Incorrect channel choices can cause duplicate deliveries, extra charges, failed fallback, and unsafe retries. This skill explains routing decisions and diagnoses outcomes from Sent evidence.

Sender Profile onboarding requires coordinated choices across identity, billing, channels, campaigns, callbacks, and access. This skill turns those choices into a guarded provisioning sequence.

Messaging integrations can fail through duplicate sends, unsafe retries, weak webhook validation, or incorrect credential scope. This skill provides a staged Sent v3 implementation and launch review.

Contact searches, bulk imports, and deletions can expose private data or modify the wrong records. This skill applies scoped lookups, minimal disclosure, and confirmation gates.

Messaging teams need consistent metrics for volume, deliverability, contacts, and number capabilities. This skill queries Sent analytics and explains trends within defined periods.

Messaging launches can fail when account scope, balance, or onboarding status is unclear. This skill checks those conditions through authorized Sent MCP tools.

Broad Sent requests can involve several channels, operations, and compliance workflows. This skill clarifies intent and routes each request to the appropriate specialist.

RCS launches require complete evidence, correct routing, and coordinated approval. This skill builds a reviewable checklist and guides controlled readiness tests.

CPaaS migrations often fail when provider concepts are copied without translation. This skill maps those differences into a phased Sent v3 cutover plan.

AI coding histories can retain credentials after they were shared with a model provider. This skill finds affected records while keeping reported secrets masked.

團隊需要可重複製作、且符合真實應用程式流程的逐步導覽影片。此技能會引導 Claude、Codex 和 Claude Code 完成 ScreenCI 腳本、旁白、測試與錄製。

當選擇器、同意橫幅或頁面流程不清楚時，瀏覽器測試設定可能會失敗。此技能會引導 Claude、Codex 和 Claude Code 透過 Playwright CLI 進行檢查，並執行可重複的自動化步驟。

手動網頁研究與爬取可能緩慢且不一致。此 skill 會引導 Claude、Codex 和 Claude Code 完成 ScrapeGraph CLI 工作流程。

當專案、職責與參考資料混在一起時，筆記就會失去價值。此技能會將 Obsidian 筆記分類到 PARA 類別，並提出安全的路由、metadata、審查與封存建議。

Using many AI providers requires separate integrations, keys, and billing workflows. SandBase offers one MCP interface for inference, media, search, scraping, and structured APIs.

Go 錯誤路徑經常遺失脈絡、重複記錄日誌，或暴露內部實作。這項技能為 Claude、Codex 和 Claude Code 提供具體規則，以實作更安全的 Go 錯誤處理。

Go 程式碼即使通過格式檢查，仍然可能難以閱讀。這項技能會引導 Claude、Codex 和 Claude Code 做出更清晰的風格選擇。

程式碼和代理程式輸出若缺乏明確訊號，可能會發生品質倒退。此技能記錄 Claude、Codex 和 Claude Code 的 Ruflo 驗證防護機制、真實性評分、報告和復原工作流程。

Mascot concepts often become detailed illustrations that fail at small sizes. This skill creates simple, product-relevant logo directions with consistent generation constraints.

複雜的軟體專案需要清晰的規劃、測試與審查。此技能透過結構化工作流程，引導 Claude、Codex 與 Claude Code 完成 SPARC 各階段。