Checking Taiwan invoices manually can miss prize matches or use the wrong draw period. This skill guides official-source lookups, batch comparisons, and cloud prize verification.

Waste collection schedules and disposal rules differ across Japanese municipalities. This skill guides dataset lookups for local schedules and item classifications, with official-source referrals when information is missing.

Furusato nozei donation limits depend on income, household details, and tax deductions. This skill estimates your limit with published formulas, explicit assumptions, and intermediate calculations.

Daily plans can depend on rainfall at a specific location during the next hour. This skill guides assistants through public JMA radar data to report approximate rainfall intensity and short-term changes.

Preparing a friendship quiz requires collecting real preferences and mapping each choice to the correct answer. This skill guides ten preset choices, previews a local draft, and optionally publishes through Block You Test Me.

Using Cargo through an AI client requires correct authentication, workspace selection, and action inputs. This skill guides hosted MCP connections, cost inspection, batch execution, and result reporting.

Scattered documents make workspace knowledge difficult to maintain. This skill guides Cargo CLI workflows to upload, organize, and manage knowledge files and connector-backed libraries.

Configuring agents requires coordinating prompts, models, knowledge, tools, and releases. This skill guides Cargo configuration through documented CLI workflows and examples.

SEO decisions become difficult when site readiness, search metrics, and content plans are disconnected. This skill guides AltoRank tools to assess readiness, interpret stored metrics, and prepare drafts for human review.

macOS 工作流程經常需要在不同 App 之間重複點擊。此技能提供 Mail、Calendar、Safari、Finder 和系統控制項的 AppleScript 模式。

瀏覽器工作可能會讓主聊天充滿頁面狀態、截圖和請求記錄。此技能會將這些任務委派給 Chrome DevTools 代理，並返回精簡結果。

First drafts often miss requirements, edge cases, or clarity problems. This skill coordinates scored reviews and targeted revisions until a quality gate is met.

銷售團隊需要針對 HYBRID 潛在客戶進行一致的資格評估，並做好清楚的通話準備。此 skill 提供問題、評分、異議回應和銷售管道指標。

當團隊使用不同評分標準時，漏斗審查可能會變得不一致。此技能提供一套結構化的 NGX 評分規準，用於視覺、UX、文案與轉換稽核。

AI 代理在不同工作階段之間會遺失脈絡，並可能重複過去的工作。此技能會指示 Claude、Codex 和 Claude Code 在採取行動前搜尋先前對話。

在長時間程式設計工作階段中，終端機視窗會變得難以識別。此技能會在 Claude、Codex 和 Claude Code 工作流程中，使用專案與主題脈絡更新標題。

高階主管常常在回顧、目標與領導決策之間失去全局洞察。此技能會建立一套結構化的私人系統，用於反思、規劃與模式追蹤。

當頁面需要真實 Cookie、工作階段和互動式表單時，手動瀏覽器任務會很慢。這項技能可讓 Claude、Codex 和 Claude Code 透過瀏覽器橋接器驅動本機 Firefox 工作階段。

Unclear goals and changing priorities can make agent decisions diverge from your expectations. Align captures confirmed criteria in ALIGN.md and reviews meaningful changes against them.

在 Product Hunt 發布產品需要協調文案、視覺素材、時機與互動。此技能可將產品詳細資料轉化為結構化的準備工作與發布日計畫。