Sop Authoring logo

Sop Authoring

Organization
zenobi-us
sop-authoring

Use when writing or creating new Standard Operating Procedures (SOPs) for AI agents. Covers effective SOP writing, clarity principles, and actionable instruction design.

Overview

Publisherzenobi-us
Repositorydotfiles
Skill namesop-authoring
Stars
67
Forks
6
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zenobi-us on GitHub. Read the source before you install it.

Installation

Install the Sop Authoring AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zenobi-us/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/files/devtools/agent/bundles/agent-core/skills/sop/sop-authoring .claude/skills/sop-authoring
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sop Authoring in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sop Authoring on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sop Authoring is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

SOP Authoring

Effective Standard Operating Procedures (SOPs) transform complex workflows into reusable, deterministic instructions for AI agents. This skill covers the principles and practices for writing clear, actionable SOPs.

Key Concepts

What Makes a Good SOP

  1. Single Responsibility: Each SOP addresses one specific workflow or task
  2. Deterministic: Same inputs produce same outputs
  3. Actionable: Every step is concrete and executable
  4. Parameterized: Variables enable reuse across contexts
  5. Self-Contained: Minimal external dependencies

SOP vs. General Documentation

  • SOPs: Prescriptive workflows with specific steps
  • Documentation: Descriptive reference material
  • Guides: Educational content with explanations
  • Tutorials: Step-by-step learning experiences

Use SOPs when you need consistent, repeatable execution of multi-step processes.

Best Practices

Writing Clear Instructions

DO:

  • Use active voice and imperative mood
  • Start steps with action verbs (analyze, generate, validate)
  • Be specific about expected outcomes
  • Include success criteria for each step
  • Use numbered lists for sequential steps
  • Use bullet points for unordered items

DON'T:

  • Use passive voice ("should be done" → "do this")
  • Include vague instructions ("improve the code")
  • Mix procedural and reference content
  • Assume implicit knowledge without stating it

Title and Description

markdown
# {Action Verb} {Outcome} SOP

## Overview
{1-2 sentences describing what this SOP accomplishes and when to use it}

Good Titles:

  • "Generate Codebase Documentation"
  • "Implement Feature Using TDD"
  • "Review Pull Request for Security"

Poor Titles:

  • "Documentation" (too vague)
  • "How to Maybe Improve Code Quality" (uncertain)
  • "The Complete Guide to Everything" (too broad)

Structuring Steps

Sequential Steps:

markdown
## Steps

1. Analyze the codebase structure
   - Identify main entry points
   - Map directory organization
   - Document key dependencies

2. Extract architectural patterns
   - Identify design patterns in use
   - Document data flow
   - Note component relationships

3. Generate documentation
   - Create README.md with overview
   - Document API interfaces
   - Add setup instructions

Conditional Logic:

markdown
## Steps

1. Check if tests exist
   - If tests exist: Run existing test suite
   - If no tests: Create test structure first

2. Implement feature based on test results
   - If tests pass: Add new functionality
   - If tests fail: Fix failing tests before proceeding

Parameters

Define parameters that make SOPs reusable:

markdown
## Parameters

- **Repository Path**: {repository_path}
- **Output Format**: {output_format} (markdown, json, html)
- **Verbosity Level**: {verbosity} (concise, detailed, comprehensive)

Usage in Steps:

markdown
1. Navigate to {repository_path}
2. Generate documentation in {output_format} format
3. Use {verbosity} level of detail

Success Criteria

Include explicit success criteria:

markdown
## Success Criteria

- [ ] All source files are documented
- [ ] README.md exists with setup instructions
- [ ] API documentation is complete
- [ ] Examples are tested and working

Examples

Example 1: Code Review SOP

markdown
# Review Code Changes for Quality

## Overview
Systematically review code changes for quality, maintainability, and adherence to project standards.

## Parameters

- **Pull Request URL**: {pr_url}
- **Review Depth**: {depth} (quick, standard, thorough)

## Steps

1. Fetch pull request details from {pr_url}
   - Read PR description and context
   - Identify changed files
   - Note breaking changes

2. Review code quality
   - Check for code smells
   - Verify error handling
   - Assess test coverage
   - Validate documentation updates

3. Check architectural consistency
   - Ensure patterns match existing code
   - Verify separation of concerns
   - Review dependency additions

4. Generate review feedback
   - List issues by severity (critical, major, minor)
   - Suggest specific improvements
   - Highlight positive changes

