데이터·AI 스킬

任意のアプリのコードベースを解析して LLM API 呼び出し箇所を洗い出し、「1 回の処理(フロー)で どれだけのトークン/費用がかかるか」「N 件・DAU 規模でいくらか」を根拠付きで試算するスキル。 プロンプト/ツール定義/RAG/エージェントループ/キャッシュ/思考トークンまで合算し、無料 or 確認付き 有料の実測でグラウンディングする。成果物は Markdown レポート + 対話 HTML 計算機 + コスト JSON。 「このアプリの API コストはいくら」「モデル別/件数別の費用」「LLM の ROI 試算」「トークン数を数えて」 「1リクエストいくら」等で起動。既定スタックの必須スキルではない optional 群であり、AI 機能を含む要件で明示された場合、 または app-orchestrator が v1 前・AI 機能変更時の試算として指示した場合のみロードする。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

スキルを作成・更新・プロンプト改善するためのメタスキル。 **最初のアクションは必ず AskUserQuestion**（インタビュー深度確認）。 **collaborative**モードでユーザーと対話しながら共創し、抽象的なアイデアから具体的な実装まで柔軟に対応する。 **orchestrate**モードでタスクの実行エンジン（Claude Code / Codex / 連携）を選択。 Anchors（主要3件・全7件は references/anchors.md 参照）: • Continuous Delivery (Jez Humble) / 適用: 自動化パイプライン / 目的: 決定論的実行 • The Lean Startup (Eric Ries) / 適用: Build-Measure-Learn / 目的: 反復改善 • Domain-Driven Design (Eric Evans) / 適用: 戦略的設計・ユビキタス言語・Bounded Context / 目的: ドメイン構造の明確化 Trigger: 新規スキルの作成、既存スキルの更新、プロンプト改善を行う場合に使用。 スキル作成, スキル更新, プロンプト改善, skill creation, skill update, improve prompt, Codexに任せて, assign codex, 実行モード選択, IPC Bridge統一, safeInvoke/safeOn, Preload API標準化, contextBridge, Electron IPC pattern

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

アプリケーションに LLM API(OpenAI / Anthropic / Gemini 等)を組み込む際のコスト最適化・セキュリティ・運用の必須パターン集。 「AI機能を付けて」「AIで読み取り」「画像認識」「PDFから抽出」「OCR」「自動分類」「レコメンド」「AI連携」「OpenAI APIを使う」 「チャットボット」「LLMを組み込む」などの文脈で、新規アプリ・既存アプリを問わず必ず使用する。 ユーザーが「AI」と明示しなくても、非構造データ(画像/PDF/自由文)からの情報抽出・分類・判別の要件が含まれるなら必ずこのスキルを読むこと。 AI機能のコスト見積・APIキー管理・利用量ダッシュボードの設計・レビューでもトリガーする。 実測グラウンディング付きの費用試算が必要な場合は Skill llm-cost-simulator を併用。 既定スタック(社内業務アプリ、mvp-first)の必須スキルではない optional 群。上記の AI 要件が要件定義で明示された場合、 または app-orchestrator の要件フラグ「AI機能あり」で指示された場合のみロードする。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use Exasol JDBC-based virtual schemas for federated read-only access to external databases such as PostgreSQL, Oracle, MySQL, SQL Server, and DB2. Covers database-source adapter selection, `CREATE VIRTUAL SCHEMA`, `ALTER VIRTUAL SCHEMA`, `EXPLAIN VIRTUAL`, metadata refresh, and query-side troubleshooting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Distributed machine learning, data mining, and iterative HPC with Exasol. Covers end-to-end ML pipelines (DISTRIBUTE BY + SET scripts + BucketFS), per-entity federated training with partial_fit and ctx.reset(), batch inference, map-reduce ensemble training, distributed ensemble and SON algorithm for frequent itemset mining (Apriori, FP-Growth, association rules, market-basket analysis), Lua execute script orchestration for iterative algorithms (k-means, SGD, gradient descent), scikit-learn model training, parallel hyperparameter search, per-entity forecasting, anomaly detection, model lifecycle in BucketFS (pickle/joblib/ONNX versioning), GPU acceleration via CUDA SLCs (PyTorch/TensorFlow/RAPIDS), and ML-specific performance tuning (skew, OOM, multi-pass chunking).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Top-level router for Exasol work. Use for any Exasol database, exapump, SQL, BucketFS, extension, integration, UDF, Script Language Container, or Exasol Personal setup task, then route to the narrowest specialized Exasol skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Take ONE specific bookmark URL and explore the neighborhood around it — tags, SIMILAR_TO neighbors, community peers — plus optionally WebFetch the page itself to summarize it. Use whenever Ahmad pastes a single URL and asks "what's near this", "tell me about this one", "expand this bookmark", "dig into this", "what else did I save like this", "give me the context for this URL". Triggers on "expand", "neighbors of", "what else like this", "dig into this URL", "context for this", and any message that's just a URL plus a short prompt.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Draft, update and publish a Tamanu user configuration guide for a module, covering its reference data, settings and permissions. Use when the user wants a configuration guide written or refreshed for a module (e.g. "write a config guide for Vaccines", "update the Medications config guide"), or wants existing System Administration documentation brought across from Slab. Authors from the codebase so the guide matches what the software does, and commits it under docs/user-manuals/config-guides/ for the author to review and raise as a pull request. Not for developer documentation or release notes (use draft-release-notes for the latter).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan or implement retirement of a system, API, feature, persisted configuration, or database shape. Use for compatibility cutovers, explicit deprecation review, or an explicit unreleased replacement decision, including determining whether consumers or data exist; not ordinary dependency bumps, local renames, prose edits, or generic architecture discussion.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Trace what an actual code change could break beyond its diff when interfaces, serialized data, database schemas, configuration, caches, lifecycle ordering, or cross-language consumers are involved. Use for explicit impact analysis; not local renames, prose edits, ordinary dependency bumps, or generic architecture discussion.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Seed or import data into the Convex database.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Suggest the matching Convex component when the user hand-rolls a pattern it already solves (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync). Passive — suggest after the task, never interrupt. Never install without consent.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user says /localstop, localstop, stop localhost for this app, /localstopall, localstopall, or asks to stop local development servers for this Teleprompt app.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Explain an existing Convex app — data model + relationships, public vs internal functions, auth/ownership model, components, a request→data flow — read from the schema and function surface. Read-only.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up Convex backups and run a restore DRILL that proves recovery — snapshot, restore into a throwaway preview, assert the data came back — plus a schedule matched to your RPO and a gated recovery runbook.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plans Convex schema and data migrations with widen-migrate-narrow and @convex-dev/migrations. Use for breaking schema changes, backfills, table reshaping, or zero-downtime rollouts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan and execute Convex schema migrations safely, including adding fields, creating tables, and data transformations. Use when schema changes affect existing data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Suggest the matching Convex component when the user hand-rolls a pattern it already solves (crons, sharded-counter, rate-limiter, storage, search, presence, workflow, RAG, prosemirror-sync). Passive — suggest after the task, never interrupt. Never install without consent.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plan and execute Convex schema migrations safely, including adding fields, creating tables, and data transformations. Use when schema changes affect existing data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Set up Convex backups and run a restore DRILL that proves recovery — snapshot, restore into a throwaway preview, assert the data came back — plus a schedule matched to your RPO and a gated recovery runbook.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Plans Convex schema and data migrations with widen-migrate-narrow and @convex-dev/migrations. Use for breaking schema changes, backfills, table reshaping, or zero-downtime rollouts.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.