Six Claude Code / Copilot skills for the Progress Observability Platform: trace triage, cost reports, eval coverage gaps, LLM-as-a-Judge eval generation, a setup health check, and a .NET agent scaffolder — over MCP.
observability-oss/progress-observability-plugin
Skill Claude CodeCodex
Report and explain LLM spend and usage on the Progress Observability Platform. Use when the user asks "what's driving my LLM costs", "how much am I spending", "cost by model/app", "am I close to my quota", "why did spend spike", or wants a cost/usage summary or a cheaper-model recommendation.
observability-oss/progress-observability-plugin
Skill Claude CodeCodex
Find which of an AI system's behaviors are running in production but have no evaluation measuring them, using the Progress Observability Platform. Use when the user asks "what should I evaluate next", "what's my eval coverage", "which behaviors aren't tested", "where are my eval gaps", or wants to prioritize which…
observability-oss/progress-observability-plugin
Skill Claude CodeCodex
Generate a research-grounded LLM-as-a-Judge evaluator prompt for an AI system. Use when the user wants to build an eval, judge, scorer, or grader for their LLM app or agent — especially grounded in real production traces from the Progress Observability Platform. Triggers on "write an eval", "build a judge", "score my…
observability-oss/progress-observability-plugin
Skill Claude CodeCodex
Add Progress Observability instrumentation to an existing AI agent or LLM app — Python, TypeScript/JavaScript, or .NET, including LangChain, LangGraph, LlamaIndex, CrewAI, OpenAI Agents, Haystack, MCP servers and Microsoft.Extensions.AI — with the smallest possible diff, then hand off with where to confirm the traces.…
observability-oss/progress-observability-plugin
Skill Claude CodeCodex
Scaffold a new .NET AI agent project with Progress Observability already wired up, starting from the observability-oss dotnet-agent-starter template. Use when the user wants to create, scaffold, bootstrap, or start a new agent — "build me an agent that…", "scaffold a .NET agent", "new agent project with…
observability-oss/progress-observability-plugin
Skill Claude CodeCodex
Investigate why an AI agent run failed, stalled, or misbehaved by walking its trace on the Progress Observability Platform. Use when the user asks "why did this run fail/error", "why was my agent slow", "what happened in this trace", "find the bottleneck", or wants to root-cause a bad tool call or a broken agent…