RigorPilot-Skills
lllllllama/RigorPilot-Skills
RigorPilot Skills provides a research-first suite of agent skills designed to keep AI-assisted deep learning experiments grounded in reproducibility, evidence, and auditable changes.
483 12MITUpdated 2026-07-26
88
GreatOverview
RigorPilot Skills is an open standard agent skills framework that guides coding and research agents through reproducible deep learning workflows. It enforces strict separation between safe, trusted reproduction/analysis lanes and explicitly authorized exploration lanes. The project emphasizes verifiable evidence, structured debugging, and produces a unique annotated README detailing step-by-step execution results.
Capabilities
- ▸Reproduce repositories from README commands
- ▸Generate annotated README files with color-coded evidence links
- ▸Perform read-only project and repository analysis
- ▸Bootstrap environment, datasets, and model weights
- ▸Execute safe, diagnose-before-patch debugging
- ▸Run conservative training and evaluation verification
- ▸Conduct candidate-only research exploration via structured thinking loops
Best for
Reproducing deep learning research papers and repositories from README instructions, Auditing and analyzing project structures and entrypoints safely without making edits, Bootstrapping environments, datasets, and model weights, Running conservative evaluations, inferences, and training verifications, Conducting evidence-anchored candidate explorations under strict user authorization
Works with
Claude CodeCodexChatGPTGemini CLICursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
88Task 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%95 → +14.3
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%38 → +4.6
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%90 → +9.0
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%68 → +5.4
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 total88.3 / 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
The skill adheres to a strict two-lane model, preventing unauthorized code modifications or exploratory execution unless explicitly requested by the researcher.
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.