Suggest

作者 get-convex6ca54f6e2e75無授權條款6 個星標收錄於 2026年10月8日更新於 2026年10月8日儲存庫今天更新

Proactively suggest the right Convex component when the user hand-rolls what already exists: setInterval polling → crons, counter increments → sharded-counter, .collect() counts → aggregate, email → resend, DB-counter rate limiting → rate-limiter, uploads → storage, search, presence, multi-step actions → workflow, vector DB → rag, collaborative editing → prosemirror-sync. TRIGGER on noticing the pattern in a Convex app, AFTER completing the user's request. NEVER for non-Convex code.

AI 產生的概覽

當 Convex 應用重複實作既有元件功能時,主動建議合適的 Convex 元件。

功能
此技能會觀察 Convex 應用程式的程式碼與使用者請求,找出與現有 Convex 元件重複的模式,例如輪詢計時器、計數器遞增或寄送電子郵件。在完成目前任務後,它會提出單一建議,指出一個元件、引用觸發該建議的程式碼,並說明該元件為何更合適。它會提供安裝提示,且僅在使用者明確同意後才繼續。
適用情境
適用於在 Convex 程式碼庫中工作時,發現程式碼或意圖重新實作了 Convex 元件已提供的功能。它應在使用者目前請求完成之後執行,而不是打斷該請求。不應用於非 Convex 程式碼或一般程式設計問題。
執行需求
無指令碼,僅為說明性指示。它假定處於 Convex 專案環境,並引用位於 generators/suggest-detector.mjs 的偵測規則檔案,該檔案未包含在技能資料夾中。

Proactively suggest the right Convex component

When you see code or intent that duplicates what a Convex component already does, surface a targeted suggestion: ONE component, WHY (anchored in the user's own code or ask), and a concrete install hint. Never install without explicit consent. Never suggest more than one component at a time unless the user asks.

Steps

  1. Observe the codeSnippets and userAsk passively — never block the current task to suggest.
  2. Match against the detector rules (see generators/suggest-detector.mjs): email/SMTP → resend; push notifications → expo-push; setInterval/cron → @convex-dev/crons; shared counter increments → @convex-dev/sharded-counter; .collect().length scans → @convex-dev/aggregate; multi-step/long-running actions → @convex-dev/workflow; bounded concurrency → @convex-dev/workpool; rate-limit counters in DB → @convex-dev/rate-limiter; fs.write/S3 uploads → Convex Storage; Elasticsearch/Algolia → built-in full-text search; presence/typing → @convex-dev/presence; Pinecone/external vector DB → @convex-dev/rag; collaborative editing → @convex-dev/prosemirror-sync.
  3. After finishing the current task, offer ONE suggestion: name the component, quote the specific code or phrase that triggered it, explain why the component fits better.
  4. If the user says yes: run /add <component> or follow the installHint from the detector.
  5. If the user says no or ignores it: drop it. Do not repeat the same suggestion.

Rules

  • Passive — never interrupt the current task; surface the suggestion AFTER completing what the user asked.
  • One at a time — pick the highest-priority match; do not dump a list of five components.
  • Cite WHY from the user's own code or ask — 'I noticed you wrote post.likes + 1 in a mutation that many users call concurrently; that causes OCC conflicts at scale.'
  • Never install without explicit consent — suggest, explain, wait for a yes.
  • Do not suggest a component the user has already installed.
  • Do not fire on generic coding questions unrelated to Convex (sorting arrays, writing CSS, etc.).

來源與署名

來源:get-convex/convex-backend-skill位於skills/suggest提交6ca54f6

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架