Fixes#503.
When running `npm start` the README.skills.md file will be updated to
include any newly-added skills. This includes the name and description
from the skill's frontmatter, but also a list of assets in the skill--
that is, files other than SKILL.md.
However, the code in yaml-parser.mjs to enumerate the asset files only
looks in the immediate skill directory, not any subdirectories. Those
files will be missing from README.skills.md.
Here we update yaml-parser.mjs to recurse through the subdirectories as
well.
- Replace static github-mcp-registry.json with live API calls
- Fetch from https://api.mcp.github.com/v0.1/servers/ with pagination support
- Extract displayName from GitHub metadata for better matching
- Implement smart matching logic:
* Case-insensitive comparison
* Match against both displayName and full name
* Strip common suffixes like -mcp-server for pattern matching
- Make build process async to support API calls
- Cache registry data to only hit API once per build run
- Remove obsolete github-mcp-registry.json file
Benefits:
- No more manual updates to registry data
- Always uses latest MCP registry information
- Improved server name matching resilience
- Successfully loads all 54 servers from registry
* Adding modernization agent
This is a Modernization Agent. It will first understand the repository it will work on, then create comprehensive suggestions by asking the developer at each main step, like choosing the target tech stack or architecture.
* Update README.agents.md for modernization agent
* Update README.agents.md
* Fix modernization.agent.md yaml format
* Revise modernization agent documentation and tools
Updated agent documentation to reflect changes in model name, tools, and workflow details. Enhanced clarity on analysis phases, documentation requirements, and implementation planning.
* Refactor modernization agent documentation
Updated the title and improved formatting for clarity.
* Update Modernization Agent description in README
* add update-docs-on-code-change instructions
* Apply suggestions from code review
Modified one of the suggestions, clarifying the terms and instruction file configuration. If possible look over and see if another edit is needed.
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Add Software Engineering Team collection with 7 specialized agents
Adds a complete Software Engineering Team collection with 7 standalone
agents covering the full development lifecycle, based on learnings from
The AI-Native Engineering Flow experiments.
New Agents (all prefixed with 'se-' for collection identification):
- se-ux-ui-designer: Jobs-to-be-Done analysis, user journey mapping,
and Figma-ready UX research artifacts
- se-technical-writer: Creates technical documentation, blogs, and tutorials
- se-gitops-ci-specialist: CI/CD pipeline debugging and GitOps workflows
- se-product-manager-advisor: GitHub issue creation and product guidance
- se-responsible-ai-code: Bias testing, accessibility, and ethical AI
- se-system-architecture-reviewer: Architecture reviews with Well-Architected
- se-security-reviewer: OWASP Top 10/LLM/ML security and Zero Trust
Key Features:
- Each agent is completely standalone (no cross-dependencies)
- Concise display names for GitHub Copilot dropdown ("SE: [Role]")
- Fills gaps in awesome-copilot (UX design, content creation, CI/CD debugging)
- Enterprise patterns: OWASP, Zero Trust, WCAG, Well-Architected Framework
Collection manifest, auto-generated docs, and all agents follow
awesome-copilot conventions.
Source: https://github.com/niksacdev/engineering-team-agents
Learnings: https://medium.com/data-science-at-microsoft/the-ai-native-engineering-flow-5de5ffd7d877
* Fix Copilot review comments: table formatting and code block syntax
- Fix table formatting in docs/README.collections.md by converting multi-line
Software Engineering Team entry to single line
- Fix code block language in se-gitops-ci-specialist.agent.md from yaml to json
for package.json example (line 41-51)
- Change comment syntax from # to // to match JSON conventions
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix model field capitalization to match GitHub Copilot convention
- Change all agents from 'model: gpt-5' to 'model: GPT-5' (uppercase)
- Aligns with existing GPT-5 agents in the repo (blueprint-mode, gpt-5-beast-mode)
- Addresses Copilot reviewer feedback on consistency
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add ADR and User Guide templates to Technical Writer agent
- Add Architecture Decision Records (ADR) template following Michael Nygard format
- Add User Guide template with task-oriented structure
- Include references to external best practices (ADR.github.io, Write the Docs)
- Update Specialized Focus Areas to reference new templates
- Keep templates concise without bloating agent definition
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix inconsistent formatting: DevOps/CI-CD to DevOps/CI/CD
- Change "DevOps/CI-CD" (hyphen) to "DevOps/CI/CD" (slash) for consistency
- Fixed in collection manifest, collection docs, and README
- Aligns with standard industry convention and agent naming
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Shorten collection description per maintainer feedback
- Brief description in table: "7 specialized agents covering the full software
development lifecycle from UX design and architecture to security and DevOps."
- Move detailed context (Medium article, design principles, agent list) to
usage section following edge-ai-tasks pattern
- Addresses @aaronpowell feedback: descriptions should be brief for table display
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Introduced comprehensive documentation for Azure Verified Modules (AVM) and Bicep.
- Included guidelines for module discovery, usage, naming conventions, and best practices.
- Added validation requirements and troubleshooting tips for Bicep files.
* feat: Add AGENTS.md file with project guidance for AI coding agents
* docs: Update AGENTS.md with line endings script requirement
* fix: Correct 'mode' field to 'agent' in prompt files documentation and add AGENTS.md reference to README
* Add Custom Agent Foundry agent
- Adds expert agent for designing and creating VS Code custom agents
- Provides comprehensive guidance on agent architecture and best practices
- Includes tool selection strategies, workflow patterns, and quality guidelines
- Updates README.agents.md with new entry
* Update README to enhance instructions for Custom Agent Foundry
* Refactor README to improve clarity and organization of Custom Agents section
* Add model specification for Custom Agent Foundry
* Add generic code review instructions
- Generic and reusable code review template
- Multi-language support (JavaScript, Python, Java, TypeScript)
- Based on GitHub Copilot prompt engineering best practices
- Includes security, performance, and architecture checks
- Customizable for any project
- Follows awesome-copilot contribution guidelines
* Add generic code review instructions
- Generic and reusable code review template
- Multi-language support (JavaScript, Python, Java, TypeScript)
- Based on GitHub Copilot prompt engineering best practices
- Includes security, performance, and architecture checks
- Customizable for any project
- Follows awesome-copilot contribution guidelines
* Add applyTo field to code review instructions front matter
