#
ENJA

LiveAgent

MCP Server

Stack-Cairn/LiveAgent

LiveAgent is a local-first AI agent desktop client and code review skill that uses parallel independent reviewers and evidence-based validation to catch high-confidence defects in pull requests and local changes.

1.7k 192MITUpdated 2026-08-13
View on GitHubOpen source file

Overview

This skill implements a rigorous code review workflow modeled after Anthropic's Claude Code review architecture. It uses multiple parallel reviewer agents specialized in rules, bugs, and security, followed by rigorous isolated validation to filter out noise, subjective style rules, and false positives before producing a high-confidence finding report.

Capabilities

  • ▸Parallel multi-role code review (rules, bugs, security)
  • ▸Evidence-based finding validation
  • ▸GitHub pull request integration via read-only gh CLI
  • ▸Local git repository snapshot resolution and diff analysis
  • ▸AGENTS.md compliance checking

Best for

Reviewing open GitHub pull requests before merging, Auditing local branches, staged changes, and working tree modifications, Detecting bugs, correctness errors, and security issues introduced by recent code changes

Works with

Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
84
Task usefulness20%88 → +17.6

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%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

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%36 → +4.3

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%100 → +15.0

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%85 → +8.5

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%83 → +6.6

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

Compatibility5%75 → +3.8

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 total84.3 / 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

Runs strictly in read-only mode. It does not write to GitHub, create commits, modify repository files, or execute tests and shells within subagents.

Categories

CodingGitTestingSecurity

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.