cellm
getcellm/cellm
A systematic triage skill for resolving Sentry production bugs through root cause analysis, failing tests, and minimal fixes.
Overview
This skill guides an AI assistant through a rigorous 7-phase process to triage, investigate, classify, and fix Sentry production issues. It emphasizes finding the root cause before writing code, distinguishing between user-specific environmental errors and real software bugs, and strictly enforcing test-driven development (TDD) principles with mandatory failing tests.
Capabilities
- ▸Fetch and rank unresolved Sentry issues by frequency and impact
- ▸Analyze issue events, stack traces, and run Seer analysis
- ▸Classify errors into user-specific or code-level categories
- ▸Formulate verified root-cause hypotheses
- ▸Implement test-driven bug fixes in .NET environments
Best for
Triaging high-impact production bugs from Sentry, Debugging unresolved error reports with stack traces and event logs, Writing failing unit or integration tests to reproduce bugs before fixing them, Classifying issues as environment-specific or genuine code defects
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
Interacts with production error reporting and issue trackers via Sentry MCP tools. Requires appropriate API access tokens and organization permissions.
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.