Add tools for maximizing GitHub Copilot effectiveness through better
context management:
- Instructions: Guidelines for structuring code so Copilot understands it
- Agent: Context Architect - plans multi-file changes by mapping dependencies
- Prompts:
- context-map: Map all affected files before changes
- what-context-needed: Ask Copilot what files it needs
- refactor-plan: Create phased refactor plans with rollback steps
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Add 5 framework-specific collections with shared agent and prompt for generating production-ready applications from OpenAPI specifications:
- Java Spring Boot
- Python FastAPI
- Node.js NestJS
- C# .NET
- Go
Reuses existing framework instructions for consistency and best practices.
- 📝 New prompt for auditing iOS app code and metadata
- 🔍 Identifies rejection risks and optimization opportunities
- 📋 Provides structured recommendations for App Store compliance
Similar to c12041b which added outdated agent detection, this commit adds:
- Version comparison process for detecting outdated local assets
- Fetch remote versions step in the process workflow
- Updated icons reference with outdated status indicators
- Update handling sections for managing outdated assets
- Updated output table examples to show outdated status
- Add version comparison process to identify outdated local agents
- Introduce ⚠️ status icon for installed but outdated agents
- Add detailed comparison of remote vs local agent content
- Include update handling instructions for outdated agents
- Enhance process to fetch and compare remote versions
- Update output format to show outdated agents with specific differences
* Initial plan
* Add DevOps resources: agents, instructions, and prompt
* Replace redundant GitHub Actions instructions with expert agent
* Make DevOps resources more generic for easier maintenance
* Remove optional model field to align with repository conventions
* Reduce code examples to focus on principles and guidance
* Add DevOps Expert agent following infinity loop principle
---------
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: benjisho-aidome <218995725+benjisho-aidome@users.noreply.github.com>
Co-authored-by: Matt Soucoup <masoucou@microsoft.com>
* Migrating chat modes to agents now that's been released to stable
* Fixing collections
* Fixing names of agents
* Formatting
* name too long
* Escaping C# agent name
- Changed tool names from 'run_in_terminal' and 'get_terminal_output'
to 'runCommands/runInTerminal' and 'runCommands/getTerminalOutput'
for uniformity across prompt files.
Signed-off-by: D. Danchev <12420863+danchev@users.noreply.github.com>
* Add AI model recommendation prompt for Copilot integrations
Introduces a detailed prompt for recommending optimal AI models
based on `.chatmode.md` or `.prompt.md` file analysis. The prompt
outlines a workflow for task evaluation, model selection criteria,
and cost-efficiency considerations. It includes support for
subscription tiers, deprecated model migration, and advanced
features like Context7 integration.
This addition enhances the ability to automate and optimize AI
model recommendations, improving alignment with task complexity,
user priorities, and available tools.
* Running update script
---------
Co-authored-by: Aaron Powell <me@aaron-powell.com>
