explanation**:
    - [Line-by-line or section-by-section explanation of key parts]
    
    **Verification**:
    [What command to run / what result to check to confirm success]
    Expected output: [Specific expected result]
  3. Writing guidelines:

    • Code blocks must specify the language (e.g., bash, python)
    • Placeholders use ALL_CAPS_WITH_UNDERSCORES format (e.g., YOUR_PROJECT_NAME) and are explained on first occurrence
    • Each code block should not exceed 30 lines; split and explain in sections if longer
    • Use relative file paths; state the project root directory at the beginning
    • Every step must end with a verification section
  4. Progressive complexity:

    • Steps 1–3: Minimal runnable example (Hello World level)
    • Middle steps: Gradually introduce real-world features
    • Final 1–2 steps: Combine everything into a complete example

Output: Numbered step list, each containing actions + explanation + verification


Phase 5: Troubleshooting

Goal: Anticipate problems the reader may encounter and provide a direct path from error message to solution.

Steps:

  1. Error collection: Based on the technical topic, list the 5–8 most common error scenarios

    • Sources: Environment misconfiguration, version incompatibilities, permission issues, typos, network problems, etc.
  2. Error entry format:

    **Error N: [Error message summary]**
    
    Full error message:
    [Actual error output]
    
    Cause: [One-sentence explanation of why this error occurs]
    
    Solution:
    [Specific fix commands or steps]
    
    Verify the fix:
    [What to run to confirm the issue is resolved]
  3. Writing guidelines:

    • Error messages must be real (do not fabricate error messages)
    • Solutions must be actionable — avoid vague advice like "check your configuration"
    • If an error has multiple possible causes, list them from most to least likely
    • For permission-related issues, explain why the permission is needed rather than jumping to sudo or chmod 777
  4. Self-check rules:

    • Solutions must not include operations that could create security risks (e.g., chmod 777, disabling firewalls)
    • Never advise the reader to disable security features to "fix" a problem

Output: Structured troubleshooting table


Show full SKILL.md (629 more words)Show less
Phase 6: Advanced Topics

Goal: Point readers who have completed the basics toward next steps, providing a learning path from beginner to advanced.

Steps:

  1. Advanced topic recommendations (3–5 directions):

    • For each direction, write a short paragraph: what it is, why it's worth learning, and what scenarios it applies to

    • Tag the difficulty level: Intermediate / Advanced

    • Format:

      **Direction N: [Topic Name]** | Difficulty: [Intermediate/Advanced]
      
      [Short paragraph]
      
      Recommended resources:
      - [Resource name] ([Type: documentation/book/course])
  2. Hands-on project suggestions:

    • Provide 2–3 small projects the reader can independently complete using what they learned
    • Each project includes: project name, one-sentence description, and relevant concepts
  3. Best practice tips (3–5 items):

    • Key differences between production and tutorial environments
    • Security considerations
    • Performance optimization directions

Output: Advanced learning roadmap + hands-on project suggestions + best practices


Phase 7: Cheatsheet

Goal: Distill the tutorial's essentials into a one-page quick reference for everyday use.

Steps:

  1. Cheatsheet structure:

    # [Technology Name] Cheatsheet
    
    ## Environment Info
    | Item | Command/Path |
    |------|--------------|
    | Install | `command` |
    | Version check | `command` |
    | Config file location | `path` |
    
    ## Common Commands
    | Action | Command | Description |
    |--------|---------|-------------|
    | xxx    | `xxx`   | xxx         |
    
    ## Common Code Snippets
    [Up to 5 frequently used code snippets, each no more than 10 lines]
    
    ## Quick Troubleshooting
    | Symptom | Possible Cause | Quick Fix |
    |---------|---------------|-----------|
    | xxx     | xxx           | `xxx`     |
  2. Writing guidelines:

    • Total cheatsheet length should fit on 2 printed A4 pages
    • Commands must be complete and ready to copy-paste
    • No explanatory prose — only "what to do → how to do it" mappings
    • Order items by frequency of use, from most to least common

Output: One-page cheatsheet


Phase 8: Document Assembly & Output

Goal: Assemble the outputs from the previous seven phases into a complete tutorial document.

