update-specification
github/awesome-copilot
Update specification files for AI consumption based on new requirements or code changes.
What is update-specification?
This skill updates existing specification files to reflect new requirements or code changes, optimizing them for Generative AI understanding. Use it when your solution's requirements, constraints, or interfaces have evolved and need documentation refresh.
- Updates specification files in `/spec/` directory with AI-optimized formatting
- Ensures specifications follow structured markdown with clear sections: Purpose, Definitions, Requirements, Interfaces, Acceptance Criteria, Testing Strategy, Dependencies, and Examples
- Validates specifications are self-contained, unambiguous, and machine-readable
- Applies naming convention `[a-z0-9-]+.md` with descriptive prefixes (schema, tool, data, infrastructure, process, architecture, design)
- Maintains front matter with metadata: title, version, dates, owner, and tags
- Includes acceptance criteria in Given-When-Then format and test automation strategy
How to install update-specification
npx skills add https://github.com/github/awesome-copilot --skill update-specification- Existing specification file to update in `/spec/` directory
- Understanding of current requirements, constraints, or code changes that necessitate the update
How to use update-specification
- 1.Identify the specification file that needs updating in the `/spec/` directory
- 2.Gather new requirements, code changes, or constraint updates that should be reflected
- 3.Run the skill and provide the specification file path and details of what changed
- 4.Review the updated specification to ensure all sections are complete and accurate
- 5.Verify the specification follows the template structure with proper front matter and markdown formatting
- 6.Commit the updated specification file to version control
Use cases
- Update API specification when adding new endpoints or changing data contracts
- Refresh infrastructure specification after architectural changes or dependency updates
- Document process changes in specification format when workflow requirements evolve
- Maintain schema specifications when data models are modified or extended
- Update design specifications to reflect new constraints or guidelines discovered during implementation
- Development teams using AI-assisted coding (Claude Code, Cursor)
- Technical leads maintaining solution documentation
- Teams practicing specification-driven development
- Projects requiring clear machine-readable requirements for AI agents
update-specification FAQ
Specification files must be well-formed Markdown (.md) with YAML front matter containing title, version, dates, owner, and tags. Follow the provided template with sections for Purpose & Scope, Definitions, Requirements, Interfaces, Acceptance Criteria, Testing Strategy, Dependencies, Examples, and Validation Criteria.
All specification files must be stored in the `/spec/` directory and named using the convention `[a-z0-9-]+.md`, where the name is descriptive and starts with a high-level purpose prefix: schema, tool, data, infrastructure, process, architecture, or design.
Requirements should be explicitly listed with identifiers (REQ-001, SEC-001, CON-001, etc.) using bullet points or tables. Use precise, unambiguous language and distinguish between requirements, constraints, and guidelines. Include acceptance criteria in Given-When-Then format.
No. Specifications should focus on architectural and business dependencies rather than specific package implementations. For example, specify 'OAuth 2.0 authentication library' rather than 'Microsoft.AspNetCore.Authentication.JwtBearer v6.0.1', unless the version represents an architectural constraint.
AI-ready specifications use precise explicit language, structured formatting (headings, lists, tables), define all acronyms and domain-specific terms, avoid idioms and metaphors, include examples and edge cases, and are self-contained without relying on external context.
Full instructions (SKILL.md)
Source of truth, from github/awesome-copilot.
name: update-specification description: 'Update an existing specification file for the solution, optimized for Generative AI consumption based on new requirements or updates to any existing code.'
Update Specification
Your goal is to update the existing specification file ${file} based on new requirements or updates to any existing code.
The specification file must define the requirements, constraints, and interfaces for the solution components in a manner that is clear, unambiguous, and structured for effective use by Generative AIs. Follow established documentation standards and ensure the content is machine-readable and self-contained.
Best Practices for AI-Ready Specifications
- Use precise, explicit, and unambiguous language.
- Clearly distinguish between requirements, constraints, and recommendations.
- Use structured formatting (headings, lists, tables) for easy parsing.
- Avoid idioms, metaphors, or context-dependent references.
- Define all acronyms and domain-specific terms.
- Include examples and edge cases where applicable.
- Ensure the document is self-contained and does not rely on external context.
The specification should be saved in the /spec/ directory and named according to the following convention: [a-z0-9-]+.md, where the name should be descriptive of the specification's content and starting with the highlevel purpose, which is one of [schema, tool, data, infrastructure, process, architecture, or design].
The specification file must be formatted in well formed Markdown.
