run-manager
Manage FABER workflow run lifecycle - create, query, resume, rerun runs
Manage FABER workflow run lifecycle - create, query, resume, rerun runs
RICE scoring framework for ruthless feature prioritization. Evaluates features against strategic objectives, customer value, and resource constraints. Produces prioritized product roadmap with clear rationale for what to build first, defer, or kill.
对spec.md、plan.md和tasks.md三个核心文档进行非破坏性跨工件一致性和质量分析。在任务生成后识别不一致、重复、模糊和规范不足的项目。触发词包括:"speckit-analyze"、"speckit分析"、"文档一致性分析"、"规范分析"、"质量检查"、"工件分析"、"spec分析"、"plan分析"、"task分析"。
Analyze and resolve Sentry comments on GitHub Pull Requests. Use this when asked to review or fix issues identified by Sentry in PR comments. Can review specific PRs by number or automatically find recent PRs with Sentry feedback.
High-level MindManager mindmap operations via the mindm-mindmap CLI or python -m mindmap.actions. Use when a map must be read (mindmap, selection, grounding info), serialized to Mermaid, or created from Mermaid.
Prepare comprehensive briefings for upcoming meetings
Template and formatting guidelines for security audit reports. Provides consistent structure for findings, severity classification, ASVS mapping, and remediation recommendations.
ユーザーから与えられたタスクを単一責務の原則に基づいて分解し、 Phase 1からPhase 13までの実行可能なタスク仕様書ドキュメントを生成する。 スキル選定は仕様書作成時に動的に行う。使用するスキルはタスクの性質に応じて 現在利用可能なスキル(.claude/skills/)から選定する。 Anchors: • Clean Code (Robert C. Martin) / 適用: 単一責務の原則 / 目的: タスク分解の基準 • Continuous Delivery (Jez Humble) / 適用: フェーズゲート / 目的: 品質パイプライン構築 • Domain-Driven Design (Eric Evans) / 適用: ユビキタス言語 / 目的: 一貫した用語設計 Trigger: タスク仕様書作成, タスク分解, ワークフロー設計, 実行計画作成 Use when creating task specifications for complex development tasks.
Use when PRD/TRD contains architectural decisions to document - extracts decisions from refined requirements (architecture choices, data model decisions, API patterns, technology selections, integration strategies, reuse patterns) and generates MADR-format ADRs. One ADR per decision point. Also use when asked to document decisions, create decision records, or retrospectively capture architectural choices.
加载项目上下文,列出现有规范与变更,搜索能力与需求。用于用户询问项目状态、现有规范、进行中的变更、可用能力或需要发现上下文时。触发词包括"openspec上下文", "有哪些规范", "显示变更", "列出能力", "项目上下文", "查找规范", "规范包含什么", "展示规范"。
ベストプラクティスの収集・評価・統合・更新を体系化するスキル。 情報源の信頼性評価、品質スコアリング、統合パターンを用いて知識ベースを改善する。 Anchors: • The Pragmatic Programmer / 適用: 実践的改善 / 目的: 継続的な品質向上 • Evidence-Based Management / 適用: 評価基準 / 目的: 判断の一貫性を担保 • Knowledge Management (Nonaka) / 適用: 知識統合 / 目的: 暗黙知の体系化 Trigger: Use when collecting best practices, assessing source credibility, scoring quality, integrating guidance, or updating knowledge bases.
Proactively captures significant work into the journal for future reference
Matches targets against configured patterns for work-ID-free planning
システム障害・インシデントの検知から解決、事後分析までを体系的に支援。ITIL・SRE原則に基づき、迅速な復旧と再発防止を実現。 Anchors: • The Site Reliability Workbook (Google) / 適用: ポストモーテム文化 / 目的: 非難なき事後分析と学習 • ITIL 4 / 適用: インシデント・問題管理 / 目的: 構造化されたエスカレーション • The Phoenix Project (Kim, Behr) / 適用: 変更管理 / 目的: 変更起因インシデントの予防 Trigger: Use when responding to system outages, handling alerts, writing incident reports, conducting postmortems, or analyzing root causes. incident, outage, postmortem, RCA, 5 whys, rollback, escalation, severity, on-call
SLO(Service Level Objective)とSLI(Service Level Indicator)の設計、 エラーバジェット管理、信頼性目標の策定を支援するスキル。 Googleの SRE プラクティスに基づき、適切な信頼性目標を設計する。 Anchors: • Site Reliability Engineering (Google) / 適用: SLO/SLI設計原則 / 目的: 信頼性目標の最適化 • The Site Reliability Workbook (Google) / 適用: 実践的なSLO実装 / 目的: 運用可能なSLO設計 • Implementing Service Level Objectives (Hidalgo) / 適用: SLO成熟度モデル / 目的: 段階的導入 Trigger: Use when designing SLOs, defining SLIs, calculating error budgets, or establishing reliability targets. SLO design, SLI definition, error budget, reliability target, service level objective
Troubleshoot and resolve OrcaFlex static analysis convergence issues. Diagnose common problems including line connectivity, tensions, environmental conditions, and numerical instabilities.
TODO list discipline for task tracking. Activates for multi-step tasks (3+), complex work, or when systematic organization is needed. Use for tracking progress and ensuring completeness.
Assign and unassign issues to users (CLI not yet available)
Generate a project tree annotated with context.md notes to help future sessions, (auto-call at session start)