deep-code-reader
CiferaTeam/deep-code-reader
Deep Code Reader systematically analyzes local or remote codebases to produce verified, reusable AI cognitive skills through a closed-book verification loop.
97 3No licenseUpdated 2026-03-19
62
GoodOverview
This skill acts as an automated codebase knowledge extractor that maps modules, generates structured documentation, and rigorously tests the comprehension of the generated artifacts using an ABC multi-agent verification loop. It ensures that the resulting skills capture genuine, verifiable technical knowledge instead of shallow summaries, allowing AI agents to operate effectively on unfamiliar repositories.
Capabilities
- ▸Codebase structure scanning and dependency graph generation
- ▸Multi-agent collaborative skill creation and refinement
- ▸Closed-book exam verification loop to test skill completeness
- ▸Cross-module scenario and global index generation
- ▸Git repository parsing, tagging detection, and selective cloning
Best for
Onboarding an AI agent to an unfamiliar open-source repository or legacy codebase., Generating persistent, loadable domain knowledge and architecture guides from complex codebases., Automating overnight code analysis and skill compilation using idle AI compute tokens.
Works with
Claude CodeCursor
Evoa Score breakdown= Σ (score × weight)
62Task 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%70 → +10.5
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%34 → +4.1
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%50 → +4.0
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
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 total72.7 / 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
The skill operates in a read-only mode on the source repository, preventing accidental modifications to target codebases. However, it executes automated subagent workflows and clones remote repositories specified via URL.
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.