Specification files must follow the template below, ensuring that all sections are filled out appropriately. The front matter for the markdown should be structured correctly as per the example following:
---
title: [Concise Title Describing the Specification's Focus]
version: [Optional: e.g., 1.0, Date]
date_created: [YYYY-MM-DD]
last_updated: [Optional: YYYY-MM-DD]
owner: [Optional: Team/Individual responsible for this spec]
tags: [Optional: List of relevant tags or categories, e.g., `infrastructure`, `process`, `design`, `app` etc]
---
# Introduction
[A short concise introduction to the specification and the goal it is intended to achieve.]
## 1. Purpose & Scope
[Provide a clear, concise description of the specification's purpose and the scope of its application. State the intended audience and any assumptions.]
## 2. Definitions
[List and define all acronyms, abbreviations, and domain-specific terms used in this specification.]
## 3. Requirements, Constraints & Guidelines
[Explicitly list all requirements, constraints, rules, and guidelines. Use bullet points or tables for clarity.]
- **REQ-001**: Requirement 1
- **SEC-001**: Security Requirement 1
- **[3 LETTERS]-001**: Other Requirement 1
- **CON-001**: Constraint 1
- **GUD-001**: Guideline 1
- **PAT-001**: Pattern to follow 1
## 4. Interfaces & Data Contracts
[Describe the interfaces, APIs, data contracts, or integration points. Use tables or code blocks for schemas and examples.]
## 5. Acceptance Criteria
[Define clear, testable acceptance criteria for each requirement using Given-When-Then format where appropriate.]
- **AC-001**: Given [context], When [action], Then [expected outcome]
- **AC-002**: The system shall [specific behavior] when [condition]
- **AC-003**: [Additional acceptance criteria as needed]
## 6. Test Automation Strategy
[Define the testing approach, frameworks, and automation requirements.]
- **Test Levels**: Unit, Integration, End-to-End
- **Frameworks**: MSTest, FluentAssertions, Moq (for .NET applications)
- **Test Data Management**: [approach for test data creation and cleanup]
- **CI/CD Integration**: [automated testing in GitHub Actions pipelines]
- **Coverage Requirements**: [minimum code coverage thresholds]
- **Performance Testing**: [approach for load and performance testing]
## 7. Rationale & Context
[Explain the reasoning behind the requirements, constraints, and guidelines. Provide context for design decisions.]
## 8. Dependencies & External Integrations
[Define the external systems, services, and architectural dependencies required for this specification. Focus on **what** is needed rather than **how** it's implemented. Avoid specific package or library versions unless they represent architectural constraints.]
### External Systems
- **EXT-001**: [External system name] - [Purpose and integration type]
### Third-Party Services
- **SVC-001**: [Service name] - [Required capabilities and SLA requirements]
### Infrastructure Dependencies
- **INF-001**: [Infrastructure component] - [Requirements and constraints]
### Data Dependencies
- **DAT-001**: [External data source] - [Format, frequency, and access requirements]
### Technology Platform Dependencies
- **PLT-001**: [Platform/runtime requirement] - [Version constraints and rationale]
### Compliance Dependencies
- **COM-001**: [Regulatory or compliance requirement] - [Impact on implementation]
**Note**: This section should focus on architectural and business dependencies, not specific package implementations. For example, specify "OAuth 2.0 authentication library" rather than "Microsoft.AspNetCore.Authentication.JwtBearer v6.0.1".
## 9. Examples & Edge Cases
```code
// Code snippet or data example demonstrating the correct application of the guidelines, including edge cases
10. Validation Criteria
[List the criteria or tests that must be satisfied for compliance with this specification.]
11. Related Specifications / Further Reading
[Link to related spec 1] [Link to relevant external documentation]
Related skills
More from github/awesome-copilot and the wider catalog.

vscode-ext-commands
Guidelines for correctly naming, scoping, and placing commands in VS Code extensions.

vscode-ext-localization
Guidelines for correctly localizing every part of a VS Code extension, from package.json to source strings.

web-coder
Expert web development engineer with deep knowledge of HTML, CSS, JavaScript, APIs, HTTP, security, and web standards.

web-design-reviewer
Visually inspect websites and fix design issues directly in source code.

what-context-needed
Get Copilot to ask for the right files before it answers your question.

winapp-cli
Windows App Development CLI for MSIX packaging, signing, debugging, and UI automation across .NET, C++, Electron, Rust, Tauri, and Flutter.