Use when writing or creating new Standard Operating Procedures (SOPs) for AI agents. Covers effective SOP writing, clarity principles, and actionable instruction design.
Limited to specific tools
Additional assets for this skill
This skill is limited to using the following tools:
name: sop-authoring description: Use when writing or creating new Standard Operating Procedures (SOPs) for AI agents. Covers effective SOP writing, clarity principles, and actionable instruction design. allowed-tools:
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.
Use SOPs when you need consistent, repeatable execution of multi-step processes.
DO:
DON'T:
# {Action Verb} {Outcome} SOP
## Overview
{1-2 sentences describing what this SOP accomplishes and when to use it}
Good Titles:
Poor Titles:
Sequential Steps:
## 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:
## 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
Define parameters that make SOPs reusable:
## Parameters
- **Repository Path**: {repository_path}
- **Output Format**: {output_format} (markdown, json, html)
- **Verbosity Level**: {verbosity} (concise, detailed, comprehensive)
Usage in Steps:
1. Navigate to {repository_path}
2. Generate documentation in {output_format} format
3. Use {verbosity} level of detail
Include explicit success criteria:
## Success Criteria
- [ ] All source files are documented
- [ ] README.md exists with setup instructions
- [ ] API documentation is complete
- [ ] Examples are tested and working
# 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
# 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
# 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
## 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
After each major step:
- Verify output meets quality criteria
- Check for errors or warnings
- Confirm results match expectations
## Process
For each {item} in {collection}:
1. Perform action on {item}
2. Validate result
3. Continue to next {item}
Avoid These Common Mistakes:
Overly General Instructions
Missing Context
npm test and verify all tests pass"Ambiguous Success Criteria
Hidden Assumptions
Mixing Multiple Workflows