Migrate AgentV eval YAML across breaking schema changes, especially workspace contract updates and portable-vs-local runtime binding cleanup.
Write, edit, review, and validate AgentV EVAL.yaml / .eval.yaml evaluation files. Use when asked to create new eval files, update or fix existing ones, add or remove test cases, configure graders (`llm-rubric`, `script`), review whether an eval is correct or complete, convert between EVAL.yaml and evals.json using `agentv convert`, or generate eval test cases from chat transcripts (markdown conversation or JSON messages). Do NOT use for creating SKILL.md files, writing skill definitions, or running evals — running and benchmarking belongs to agentv-bench.
Run AgentV evaluations and optimize agents through eval-driven iteration. Triggers: run evals, benchmark agents, optimize prompts/skills against evals, compare agent outputs across providers, analyze eval results, offline evaluation of recorded sessions, run autoresearch, optimize unattended, run overnight optimization loop. Not for: writing/editing eval YAML without running (use agentv-eval-writer), analyzing existing traces/JSONL without re-running (use agentv-trace-analyst).
Capture, optimize, and publish screenshots to Astro docs. Use when asked to take screenshots for docs, update doc images, compress PNG assets, or add visual documentation to the agentv.dev docs site. Triggers on "add screenshots to docs", "update docs images", "compress screenshots", "optimize PNG", "document with screenshots".
Use when the user asks to analyze, summarize, or extract insights from CSV data or files
Use when reviewing eval YAML files for quality issues, linting eval files before committing, checking eval schema compliance, or when asked to "review these evals", "check eval quality", "lint eval files", or "validate eval structure". Do NOT use for writing evals (use agentv-eval-writer) or running evals (use agentv-bench).
Analyze AgentV evaluation traces and result JSONL files using `agentv inspect` and `agentv results compare` CLI commands. Use when asked to inspect AgentV eval results, find regressions between AgentV evaluation runs, identify failure patterns in AgentV trace data, analyze tool trajectories, or compute cost/latency/score statistics from AgentV result files. Do NOT use for benchmarking skill trigger accuracy, analyzing skill-creator eval performance, or measuring skill description quality — those tasks belong to the skill-creator skill.
AgentV CLI skills for evaluating, optimizing, and governing AI agents. Triggers: run evals, benchmark agents, write evals, review evals, analyze traces, optimize prompts, governance linting. Covers: eval running, eval writing, eval review, trace analysis, description optimization, autoresearch, and governance compliance.