itlightning

Sparklogs AI Plugins — AI skill for Claude Code

AI community

SparkLogs helps managed service providers and IT pros investigate client issues with evidence instead of guesswork.

How to install Sparklogs AI Plugins

This entry records only its repository, not the path inside it, so there is no exact command to give. Open itlightning/sparklogs-ai-plugins and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Sparklogs AI Plugins does

SparkLogs helps managed service providers and IT pros investigate client issues with evidence instead of guesswork. This repository packages the SparkLogs AI skills, commands, subagents, and MCP configuration for Claude Code, Cursor, and Codex.

Alternatives in AI

Jcodemunch MCP — Cut AI token costs 95%+ on code exploration 2.6k ★
Hol Guard — Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, M 485 ★
Agenvoy — Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets 474 ★

README

SparkLogs AI Plugin

Give your AI assistant or AI agent real evidence from your fleet: logs, device health, and system state, one host or all of them.

What is SparkLogs

SparkLogs is [IT fleet intelligence](https://sparklogs.com/docs/it-fleet-intelligence) for MSPs and IT teams: it collects and understands the logs and health signals from across your IT fleet, so problems can be investigated with evidence instead of guesswork. This plugin connects your AI assistant to that intelligence.

Data comes from Windows systems across your fleet through the [SparkLogs Agent](https://sparklogs.com/docs/agents). You can also send it with any [popular open source log shippers](https://sparklogs.com/docs/ingest) such as [OpenTelemetry](https://sparklogs.com/docs/ingest/tools/opentelemetry-collector), [Vector](https://sparklogs.com/docs/ingest/tools/vector), or [Fluent Bit](https://sparklogs.com/docs/ingest/tools/fluentbit), which forward [syslog](https://sparklogs.com/docs/ingest/data-sources/syslog) and other sources.

What your AI assistant can do with it

Investigate one device end to end: what changed, what failed, and what it means, with every claim tied to the events behind it. See skills/sparklogs-investigate.
Triage the whole fleet: what needs attention today, what is new this week, and who else is affected.
Follow guided steps for common MSP situations such as backup failures, patch failures, slow logon, and degraded storage. See playbooks.
Read per-feed reference knowledge for Windows Event Log, servicing, and Defender data, so answers cite what an event actually means instead of guessing from an event ID. See feeds.
Write ticket-ready summaries, and explain any single finding back to the evidence it came from. See [command