メニュー
System anomalies, errors, latency diagnosis. Logs, traces, metrics. Orchestrates log-analyze, trace, metrics primitives. Fetches data, frontend renders charts.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | troubleshoot |
| description | System anomalies, errors, latency diagnosis. Logs, traces, metrics. Orchestrates log-analyze, trace, metrics primitives. Fetches data, frontend renders charts. |
| metadata | {"type":"feature","dependencies":"log-analyze,trace,metrics,deep-recall"} |
When to use which primitive:
log-analyze
list: List available log sessions and dates. Use when user asks "list logs".query: Get raw log entries (message, level). Use for error source analysis—pass level=ERROR. Use for "show/display error logs".analyze: Aggregation for charts (count by level, time series). Use when user asks for chart/graph. NOT for raw logs.trace
list: List recent trace sessions. Use when user asks "list traces".query: Query traces. session_id optional; omit for global view.analyze: Statistical analysis (duration, operations, errors). session_id optional for global.metrics
list: List metric names. Use when user asks "show metrics".query: Query single metric for charts.query_multi: Query multiple metrics for one chart (each metric a line). Use when user wants to compare/overlay metrics.query_compare: Same metric, different time periods (e.g. last 3d vs prev 3d). Call time.calculate for each period; pass {label, since, until} per period. Use since/until (not start/end).write: Write metric points. Use when recording measurements.troubleshoot
diagnose: Full diagnostic. Aggregates traces and logs. session_id optional; omit for global.
Skills produce typed output. Main agent passes through without transformation. Frontend renders by type.
Schema: schemas/diagnose_output.json
| Field | Type | Description |
|---|---|---|
| summary | string | Human-readable summary. Required. |
| traces_count | int | Number of traces. |
| logs_count | int | Number of log entries. |
| by_level | object | Log level counts { level: count }. |
| time_series | array | [{ date, count }] for time-based charts. |
| operation_breakdown | array | [{ operation, count }] trace operations. |
| gen_ui | object | When present: { type, payload: { charts } }. Each chart: { kind, labels?, values?, x?, y?, chart_type? }. |
Introduce Sophon and list available capabilities. Use ONLY when the user explicitly asks who you are, what you can do, what your capabilities are, or what skills you have. Do NOT call for greetings, small talk, or when the user has not asked about your identity or capabilities.
Deep research on a topic. Decomposes question into sub-questions, searches and fetches web sources in parallel, synthesizes a structured report with inline citations and a source list. Use when user asks for in-depth research, comprehensive analysis, or a structured report.
Process xlsx workbooks; fill columns from web via key column (URL→crawl, else search), LLM extract per batch. Tools: list_sheets, read_structure, read_sample, fill_by_column. Cross-sheet copy via copy_columns / copy_column_map.
Web scraping via Playwright. Use when user wants to fetch page content or scrape a URL.
Memory recall and history exploration. Use for any question about past conversations, previous topics, what the user asked before, or recent activity. Replaces the memory skill.
Read and write Excel/CSV files. Supports .xlsx, .xls, and .csv formats.