#
ENJA

BugZooka

redhat-performance/BugZooka

BugZooka is a Slack bot and log analysis tool that integrates static rules, LLM inference, and Model Context Protocol (MCP) servers to monitor CI pipelines, summarize errors, and inspect performance regressions.

7 15Apache-2.0Updated 2026-07-08

Overview

BugZooka operates as a Slack monitoring and conversational bot designed to parse and categorize log errors using configurable prompts and OpenAI-compatible LLM endpoints. It supports both a polling mode for routine channel failure assessments and a real-time Socket Mode for chat interactions. Through integration with external tools like the Orion MCP server, it can run advanced multi-step analysis on GitHub pull requests, check nightly test regressions, and optionally incorporate RAG-based context from local vector stores to deliver rich infrastructure insights.

Capabilities

  • Slack channel log monitoring and automated failure summarization
  • LLM-powered log analysis using custom or default prompts
  • Real-time event processing and command handling through Slack Socket Mode
  • GitHub pull request performance analysis via Orion-MCP integration
  • Nightly test regression detection and comparison
  • Optional RAG-augmented insights using local vector stores

Best for

Analyzing and categorizing CI job failure logs directly within Slack channels, Generating performance summaries and trend comparisons for Kubernetes and OpenShift across specified lookback windows, Inspecting nightlies for test regressions and comparing versions using Model Context Protocol (MCP) tool calls, Interactively evaluating pull request performance impacts via real-time Slack bot mentions

Works with

Gemini CLI
Evoa Score breakdown= Σ (score × weight)
74
Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 AIによるcapabilities/use-cases解析

Code quality15%85 → +12.8

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%85 → +12.8

リポジトリがどれだけ活発に保守されているか。 GitHub 最終push日時の新しさ

Documentation12%41 → +4.9

ドキュメントの充実度・分かりやすさ。 README/独自要約の情報量

Security15%80 → +12.0

危険・不審な挙動が無いか。 AIによるセキュリティレビュー

Originality10%75 → +7.5

ありふれたラッパーではない独自性。 AIによる独自性判定

Popularity8%39 → +3.1

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%25 → +1.3

対応AIエージェントの広さ。 AIによる対応エージェント判定

Weighted total74.3 / 100

ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

Users should avoid inputting personal or sensitive corporate information into LLM prompt inputs. All necessary authorization credentials, API keys, and Slack tokens must be securely stored in a local .env configuration file.

Categories

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.