agentic-eval
FreePatterns and techniques for evaluating and improving AI agent outputs.
The English summary is being prepared. Showing the original description.
Offline mode with local caching for air-gapped environments
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Enable offline operation with local skill and MCP caching.
# Set offline mode
export DOTNET_HARNESS_OFFLINE=true
# Or use flag
rulesync generate --offline
```text
## Cache Structure
```text
.dotnet-harness/
├── cache/
│ ├── skills/ # Cached skill content
│ ├── mcp-responses/ # Cached MCP responses
│ └── registry/ # Cached registry data
└── index.json # Search index
Online Sync (when connected):
dotnet-harness:sync-cache
Offline Operation:
{
"offline": {
"enabled": false,
"cachePath": ".dotnet-harness/cache",
"maxCacheAge": "7d",
"fallbackEnabled": true
}
}
dotnet-harness:sync-cache - Sync cache from remotedotnet-harness:clear-cache - Clear local cachedotnet-harness:cache-status - Show cache statisticsWhen offline:
Cache Miss: Run dotnet-harness:sync-cache Stale Data: Clear and re-sync Large Cache: Exclude heavy MCP
servers
Primary approach: Use Serena symbol operations for efficient code navigation:
serena_find_symbol instead of text searchserena_get_symbols_overview for file organizationserena_find_referencing_symbols for impact analysisserena_replace_symbol_body for clean modificationsWhen to use Serena vs traditional tools:
Example workflow:
# Instead of:
Read: src/Services/OrderService.cs
Grep: "public void ProcessOrder"
# Use:
serena_find_symbol: "OrderService/ProcessOrder"
serena_get_symbols_overview: "src/Services/OrderService.cs"
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Patterns and techniques for evaluating and improving AI agent outputs.
The English summary is being prepared. Showing the original description.
Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations.
The English summary is being prepared. Showing the original description.
Use when user requests research requiring multiple sources, comprehensive analysis, or synthesis across topics - technical research, domain knowledge gathering, market analysis, or learning about complex subjects
The English summary is being prepared. Showing the original description.
AI-powered wiki generation for code repositories with commands, agents, and skills
The English summary is being prepared. Showing the original description.
Use when building .NET 10 or C# 14 applications; when using minimal APIs, modular monolith patterns, or feature folders; when implementing HTTP resilience, Options pattern, Channels, or validation; when seeing outdated patterns like old extension method syntax
The English summary is being prepared. Showing the original description.
Implements accessible .NET UI. SemanticProperties, ARIA, AutomationPeer, testing per platform.
The English summary is being prepared. Showing the original description.