エラーや例外シナリオを顧客体験(CX)の観点で体系的に分析し、改善優先度を付ける スキル。6軸評価（影響度・頻度・復旧容易性・メッセージ品質・感情的影響・ ビジネスコスト）でスコアリングし、Impact vs Effort マトリクスで改善施策を 優先順位付けする。
Use when analyzing error scenarios from customer experience perspective, evaluating error message quality, prioritizing error UX improvements, or creating CX-focused error analysis reports. Triggers: "CXエラー分析", "error experience", "エラーUX改善", "customer experience error", "エラーメッセージ品質", "error scenario analysis", "顧客体験エラー評価"
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
CX Error Analyzer は、システムやアプリケーションのエラーシナリオを顧客体験（Customer Experience）の観点から体系的に分析・評価するスキルです。6軸の定量評価フレームワークにより、エラーが顧客体験に与える影響を可視化し、Impact vs Effort マトリクスで改善施策の優先順位を決定します。
This skill provides conversational guidance and analysis rather than file generation. Outputs include:
When formal documentation is needed, use Workflow 5 to generate a comprehensive report using the provided templates.
Enumerate and classify all error scenarios in the target system or feature.
Evaluate each error scenario across 6 dimensions using a 1-5 scale.
references/cx_evaluation_methodology.mdassets/cx_error_evaluation_template.md to record each evaluationCalculate weighted CX Scores and classify by severity tier.
Apply weights to each axis:
| Axis | Weight |
|---|---|
| Impact Severity (影響度) | 25% |
| Frequency (頻度) | 20% |
| Recovery Ease (復旧容易性) | 15% |
| Message Quality (メッセージ品質) | 15% |
| Emotional Impact (感情的影響) | 10% |
| Business Cost (ビジネスコスト) | 15% |
Calculate weighted CX Score (1.0-5.0) for each scenario:
CX Score = (Impact * 0.25) + (Frequency * 0.20) + (Recovery * 0.15)
+ (Message * 0.15) + (Emotional * 0.10) + (Business * 0.15)
Higher score = worse customer experience.
Classify by CX Score tier:
| Score Range | Tier | Action |
|---|---|---|
| 4.0-5.0 | Critical CX Issue | Immediate action required |
| 3.0-3.9 | Significant CX Issue | Plan improvement |
| 2.0-2.9 | Moderate CX Issue | Add to backlog |
| 1.0-1.9 | Minor CX Issue | Nice to have |
Rank all scenarios by CX Score descending
Refer to references/cx_metrics_reference.md for business impact estimation
Plot errors on an Impact vs Effort matrix to determine improvement priorities.
Assess implementation effort for improving each error scenario:
Plot on 2x2 matrix (Impact = CX Score, Effort = Implementation Difficulty):
High Impact ┌──────────────┬──────────────┐
│ Strategic │ Quick Wins │
│ Projects │ (Do First) │
│ │ │
├──────────────┼──────────────┤
│ Deprioritize │ Fill-Ins │
│ (Avoid) │ (Batch) │
Low Impact └──────────────┴──────────────┘
High Effort Low Effort
Identify Quick Wins (High Impact + Low Effort) for immediate action
Plan Strategic Projects (High Impact + High Effort) with proper roadmap
Suggest specific improvements for top priority items:
references/error_ux_best_practices.md for design patternsreferences/cx_metrics_reference.mdCompile all analysis results into a comprehensive CX Error Analysis Report.
assets/cx_error_report_template.mdreferences/cx_metrics_reference.md for ROI calculations| File | Purpose | When to Load |
|---|---|---|
references/cx_evaluation_methodology.md | Detailed scoring criteria for all 6 evaluation axes, error classification taxonomy, and data collection guidance | Workflow 2 (Multi-Axis CX Evaluation) |
references/error_ux_best_practices.md | Error message design principles, recovery flow patterns, emotional design, accessibility guidelines, and good/bad examples | Workflow 4 (Improvement Priority Matrix) when drafting improvements |
references/cx_metrics_reference.md | CX metrics (CES, CSAT, NPS), support cost formulas, churn risk estimation, industry benchmarks, and ROI calculation | Workflow 3 (CX Scoring) and Workflow 5 (Report Generation) |
assets/cx_error_report_template.md | Complete CX Error Analysis Report template with all sections and placeholders | Workflow 5 (Report Generation) |
assets/cx_error_evaluation_template.md | Individual error scenario evaluation card template for per-scenario assessment | Workflow 2 (Multi-Axis CX Evaluation) for each scenario |
User: ECサイトのエラー体験を改善したい。主要なエラーシナリオを分析してください。
Claude:
1. [Workflow 1] エラー棚卸し → ERR-001(在庫切れ), ERR-002(決済失敗),
ERR-003(セッションタイムアウト), ERR-004(住所バリデーション), ...