Tutorial document template:

markdown
# [Technical Topic] Complete Tutorial

> Last updated: [Current date] | Applicable version: [Version number]
> Difficulty: [Beginner/Intermediate/Advanced] | Estimated time: [N hours/minutes]

## Tutorial Overview

[Phase 1 metadata summary — what the reader will be able to do after completion]

## 1. Prerequisites

[Phase 2 prerequisites checklist]

## 2. Environment Setup

[Phase 3 installation and configuration guide]

## 3. Core Steps

[Phase 4 numbered step list]

## 4. Troubleshooting

[Phase 5 troubleshooting table]

## 5. Advanced Topics

[Phase 6 advanced roadmap and hands-on projects]

## 6. Cheatsheet

[Phase 7 cheatsheet]

## Appendix

- Glossary (if domain-specific terminology is used, list in a table: Term | Definition)
- Reference links (official documentation, community resources, etc.)

Document output requirements:

  • All code blocks must specify the language
  • All commands must be directly copy-pasteable (no line numbers, prompts, or other noise)
  • All placeholders use the YOUR_XXX format and are explained on first occurrence
  • Configuration files must not contain real keys or tokens
  • Dates must use the actual current date

Flow Control Rules

Interaction Mode Selection

Choose the mode based on the level of detail in the user's input:

User InputModeBehavior
Just a technology name (e.g., "Docker tutorial")Guided modeExecute Phase 1 questions, wait for answers before continuing
Specific goal (e.g., "Deploy a Node.js app with Docker")Semi-auto modeAsk 1–2 key questions while simultaneously planning the steps
Detailed description (includes audience, environment, goal)Full-auto modeStart output directly from Phase 2
User says "just write it / don't ask"Quick modeOutput the complete tutorial based on default assumptions
Quality Checklist

Before outputting the final tutorial, check each item:

  • Prerequisites checklist is complete with no knowledge gaps
  • Every environment setup command has a verification step
  • Every core step includes "actions + explanation + verification"
  • Step dependencies are correct (no step uses a tool that hasn't been installed yet)
  • At least 5 common errors with specific, actionable solutions
  • At least 3 advanced directions with resource recommendations
  • Cheatsheet is self-contained with common commands and troubleshooting info
  • All code blocks specify the language
  • No hardcoded keys, tokens, or personal paths
  • No suggestions that could create security vulnerabilities (e.g., chmod 777)
  • No dependency on paid APIs or subscription-only tools (unless the tool itself is the tutorial subject)
Iterative Refinement

If the user provides feedback on the tutorial:

  1. Identify which Phase the feedback relates to
  2. Re-execute from that Phase
  3. Cascade updates to all downstream content (e.g., an environment change must propagate to subsequent steps and the Cheatsheet)
  4. Maintain step numbering continuity

Use Cases

This tutorial generator is suitable for the following types of technical tutorials:

  • Tool usage: Tutorials for tools like Git, Docker, Kubernetes, Vim, etc.
  • Environment setup: Development environments, CI/CD pipelines, server configuration, etc.
  • Programming introductions: Language primers, framework quickstarts, library usage, etc.
  • Operations manuals: Deployment, monitoring, logging, backup and recovery, etc.
  • Data processing: Database operations, ETL workflows, data analysis tool usage, etc.

© zebbern, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in skills/dev-guide-generator of zebbern/claude-code-guide.

  • SKILL.md
  • LICENSE

Open the folder on GitHubat commit 4698e3b

Compare with similar skills

Dev Guide Generator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Dev Guide Generator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Dev Guide Generator this skillzebbern/claude-code-guide4.6k—~3.4kAutomated safety check: NotesMIT
JavaScript Concept Fact Checkerleonardomso/33-js-concepts67k1 repos~5kAutomated safety check: PassMIT
Beads Documentation Style Guidegastownhall/beads28k—~3.2kAutomated safety check: PassMIT
JavaScript Concept Page Workflowleonardomso/33-js-concepts67k—~3.9kAutomated safety check: PassMIT
JS Concept Resource Curatorleonardomso/33-js-concepts67k—~4.9kAutomated safety check: PassMIT
Technical Writing Standardcursor/plugins10k10 repos~2.4kAutomated safety check: PassNone

Similar skills

  • JavaScript Concept Fact Checker

    leonardomso/33-js-concepts

    Verifies the technical accuracy of JavaScript concept pages by checking code examples, MDN and ECMAScript claims and external links through a five-phase method.

    67k GitHub starsUsed in 1 repo~5k tokens
    Writing & ContentAuto-check passed
  • Sets the house style for the beads user docs: the canonical concept model, required terminology, prose and diagram conventions, and checks before docs work is done.

    28k GitHub stars~3.2k tokensUpdated today
    Writing & ContentAuto-check passed
  • JavaScript Concept Page Workflow

    leonardomso/33-js-concepts

    Orchestrates five skills to produce a complete JavaScript concept documentation page, from resource curation through writing, tests, fact-checking and SEO.

