- Add 150+ line prompt file for AI prompt engineering safety review and improvement
- Include systematic analysis framework covering safety, bias, security, and effectiveness
- Provide structured output format with detailed assessment criteria
- Include safety guidelines, testing recommendations, and educational insights
- Complement the existing AI prompt engineering safety best practices instruction
- Follow repository guidelines and best practices for prompt creation
This prompt enables developers to systematically review and improve prompts for safety, bias mitigation, security, and responsible AI usage.
- Re-run update-readme.js to ensure only the correct, original description for prompt-engineer.chatmode.md is present
- Remove any duplicate or outdated descriptions from previous comprehensive version
- README is now fully in sync with the restored chat mode and current repo state
- Restore the original prompt-engineer.chatmode.md from upstream/main
- Remove overwritten comprehensive version to avoid duplication and conflict
- Ensure only the official, simple prompt engineer chat mode is present
All advanced prompt engineering best practices are now in the new instruction file only.
- Add 868-line comprehensive instruction file covering prompt engineering fundamentals
- Include safety frameworks, bias mitigation, security best practices, and responsible AI usage
- Provide detailed templates, checklists, and testing methodologies
- Cover anti-patterns, prompt injection prevention, and ethical considerations
- Add educational content on prompt patterns, validation techniques, and documentation
- Include practical examples and real-world scenarios for developers
- Rename file to avoid conflict with existing prompt-engineer chat mode
- Update README with new instruction file
This instruction provides developers with industry-standard best practices for creating safe, effective, and responsible AI prompts for Copilot and other LLMs.
- Add 868-line instruction file covering prompt engineering fundamentals, safety, bias mitigation, security, and responsible AI usage
- Add 527-line expert chat mode for prompt analysis and improvement with systematic evaluation frameworks
- Include detailed templates, checklists, examples, and educational resources
- Follow industry best practices from Microsoft, OpenAI, and Google AI principles
- Implement comprehensive safety assessment frameworks and bias detection tools
- Add advanced techniques: prompt chaining, templates, versioning, and testing frameworks
- Provide extensive references to official guidelines, research papers, and community resources
- Strictly comply with project guidelines (CONTRIBUTING.md, SECURITY.md, SUPPORT.md)
Total: 1,395 lines of professional-grade prompt engineering guidance
Refactors the frontmatter parsing logic in the README update script.
Removes redundant checks and simplifies the state management for
identifying frontmatter sections, improving code readability and
maintainability.
* Refine 4.1 Beast Mode instructions and tools
Updated the 4.1 Beast Mode chat mode to enhance clarity and detail in the instructions. Removed the tools list and added more comprehensive guidelines for problem-solving, including steps for fetching URLs and conducting internet research. Improved communication guidelines to ensure concise user interactions.
* Update chatmodes/4.1-Beast.chatmode.md
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update chatmodes/4.1-Beast.chatmode.md
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update chatmodes/4.1-Beast.chatmode.md
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Rename 4.1 Beast Mode to 4.1 Beast Mode v3
Updated the chat mode title from "4.1 Beast Mode" to "4.1 Beast Mode v3" in the README.md to reflect the latest version of the custom prompt for GitHub Copilot.
* Rename 4.1 Beast Mode in README.md
Updated the title of the 4.1 Beast Mode chat mode in the README to remove the version suffix, ensuring consistency in naming conventions across documentation.
---------
Co-authored-by: Aaron Powell <me@aaron-powell.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Add WG chatmodes for clean code and security
* Update readme with the script
* Replace the front matter description with single quotes
* Remove yarn lock file
* Remove chatmodes custom header metadata
* Update README file from latest changes
* feat: add Playwright test generation instructions and best practices
* feat: add Playwright test generation instructions and related prompts
* fix: standardize formatting of description and applyTo fields in Playwright instructions
* fix: remove files not ready for submitting from README
---------
Co-authored-by: Aaron Powell <me@aaron-powell.com>
* Add prompts for .NET best practices, design pattern review, and GitHub Copilot suggestions
- Introduced a comprehensive prompt for ensuring .NET/C# code adheres to best practices, covering documentation, design patterns, dependency injection, resource management, async patterns, testing standards, configuration, AI integration, error handling, performance, security, and code quality.
- Added a prompt for reviewing C#/.NET code for design pattern implementation, providing a checklist for required patterns, architecture, best practices, SOLID principles, performance, maintainability, testability, security, documentation, code clarity, and clean code.
- Created prompts for suggesting relevant GitHub Copilot chatmodes and prompts based on the current repository context, including a structured process for fetching available chatmodes/prompts, scanning local files, and presenting options with rationale.
- Developed a prompt for updating Azure Verified Modules (AVM) in Bicep files, detailing the process for scanning, checking for updates, validating, and handling breaking changes.
- Implemented a prompt for updating implementation plans with new requirements, ensuring machine-readable output and adherence to a strict template.
- Added a prompt for updating the llms.txt file to reflect changes in documentation or specifications, focusing on compliance with the llmstxt specification.
- Created a prompt for updating markdown file indices with files from specified folders, including options for table structures and update strategies.