## Success Criteria

- [ ] All critical issues identified
- [ ] Feedback is specific and actionable
- [ ] Code style checked against project standards
- [ ] Security implications reviewed

Example 2: Feature Implementation SOP

markdown
# Implement Feature Using Test-Driven Development

## Overview
Implement new feature following TDD red-green-refactor cycle with comprehensive test coverage.

## Parameters

- **Feature Description**: {feature_description}
- **Test Framework**: {test_framework}

## Steps

1. Create failing test (RED)
   - Write test that describes desired behavior
   - Run test to confirm it fails
   - Verify failure message is correct

2. Implement minimal code (GREEN)
   - Write simplest code to pass the test
   - Avoid premature optimization
   - Run test to confirm it passes

3. Refactor (REFACTOR)
   - Improve code structure
   - Extract common patterns
   - Run tests to ensure they still pass

4. Repeat for each requirement
   - Break feature into small increments
   - Follow red-green-refactor for each
   - Commit after each complete cycle

## Success Criteria

- [ ] All tests pass
- [ ] Test coverage ≥ 80%
- [ ] No code duplication
- [ ] Feature meets requirements

Example 3: Documentation Generation SOP

markdown
# Generate Comprehensive Codebase Documentation

## Overview
Analyze codebase and generate comprehensive documentation including architecture overview, API reference, and setup instructions.

## Parameters

- **Repository Path**: {repository_path}
- **Documentation Format**: {format} (markdown, html, pdf)
- **Include Examples**: {include_examples} (yes, no)

## Steps

1. Analyze repository structure
   - Identify programming languages
   - Map directory organization
   - Locate configuration files
   - Find existing documentation

2. Extract architectural information
   - Identify main entry points
   - Document data flow
   - Map component dependencies
   - Note design patterns

3. Document public APIs
   - List all public functions/methods
   - Extract parameter types
   - Document return values
   - Include usage examples if {include_examples} is yes

4. Generate setup instructions
   - List prerequisites
   - Document installation steps
   - Provide configuration examples
   - Include troubleshooting section

5. Create documentation files
   - Generate README.md with overview
   - Create API.md with interface documentation
   - Add CONTRIBUTING.md if project accepts contributions
   - Format output as {format}

## Success Criteria

- [ ] Documentation covers all public APIs
- [ ] Setup instructions are complete
- [ ] Architecture is clearly explained
- [ ] Examples are tested and accurate

Common Patterns

Error Handling

markdown
## Error Handling

If any step fails:
1. Document the failure reason
2. Provide troubleshooting steps
3. Suggest alternative approaches
4. Do NOT proceed to next step

Validation Steps

markdown
## Validation

After each major step:
- Verify output meets quality criteria
- Check for errors or warnings
- Confirm results match expectations

Iterative Processes

markdown
## Process

For each {item} in {collection}:
1. Perform action on {item}
2. Validate result
3. Continue to next {item}

Anti-Patterns

Avoid These Common Mistakes:

  1. Overly General Instructions

    • ❌ "Improve the code quality"
    • ✅ "Run linter and fix all errors, then remove code duplication"
  2. Missing Context

    • ❌ "Run the tests"
    • ✅ "Run test suite using npm test and verify all tests pass"
  3. Ambiguous Success Criteria

    • ❌ "Code should be good"
    • ✅ "Code passes all linter checks and has no security vulnerabilities"
  4. Hidden Assumptions

    • ❌ Assuming tools are installed
    • ✅ Explicitly list prerequisites
  5. Mixing Multiple Workflows

    • ❌ Combining testing, deployment, and monitoring in one SOP
    • ✅ Create separate SOPs that can be composed

Related Skills

  • sop-structure: Learn how to organize SOP sections
  • sop-rfc2119: Use RFC 2119 keywords for precise requirements
  • sop-maintenance: Keep SOPs up to date and relevant

Frequently asked questions

What does the Sop Authoring AI skill do?

Use when writing or creating new Standard Operating Procedures (SOPs) for AI agents. Covers effective SOP writing, clarity principles, and actionable instruction design.

Why use Sop Authoring on TypingMind?

Because you install it once and use it with any model. Sop Authoring is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sop Authoring in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zenobi-us/dotfiles/tree/master/files/devtools/agent/bundles/agent-core/skills/sop/sop-authoring. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Sop Authoring?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sop Authoring?

As many as you like. As long as a model supports skills, you can use Sop Authoring with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sop Authoring AI skill free?

Yes. It is published on GitHub by zenobi-us under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