assess-rfe
opendatahub-io/assess-rfe
Assesses Jira Request For Enhancement (RFE) issues against quality criteria using automated pipelines and background LLM agents. Supports both single-issue checks and large-scale bulk evaluations.
Overview
This skill provides a structured framework for evaluating software feature requests and RFEs against a rigorous rubric. It integrates with Jira via MCP and REST APIs to fetch issues, caches data locally, and coordinates concurrent background evaluation agents to score items. Results are compiled into persistent run directories with CSV summaries, what-if analyses, and aggregated reporting.
Capabilities
- ▸Jira integration via Model Context Protocol (MCP) and REST API
- ▸Bulk issue fetching and markdown conversion
- ▸Parallel background agent dispatch for scalable scoring
- ▸Automated state tracking and resume capabilities
- ▸CSV score aggregation and statistical run summarization
Best for
Evaluating incoming Jira enhancement requests against predefined product quality rubrics, Bulk scoring entire Jira project backlogs to identify high-value or incomplete feature proposals, Running quick single-issue assessments via Jira keys, local documents, URLs, or raw text input
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
Requires access to Atlassian/Jira credentials via environment variables. Interacts with external Jira APIs and executes local Python utility scripts.
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.