- Developed a prompt for updating object-oriented component documentation, following industry best practices and ensuring alignment with current implementations.
- Added a prompt for updating specification files, emphasizing clarity, structure, and compliance with established documentation standards.
* CHANGE: Update implementation plan prompt formatting
- Renamed prompt title for clarity.
- Added spacing for improved readability.
- Enhanced structure to ensure compliance with template validation rules.
* CHANGE: Fix typo in .NET best practices prompt
- Corrected "soltion" to "solution" in the prompt description.
* Add Spring Boot Java project prompt with setup instructions and configurations
* Add prompt for creating Spring Boot Kotlin project skeleton
---------
Co-authored-by: Vincent Huang iMac <vincent.huang@opennet.tw>
* Adds prompt engineering chat mode
Introduces a new chat mode to refine user-provided prompts, leveraging OpenAI prompt engineering techniques.
This mode helps improve prompts by analyzing their structure, complexity, and specificity,
and then suggesting improvements and providing a refined prompt as output.
It is intended to help generate better and more complete prompts based on user input.
* fix: Correct filename casing for Prompt Engineering Chat Mode in README
* feat: Add Prompt Engineer chat mode to README
* Update chatmodes/prompt-engineer.chatmode.md
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: Add missing front matter to prompt engineer chat mode documentation
* fix: Update description for Prompt Engineer chat mode to include OpenAI's techniques
* Updates prompt engineer chat mode description
Improves the description of the Prompt Engineer chat mode to clarify its purpose: analyzing and improving user-provided prompts based on established prompt engineering principles. The updated description reflects the mode's behavior of treating all user input as prompts and providing detailed analyses along with enhanced versions.
* Adds Prompt Engineer chat mode
Introduces a new chat mode specialized in analyzing and improving prompts.
This mode treats every user input as a prompt, providing a detailed analysis and generating an improved version, enhancing prompt engineering workflows.
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Adding badges
* Adding links to easy-install into vscode/insiders
This does mean that the layout of the readme needs a change, moving to a table layout so that we keep better alighnment
* handing different types
* Using the vscode.dev redirect
* wrong link - bad copilot
* handler should be instructions not instruction
* feat: Add security and OWASP instructions
This adds a new instruction file for secure coding practices based on the OWASP Top 10 to guide GitHub Copilot in generating more secure code.
* fix: add YAML front matter to security instructions and correct README link casing
* chore: update README.md after running update-readme.js
* feat: add the most comprehensive, practical, and engineer-authored performance optimization instructions. Covers frontend, backend, and database best practices with actionable guidance, scenario-based checklists, troubleshooting, and pro tips. Updates README.md to include this new resource.
* Apply suggestion from @aaronpowell
* Apply suggestion from @aaronpowell
---------
Co-authored-by: Aaron Powell <me@aaron-powell.com>
* feat: ✨ Add comprehensive Go development instructions
- Introduced a detailed guide for writing Go code adhering to idiomatic practices.
- Covers general instructions, naming conventions, code style, error handling, and security best practices.
- References established resources like Effective Go and Google's Go Style Guide.
* feat: ✨ Add Go development instructions
- Introduced guidelines for writing Go code that adhere to idiomatic Go practices and community standards.
* feat: Add security and OWASP instructions
This adds a new instruction file for secure coding practices based on the OWASP Top 10 to guide GitHub Copilot in generating more secure code.
* fix: add YAML front matter to security instructions and correct README link casing
* chore: update README.md after running update-readme.js
* Fixing line endings and removing dead code
* Missing descriptions due to line endings
* Enforcing that the line endings should be LF
* Potential fix for code scanning alert no. 18: Workflow does not contain permissions
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Fixing readme generator
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
* Delete outdated development instructions for Next.js + Tailwind and Python; add comprehensive guidelines for PostgreSQL DBA, Angular, ASP.NET REST APIs, Azure Functions with TypeScript, Bicep, Blazor, CMake with vcpkg, C#, .NET MAUI, GenAIScript, Terraform for Azure, localization, and markdown standards.
* Update documentation and prompts for consistency and clarity
- Standardized description formatting in various markdown files to use single quotes.
- Added error handling utility in update-readme.js for safer file operations.
- Improved title extraction logic in update-readme.js to handle frontmatter more robustly.
- Updated chat modes section in README to reflect new emoji and sorted chat mode links.
- Cleaned up various instruction files for better readability and consistency.
- Ensured all markdown files end with a newline for better compatibility with version control.
* Remove standardize-frontmatter.js script
* Add usage instructions for creating and switching chat modes in README.md
* Update README.md generation script to enhance instructions and usage details for custom chat modes
* Update README.md and update-readme.js for improved instruction clarity and consistency
* Refactor README.md links and update readme script for improved clarity and consistency in instructions
* Update README.md and update-readme.js for improved instruction clarity and consistency
* Changing from a patch to regen approach for the readme
* Bit more cleanup for how to show things in the readme
* Adding missing description
* Another missing description
---------
Co-authored-by: Aaron Powell <me@aaron-powell.com>
