メニュー
Voice, tone, and content guidelines for data/ML dashboards. Covers microcopy, error messages, success states, and data presentation language. Auto-invokes on copy, messaging, content, labels, error messages keywords.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Coordination protocol for main Claude Code agent. Explicit user invocation required ("mobilize agents", "coordinate", "check registry"). Provides agent orchestration, registry management, and handoff protocols. Subagents never access this - main agent provides context in task prompts.
Unified design system for data/ML dashboards. Quick reference for brand vs data color decisions, component patterns, typography, spacing. Auto-invokes on styling, CSS, design, colors, UI, visualization keywords. Tiered loading - core always, philosophy/implementation on-demand.
Data quality validation rules, quality metrics, and acceptance criteria for Somali dialect classifier datasets. Covers duplicate detection, language filtering, quality scoring, and validation protocols. Auto-invokes when discussing data quality, validation, cleaning, or quality guardrails for this project.
ETL workflow patterns, data pipeline architecture, and ingestion strategies for Somali dialect classifier. Covers source integration, transformation logic, staging patterns, and load strategies. Auto-invokes when discussing data pipelines, ETL, ingestion workflows, or data processing architecture.
WCAG AA accessibility checklist and verification protocols for Somali dialect classifier dashboard. Covers keyboard navigation, screen readers, color contrast, ARIA labels, and accessibility testing procedures.
Reusable React/JavaScript patterns for Somali dialect classifier dashboard. Covers Chart.js integration, data card components, filter patterns, responsive layouts, and dashboard-specific UI patterns. Auto-invokes when building dashboard components, charts, data visualizations, or dashboard UI.
| name | ux-writing |
| description | Voice, tone, and content guidelines for data/ML dashboards. Covers microcopy, error messages, success states, and data presentation language. Auto-invokes on copy, messaging, content, labels, error messages keywords. |
| allowed-tools | Read |
| Context | Tone | Example |
|---|---|---|
| Executive | Strategic, narrative | "ML models require quality data for production performance" |
| Analyst | Precise, data-rich | "Retention: discovery → silver dataset" |
| Error | Calm, solution-focused | "Unable to load metrics. Check connection and refresh." |
| Success | Confirming, brief | "Pipeline completed successfully." |
Structure: Problem + Solution
Structure: Explanation + Action
Be specific: "Loading dashboard..." not "Loading..."
Describe: "Bar chart showing training data distribution" Not: "Image of chart"
Specific: "View dataset documentation" Not: "Click here"
| Use | Avoid |
|---|---|
| Dataset | Data set |
| Pipeline | ETL process |
| Real-time | Realtime |
| Training data | Train data |
Version: 2.0.0
