observability-analyzer
Query and analyze Claude Code observability data (metrics, logs, traces). Use when analyzing performance, costs, errors, tool usage, sessions, conversations, or subagents.
npx skills add majiayu000/claude-skill-registry --skill observability-analyzer --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.
# Observability Analyzer Query Claude Code telemetry and generate insights from metrics, logs, and traces. Works with both default OTEL telemetry and enhanced hook-based telemetry. ## Data Sources | Source | Job Name | Contains | |--------|----------|----------| | Default OTEL | `claude_code` | API metrics, token usage, costs | | Enhanced Hooks | `claude_code_enhanced` | Sessions, conversations, tools, subagents | ## Operations ### `query-metrics <promql>` Execute PromQL query against Prometheus. ```bash query-metrics 'sum(claude_code_token_usage)[7d]' ``` ### `query-logs <logql>` Execute LogQL query against Loki. ```bash query-logs '{job="claude_code_enhanced", event_type="tool_call"} | json' --since 24h ``` ### `analyze-errors` Detect and group error patterns from enhanced telemetry. ```logql {job="claude_code_enhanced", event_type="tool_result", status="error"} | json ``` **Output**: Error types, frequencies, affected tools, recommendations. ### `analyze-performance` Identify slow operations and response sizes. ```logql {job="claude_code_enhanced", event_type="tool_result"} | json | response_length > 50000 ``` **Output**: Large responses, estimated token costs, slow patterns. ##
- Data Sources
- Operations
- query-metrics <promql>
- query-logs <logql>
- analyze-errors
- analyze-performance
- analyze-costs
- analyze-tools
- analyze-sessions
- analyze-conversations
- analyze-subagents
- analyze-skills
- analyze-context
- analyze-repos
query-metrics 'sum(claude_code_token_usage)[7d]'
query-logs '{job="claude_code_enhanced", event_type="tool_call"} | json' --since 24hWhat does the observability-analyzer skill do?
Query and analyze Claude Code observability data (metrics, logs, traces). Use when analyzing performance, costs, errors, tool usage, sessions, conversations, or subagents.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill observability-analyzer --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.