    67k GitHub stars~3.9k tokensUpdated 26 days ago
    Writing & ContentAuto-check passed
  • JS Concept Resource Curator

    leonardomso/33-js-concepts

    Finds, vets, writes up and maintains external articles, videos and courses for JavaScript concept pages, including audits for broken and outdated links.

    67k GitHub stars~4.9k tokensUpdated 26 days ago
    Writing & ContentAuto-check passed
  • Official

    Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.

    10k GitHub starsUsed in 10 repos~2.4k tokens
    Writing & ContentAuto-check passed
  • Writing Docs

    nukeop/nuclear

    A skill your agent uses when writing or editing documentation in packages/docs.

    19k GitHub stars~907 tokensUpdated yesterday
    Writing & ContentAuto-check passed

More from zebbern/claude-code-guide

All 46 skills in this repo
  • Localization Toolkit

    zebbern/claude-code-guide

    This skill should be used when setting up, auditing, or enforcing internationalization/localization in UI codebases (React/TS, i18next or similar, JSON locales), including installing/configuring the…

    4.6k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed
  • Audit Flow

    zebbern/claude-code-guide

    Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export.

    4.6k GitHub stars~4.2k tokensUpdated today
    Auto-check passed
  • Chart Image

    zebbern/claude-code-guide

    Generate publication-quality PNG chart images from data, supporting line, bar, area, candlestick, pie, and heatmap charts.

    4.6k GitHub stars~2.7k tokensUpdated today
    Auto-check passed
  • Code To Diagram

    zebbern/claude-code-guide

    Analyze codebases and automatically generate architecture diagrams, flowcharts, and org charts.

    4.6k GitHub stars~972 tokensUpdated today
    Auto-check passed
  • Code Vuln Audit

    zebbern/claude-code-guide

    Scan code for security issues: dependency vulnerabilities (npm/pip audit), secret leaks (regex and entropy analysis), and OWASP anti-patterns like SQL injection, XSS, or command injection.

    4.6k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Data Viz Renderer

    zebbern/claude-code-guide

    Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards.

    4.6k GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Questions about Dev Guide Generator

What does Dev Guide Generator do?

Generates complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting, and a final cheatsheet. Dev Guide Generator is an agent skill from zebbern/claude-code-guide. Generates complete technical tutorials from prerequisites and environment setup to core steps, troubleshooting, and a final cheatsheet.

When should I use Dev Guide Generator?

Dev Guide Generator fits situations like: requests to write a tutorial; create a setup guide; organize steps for beginners; keywords like step-by-step.

How do I install Dev Guide Generator in Claude Code?

Run `npx skills add zebbern/claude-code-guide --skill dev-guide-generator -a claude-code`. Or copy the skill folder (skills/dev-guide-generator in zebbern/claude-code-guide) into .claude/skills/dev-guide-generator in your project. Claude Code loads it when a task matches its description.

How do I install Dev Guide Generator in Codex?

Run `npx skills add zebbern/claude-code-guide --skill dev-guide-generator -a codex`. Or copy the skill folder (skills/dev-guide-generator in zebbern/claude-code-guide) into .agents/skills/dev-guide-generator in your project. Codex loads it when a task matches its description.

Can I use Dev Guide Generator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zebbern/claude-code-guide --skill dev-guide-generator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dev-guide-generator, .gemini/skills/dev-guide-generator, .github/skills/dev-guide-generator and .opencode/skills/dev-guide-generator in your project.

What does Dev Guide Generator need to run?

SKILL.md names no scripts, command-line tools or credentials: Dev Guide Generator is instructions for the agent only. Our summary lists: Node.js; Docker; A credential in YOUR_API_KEY.

Does Dev Guide Generator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Dev Guide Generator safe to install?

Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Dev Guide Generator use?

Dev Guide Generator is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Dev Guide Generator use?

About 3.4k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Dev Guide Generator?

Skills that share tags, products or a category with Dev Guide Generator: JavaScript Concept Fact Checker (leonardomso/33-js-concepts, 67k stars), Beads Documentation Style Guide (gastownhall/beads, 28k stars), JavaScript Concept Page Workflow (leonardomso/33-js-concepts, 67k stars) and JS Concept Resource Curator (leonardomso/33-js-concepts, 67k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Dev Guide Generator?

zebbern (a GitHub user) maintains it in zebbern/claude-code-guide, which has 4,648 GitHub stars. The repository holds 46 skills in this directory. The repository was last updated on October 7, 2026.

Source: zebbern/claude-code-guide on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.