yoyo-evolve
yologdev/yoyo-evolve
Analyzes recurring failure trajectories and CI errors by deploying sub-agents to digest logs without overflowing the main context window. Utilizes token-aware chunking and a recursive investigation workflow to isolate root causes.
1.9k 126MITUpdated 2026-08-13
82
GreatOverview
This skill provides a structured framework for diagnosing stubborn software failures, recurring CI errors, and repeatedly reverted tasks. Instead of loading massive log files into the primary context, it leverages shared state and sub-agents to fetch, split, and analyze log artifacts recursively. It incorporates strict validation, retries, recursion depth caps, and fallback mechanisms to ensure robust root-cause diagnosis.
Capabilities
- ▸Sub-agent dispatch for reading large log files
- ▸Token-aware log splitting and parallel chunk analysis
- ▸Recursive failure analysis with depth controls
- ▸Shared state management for inter-agent communication
- ▸JSON validation and fallback handling for malformed agent outputs
Best for
Diagnosing tasks that repeatedly fail or get stuck across multiple execution attempts, Investigating recurring CI error fingerprints without bloating the main context, Analyzing regression patterns and reasons behind frequent code reverts
Works with
Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
82Task 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%40 → +4.8
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%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 total81.8 / 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
Executes bash commands to fetch remote logs and interacts with git worktrees. Ensure commands run within a trusted repository environment.
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.