Loading...
Loading...
Found 4 Skills
End-to-end interactive workflow — pick a product, then either run existing tasks and environments (Path A) or set up new ones from docs, suggested tasks, credentials, and templates (Path B). Builds the experiment, attaches signals, and optionally triggers the first iteration. Trigger when users say: "set up an experiment", "create an experiment", "I want to run an experiment", "run my tasks", "setup experiment", "new experiment", "configure an experiment", or "experiment setup".
Generates YAML signal configs for agent simulation experiments. Use when the user wants to define what signals to track, how to extract them from run artifacts, and how to aggregate them into experiment-level metrics. Trigger when users say: "generate a signal config", "create signals for my experiment", "I want to track [metric]", "write a signal YAML", "set up extraction for [thing]", "how do I measure [behavior] across runs", "configure signals for [experiment]", "create a signal config", "create signal config file", or "build a signal config".
Turn a completed experiment iteration into an honest, evidence-backed analysis — a markdown report and a portable data dump. Pulls run data via the tpc CLI, scores each task, clusters friction by root cause (with a transcript example per claim), compares arms, and closes on agent-readiness gaps. The natural companion to setup-experiment: setup → run → analyze. Trigger when users say: "analyze my experiment", "write the report", "experiment report", "analyze the results", "summarize the runs", "what happened in this iteration", "friction report", or "report gen".
Agent simulation and GEO simulation prompt generation for AI visibility auditing. Use when the user wants to create simulation tasks via the TPC CLI, generate unbranded GEO prompts to test whether AI recommends a product, or run agent simulations.