菜单
Search and analyze DealerVision production logs via SolarWinds Observability API. Use when investigating errors, debugging issues, checking system health, or when the user mentions logs, SolarWinds, production errors, or system monitoring. Requires the `logs` CLI tool to be installed.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/jakenuts/agent-skills --skill solarwinds-logs命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Create and iterate on shareable visual diagrams (architecture maps, flowcharts, state machines, class/domain models, mindmaps, dependency maps) via the Agent Vision MCP server or its HTTP action API. Use when the user asks for a diagram, visualization, or "draw this out" during a conversation, or when the user hands you an Agent Vision app URL + connection token.
ElevenLabs Speech Engine — the SDK for giving a voice interface to a custom agent you host yourself (your existing chat agent, LangGraph workflow, containerized LLM service, etc.). ElevenLabs runs the audio pipeline (STT, turn detection, VAD, TTS, barge-in); your server receives transcripts over a WebSocket and streams text replies back. Use when wiring an existing non-ElevenLabs agent to voice, when the user mentions "Speech Engine", `seng_*` engine IDs, `@elevenlabs/elevenlabs-js` `speechEngine.attach()` / `SpeechEngine.Server`, Python `AsyncElevenLabs.speech_engine`, or full-duplex voice with bring-your-own-LLM. Also covers the matching client SDKs (`@elevenlabs/client`, `@elevenlabs/react`, `@elevenlabs/react-native`, the convai widget) for the browser/mobile side. Do NOT use this skill for ElevenAgents (fully hosted agent platform — different product, see distinction below) or plain TTS / STT calls.
WolverineFx (.NET) framework for in-process command/event handling, asynchronous messaging, durable inbox/outbox, sagas, and HTTP endpoints. Use when working in a .NET project that references `WolverineFx*` packages, calls `UseWolverine()`, or whenever the user asks about Wolverine handlers, message routing, transactional outbox, transports (RabbitMQ, Azure Service Bus, SQS, Kafka, NATS, Pulsar, PostgreSQL, SQL Server, Redis, MQTT, etc.), Wolverine.HTTP endpoints, Marten/EF Core/RavenDb integration, sagas/process managers, middleware, cascading messages, side effects, FluentValidation integration, tracked-session testing, or migrating to/from MediatR/NServiceBus/MassTransit. Also applies to Critter Stack and JasperFx conversations that mention Wolverine.
正在显示 SKILL.md
基于 SOC 职业分类
| name | solarwinds-logs |
| description | Search and analyze DealerVision production logs via SolarWinds Observability API. Use when investigating errors, debugging issues, checking system health, or when the user mentions logs, SolarWinds, production errors, or system monitoring. Requires the `logs` CLI tool to be installed. |
| compatibility | Requires .NET SDK 10.0+, SOLARWINDS_API_TOKEN environment variable |
| allowed-tools | logs |
| metadata | {"requires-setup":true,"tool-name":"solarwinds-logs"} |
Search DealerVision production logs through the SolarWinds Observability API using the logs CLI tool.
This skill requires the logs CLI tool, .NET 10, and a SolarWinds API token. Install only when the skill is activated.
Linux/macOS:
logs --help 2>/dev/null || echo "Not installed - setup required"
echo "$SOLARWINDS_API_TOKEN"
Windows (PowerShell):
logs --help 2>$null
Write-Host "SOLARWINDS_API_TOKEN=$env:SOLARWINDS_API_TOKEN"
Run the setup script from the deployed skill folder:
Linux/macOS:
bash ~/.codex/skills/solarwinds-logs/scripts/setup.sh
Windows (PowerShell):
pwsh ~/.codex/skills/solarwinds-logs/scripts/setup.ps1
If you are using Claude Code, replace ~/.codex/skills with ~/.claude/skills.
What this does:
logs CLI tool from the skill-local packageNote: Installation only happens once; the tool becomes globally available.
The tool requires a SolarWinds API token for authentication.
Linux/macOS:
export SOLARWINDS_API_TOKEN="your-token-here"
Windows (PowerShell):
$env:SOLARWINDS_API_TOKEN = "your-token-here"
To obtain a token:
Linux/macOS:
dotnet tool list --global | grep SolarWindsLogSearch
logs "test" --limit 1
Windows (PowerShell):
dotnet tool list --global | Select-String SolarWindsLogSearch
logs "test" --limit 1
na-01If you prefer to install manually without the setup script:
# Requires .NET SDK 10.0+
dotnet tool install --global DealerVision.SolarWindsLogSearch --version 2.4.0 --add-source ~/.codex/skills/solarwinds-logs/tools
# If using Claude Code, replace ~/.codex/skills with ~/.claude/skills
# Windows path: %USERPROFILE%\\.codex\\skills\\solarwinds-logs\\tools (or .claude for Claude Code)
# Verify
logs --help
The SolarWinds/Papertrail API is finicky with time ranges and often skips recent entries when time arguments are used. The logs tool is designed to start from the most recent entries and page backward through time automatically until a predefined limit (typically 24 hours worth of data).
Always prefer simple keyword searches without time arguments:
# ✅ RECOMMENDED - Simple searches that capture current entries
logs 'error'
logs 'exception'
logs 'timeout'
logs 'DbUpdateException'
# ✅ GOOD - Add filters, but avoid time arguments
logs 'error' --severity ERROR
logs 'exception' --program webhook-api
When you use --time-range, --start-time, or --end-time, the API may return a subset of entries that misses vital current/recent log entries. This is a known quirk of the underlying Papertrail API.
# ⚠️ AVOID - Time arguments can miss recent entries
logs "error" --time-range 1h # May miss errors from the last few minutes
logs "error" --time-range 24h # May skip entries that just happened
When a user asks for something like "errors from today" or "logs from the last hour":
logs 'error' without time argumentsExample interpretations:
logs 'error' OR 'exception' (filter results yourself)logs 'exception' (filter results yourself)Only use time arguments when the user explicitly wants to:
# Search for errors (recommended - no time arguments)
logs 'error'
# Find specific exceptions
logs 'DbUpdateException' --severity ERROR --limit 10
# Filter by service (still no time arguments)
logs 'timeout' --program webhook-api
# Get full details for a specific log entry
logs --id 1901790063029837827 --with-data
# Export large result sets to file
logs 'exception' --output-file results.json
| Option | Description |
|---|---|
--time-range | 1h, 4h, 12h, 24h, 2d, 7d, 30d |
--severity | INFO, WARN, ERROR, DEBUG |
--program | Filter by service name (e.g., media-processing) |
--hostname | Filter by host |
--limit | Max results (default 1000, max 50000) |
--with-data | Include structured JSON payload |
--no-data | Exclude payload (faster, smaller response) |
--output-file | Save full results to file |
--id with --with-data for full log entry inspection--output-file for comprehensive analysisReturns JSON with:
success: boolean statusquery: search parameters usedsummary: statistics including severity breakdown, truncation inforesults: array of log entries with timestamps, source, severity, messagepagination: info for getting more resultsFor detailed documentation on query syntax, MCP server modes, and advanced patterns, see references/REFERENCE.md.
For common investigation patterns and recipes, see references/RECIPES.md.