#
ENJA

skillreaper

MCP Server

thousandflowers/skillreaper

Skillreaper analyzes your AI agent session transcripts to identify and prune loaded skills, MCP servers, and agents that are never actually used, saving valuable context tokens.

48 4MITUpdated 2026-08-04

Overview

Skillreaper is a zero-config, read-only utility designed to optimize AI agent context windows by analyzing session transcripts and configuration files. It highlights dead weight, calculates token waste, and provides safe, reversible management commands such as pruning, muting, routing plans, and utilization gap reports.

Capabilities

  • Scan and inventory skills, MCP servers, and agents across multiple platforms
  • Parse session transcripts to gather real usage evidence
  • Calculate approximate token weight and utilization rates
  • Safely quarantine unused items via atomic file moves
  • Mute verbose or rarely used skill descriptions
  • Generate lazy-load routing plans and APM manifests
  • Provide structured JSON and Markdown reporting

Best for

Auditing AI agent configurations to identify unused skills, agents, and MCP servers., Reducing token consumption and improving prompt cache hit rates., Safely quarantining or muting unused tools with full rollback capabilities., Generating usage-informed lazy-load routing plans or APM manifests.

Works with

Claude CodeCodexOpenCodeCursor
Evoa Score breakdown= Σ (score × weight)
85
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%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%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%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%44 → +3.5

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

Compatibility5%100 → +5.0

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 total85.4 / 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

Operates entirely locally with read-only transcript inspection and atomic file operations confined to local configuration directories.

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.