devboy-tools
meteora-pro/devboy-tools
Analyze high-level usage patterns in Claude Code sessions to generate graphical periodic digests, metrics, and behavioral archetypes. It processes local log files into structured parquet bundles and markdown reports.
Overview
This skill extends research pipelines by examining Claude Code usage behavior, classifying sessions into biological and behavioral metaphors (like biomes and archetypes), and computing productivity metrics such as DORA indicators. It provides a multi-tiered output system that handles data anonymization, local Python-based extraction, and LLM-driven narrative reporting.
Capabilities
- ▸Session biome and archetype classification
- ▸DORA metrics calculation (CFR, lead time, push frequency)
- ▸Data anonymization and leak auditing
- ▸Growth curve and milestone extraction
- ▸Periodic reporting in terminal, markdown, and HTML formats
Best for
Generating weekly or monthly graphical productivity digests and DORA metrics reports, Classifying session types, rhythms, and work biomes (e.g., whale, shark, plankton), Auditing and anonymizing local session logs for safe sharing, Drilling down into specific development sessions to view timelines and prompt distributions
Works with
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
実装・指示の品質。 — AIによるSKILL.md/README解析
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
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
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
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
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
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
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
Processes local session logs which may contain sensitive source code paths, branch names, and prompts. Implements strict tiering and anonymization utilities to strip identifiers before sharing.
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.