- Fix broken reasoning framework: complete Ordering field and Necessity scale
- Remove OpenAI attribution from description; add invocation example block
- Restrict tools to Read only (text-transformation agent needs no writes)
- Add XML Structure and CoT Opportunity dimensions to reasoning template
- Move meta-instruction NOTE out of output template, place as agent directive
- Fix stray markdown bold markers on Reasoning Before Conclusions guideline
- Integrate orphaned examples bullet into the Examples guideline line
- Add concrete worked example section (classify customer feedback)
Automated review cycle | Co-Authored-By: Claude Code <noreply@anthropic.com>
Remove `model: sonnet/haiku/opus` from 396 component files. The Anthropic
API requires full model IDs (e.g., claude-sonnet-4-6), so shorthand names
cause 404 errors. Removing the field lets Claude Code use the user's
configured default model instead.
Fixes#99https://claude.ai/code/session_01Hqx78XZNbdfh38YGZn4g4T
Co-authored-by: Claude <noreply@anthropic.com>
Imported and converted components from github.com/github/awesome-copilot:
- 135 agents covering various domains (security, devops, web development, etc.)
- 7 skills converted to commands (GitHub issues, NuGet, Azure, testing, etc.)
New agent categories:
- Programming languages experts (C#, Python, Rust, TypeScript, etc.)
- Azure and cloud infrastructure specialists
- Web development experts (React, Next.js, accessibility)
- Security and DevOps specialists
- Data and AI specialists
New command categories:
- Azure (AppInsights, role selector)
- Database (Snowflake)
- Design (web design reviewer)
- Project management (GitHub issues, NuGet manager)
- Testing (webapp testing)
All components converted from awesome-copilot format to claude-code-templates format with appropriate frontmatter and categorization.
Co-authored-by: Claude <noreply@anthropic.com>
Daniel Avila