2. [Workflow 2] 6軸評価 → ERR-002(決済失敗)が最高スコア4.2: 影響度5, 復旧困難4, 感情5
3. [Workflow 3] CXスコア計算 → ERR-002: 4.2(Critical), ERR-003: 3.5(Significant), ...
4. [Workflow 4] 優先度マトリクス → Quick Win: ERR-004(メッセージ改善のみ、工数Low)
5. [Workflow 5] レポート出力: 改善提案8件、推定サポートコスト削減20%
User: ログイン・認証エラーのUXを改善したい。
Claude:
1. [Workflow 1] 棚卸し → ERR-001(パスワード誤り), ERR-002(アカウントロック),
ERR-003(2FA失敗), ERR-004(SSO連携エラー)
2. [Workflow 2] 各シナリオを評価 → ERR-002のメッセージ品質が5(最低: "Account locked"のみ)
3. [Workflow 4] Quick Win: ERR-002のメッセージ改善
Before: "Account locked. Contact support."
After: "セキュリティのためアカウントがロックされました。30分後に自動解除されます。
すぐにログインが必要な場合はパスワードリセットをお試しください。"
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Track and update action item status from natural language updates like 'Seanのメールには返信しておいた' or 'Lu対応予定'. Integrates with daily-comms-ops workflow. Use when managing action items across communication channels.
The English summary is being prepared. Showing the original description.
AI活用提案の専門コンサルタントスキル。LLM・AIエージェントの活用事例知識を基に、業界別、部門別、シーン別に最適なAI導入提案を行います。システム化、業務改善、効率化を得意とし、具体的な活用事例、期待効果、導入ステップを含む実践的な提案を提供します。Use when proposing AI/LLM adoption strategies for specific industries, departments, or business scenarios.
The English summary is being prepared. Showing the original description.
Generate AI-powered BPO service proposals for Japanese companies in the US market. Use when creating outsourcing proposals with AI service menus, ROI estimation, implementation roadmaps, and bilingual (JA/EN) proposal documents for 在米日系企業向けAI実装.
The English summary is being prepared. Showing the original description.
AI（LLM）が生成した日本語テキストの「AI臭」を検出・診断し、人間らしい文章にリライトするスキル。 Use when: 「AIっぽい文章を直して」「人間らしくリライトして」「AI臭を消して」「この文章をもっと自然にして」 「テキストのAI感を減らして」「機械っぽさを取りたい」 "make this sound more human", "remove AI tone", "humanize this text", "detect if this is AI-generated". 6つのAI特有パターン（視覚的マーカー、単調なリズム、マニュアル的構成、非コミット姿勢、抽象語の濫用、 定型メタファー）を正規表現ベースで検出し、0-100のAI臭スコアを算出。3つの人間化技法 （バランスを崩す・客観を崩す・論理を崩す）でリライトを実行する。 Note: 検出スクリプトは日本語テキスト専用。英語テキストの場合はClaude自身がreferences/を参照して分析・リライトする。
The English summary is being prepared. Showing the original description.
Generate audit-ready internal control design documents from As-Is business process inventories. Produces control IDs, assertion mappings, procedures, SoD analysis, KPIs, materiality thresholds, and implementation roadmaps. Use when building internal controls for new audit engagements, SOX/J-SOX compliance, or process improvement initiatives.
The English summary is being prepared. Showing the original description.
Review audit-related documents (control design documents, bottleneck analyses, requirements definitions, etc.) for quality, scoring them 0-100 with a severity-rated findings list. Use when reviewing audit documents, checking control design quality, or verifying cross-document consistency. Supports documents governed by US GAAP, IFRS, or J-GAAP.
The English summary is being prepared. Showing the original description.