adk-rust-eval-observability-guardrails
Add evaluation, telemetry, and guardrails to ADK-Rust systems as one quality loop. Use when hardening agent behavior before production release.
Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Add evaluation, telemetry, and guardrails to ADK-Rust systems as one quality loop. Use when hardening agent behavior before production release.
Build and debug ADK graph workflows with checkpoints, routing, interrupts, and state reducers. Use when implementing graph-based orchestration in adk-graph.
Select and configure ADK-Rust model providers and feature flags with environment validation. Use when choosing Gemini/OpenAI/Anthropic/DeepSeek/Groq/Ollama/mistralrs for a project.
Implement realtime voice agents with ADK-Rust, including audio formats, event handling, and streaming reliability. Use when building or debugging voice interactions in adk-realtime.
Add ADK-Rust tools, MCP integrations, and ADK UI protocol outputs safely. Use when building function tools, MCP toolsets, browser tools, or UI render tools.
Build, debug, and validate ADK Studio projects and generated Rust workflows. Use when working on adk-studio schemas, action nodes, code generation, graph runner behavior, or studio deployment readiness.
Use when configuring dubbo-go-pixiu as an MCP gateway: `dgp.filter.mcp.mcpserver`, Streamable HTTP/SSE, `tools/list`, `tools/call`, OAuth/JWT `dgp.filter.http.auth.mcp`, Nacos `dgp.adapter.mcpserver`, or stdio MCP bridge guidance.
Load this skill when working on the RAG-GPT sub-project pipeline — document ingestion, embedding, retrieval, prompt construction, or response formatting. Also load when debugging ChromaDB, LangChain, or Gradio issues in RAG-GPT.
Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing toolboxes with a team.