agentv-trace-analyst
Analyze AgentV evaluation traces and result JSONL files using `agentv trace` and `agentv 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.
npx skills add majiayu000/claude-skill-registry --skill agentv-trace-analyst --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# AgentV Trace Analyst Analyze evaluation traces headlessly using `agentv trace` primitives and `jq`. ## Primitives ```bash # List result files (most recent first) agentv trace list [--limit N] [--format json|table] # Show results with trace details agentv trace show <result-file> [--test-id <id>] [--tree] [--format json|table] # Percentile statistics agentv trace stats <result-file> [--group-by target|dataset|test-id] [--format json|table] # A/B comparison between runs agentv compare <baseline.jsonl> <candidate.jsonl> [--threshold 0.1] [--format json|table] ``` ## Analysis Workflow ### 1. Discover results ```bash agentv trace list ``` Pick the result file to analyze. Most recent is first. ### 2. Get overview ```bash agentv trace stats <result-file> ``` Read the percentile table. Key signals: - **score p50 < 0.8**: Significant quality issues - **latency p90 > 30s**: Performance bottleneck - **cost p99 spike**: Outlier cost tests to investigate - **tool_calls p90 >> p50**: Some tests are much chattier ### 3. Investigate failures ```bash agentv trace show <result-file> --format json | jq '[.[] | select(.score < 0.8) | {test_id, score, assertions: [.assertions[] | select(.passed | not
- Primitives
- Analysis Workflow
- 1. Discover results
- 2. Get overview
- 3. Investigate failures
- 4. Inspect specific tests
- 5. Compare runs
- 6. Group analysis
- Advanced Queries with jq
- Reasoning Patterns
List result files (most recent first) agentv trace list [--limit N] [--format json|table] Show results with trace details agentv trace show <result-file> [--test-id <id>] [--tree] [--format json|table] Percentile statistics agentv trace stats <result-file> [--group-by target|dataset|test-id] [--format json|table] A/B comparison between runs agentv compare <baseline.jsonl> <candidate.jsonl> [--threshold 0.1] [--format json|table] agentv trace list agentv trace stats <result-file>
What does the agentv-trace-analyst skill do?
Analyze AgentV evaluation traces and result JSONL files using `agentv trace` and `agentv 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.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill agentv-trace-analyst --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.