
Dataform Bigquery
作者 gemini-cli-extensions2df10e25bbf7Apache-2.0215 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
Expertise in generating clean, correct, and efficient Dataform pipeline code for BigQuery ELT. Use this when creating or modifying Dataform pipelines, actions, or source declarations, when Dataform, SQLX, or BigQuery are mentioned in a transformation, when data needs to be ingested from GCS into BigQuery via Dataform, or when setting up a new Dataform project or configuring workflow_settings.yaml.
新增到 SourceWeft 工作區
- 在儀表板中開啟該技能,並將它新增到工作區。
- 為需要使用它的對話啟用該技能。
該技能僅含說明:不附帶任何可執行的腳本。
新增到 SourceWeft系統會先要求你登入,然後直接帶你回到這個技能。
讓你的代理程式來安裝
把這段提示詞貼上到 Claude Code、Codex、Cursor 或其他能執行命令的代理程式中,也可以貼上到 SourceWeft 對話裡。代理程式會閱讀這個技能的安裝說明,向你展示它的來源、授權條款和腳本情況,在你同意後用 SourceWeft CLI 安裝。
閱讀 https://sourceweft.com/skills/gh-gemini-cli-extensions-data-agent-kit-starter-pack-dataform-bigquery/install.md 中的說明,按說明安裝這個技能。安裝前先告訴我它的來源、授權條款以及是否附帶腳本,等我確認。修改我電腦上的其他任何內容之前也要先問我。用命令列自行安裝
適用於 Claude Code、Codex、Cursor 及其他本機代理程式。SourceWeft CLI 會從原始碼儲存庫中取得此處掃描過的那次提交,並根據掃描時記錄的雜湊值逐一驗證每個檔案。只要有任何不一致,就不會寫入任何內容。
npx @sourceweft/cli skills install gh-gemini-cli-extensions-data-agent-kit-starter-pack-dataform-bigquery新增 --agent claude-code、codex、cursor 或 universal 來選擇安裝給哪個代理程式(預設為 Claude Code)。
上游安裝器——未經 SourceWeft 驗證
開源的 skills 安裝器會取得同一個固定的提交,但不會根據 SourceWeft 記錄的雜湊值驗證檔案。
npx skills add https://github.com/gemini-cli-extensions/data-agent-kit-starter-pack/tree/2df10e25bbf7dba2570dce1b2e2e77870143969e/skills/dataform-bigquery來源與署名
來源:gemini-cli-extensions/data-agent-kit-starter-pack位於skills/dataform-bigquery提交2df10e2
授權條款: Apache-2.0
內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。
更多來自 gemini-cli-extensions/data-agent-kit-starter-pack 的技能

Schema Mapping
gemini-cli-extensions
為 ETL、ELT 或資料整合任務規劃來源到目標的結構描述對應,產出文件化的對應宣言。

Resolving Mcp Region Configs
gemini-cli-extensions
修復區域性 Google Cloud MCP 伺服器設定中未取代的區域佔位符,讓缺少的 MCP 工具得以註冊。

Notebook Guidance
gemini-cli-extensions
This skill guides the use of Jupyter notebooks for data analysis, exploration, and visualization, particularly with BigQuery. It outlines best practices for notebook execution and validation (supporting both cell-by-cell execution and full notebook generation depending on tool availability), library installation, and structuring notebooks for clarity. It also covers specific rules for data cleaning, plotting, and integrating with BigQuery SQL and machine learning workflows. Relevant when any of the following conditions are true: 1. The user request involves a data analysis, data exploration, data visualization, or data insights task that requires multiple steps, queries, or visualizations to answer. 2. The user explicitly requests a notebook (.ipynb). 3. You are creating, editing, or executing cells in a Jupyter notebook. 4. You need to query BigQuery from within a notebook. DO NOT use the Python BigQuery client library; instead, you MUST use the `%%bqsql` magics explained in this skill.

Ml Best Practices
gemini-cli-extensions
為機器學習筆記本提供逐步方案,涵蓋分群、預測、分類、迴歸與模型比較。

Managing Python Dependencies
gemini-cli-extensions
指導代理偵測 Python 專案的相依性管理器並正確安裝套件,而不是使用全域 pip。

Google Cloud Storage Fuse
gemini-cli-extensions
Mounts Cloud Storage buckets as a POSIX file system with Cloud Storage FUSE (gcsfuse). Use when you need to interact with gcsfuse — decide whether FUSE, native gs:// reads, or Filestore/Managed Lustre fits a workload, deploy tuned mounts on GKE, Compute Engine, or Cloud Run, enable and size the file, stat, and list caches, tune mount flags or config-file settings, apply workload profiles, keep ML checkpointing safe (rename atomicity, hierarchical namespace, close-time finalization, concurrent writers), or diagnose slow training, low throughput, or GCS bill spikes on existing mounts with gcsfuse metrics. Covers mount semantics, the gcsfuse CLI and config file, the GKE gcsfuse CSI driver (Workload Identity principal:// bindings, profile StorageClasses, sidecar sizing), and Cloud Run volume mounts. Don't use for bucket administration or data management without a mount (google-cloud-storage-basics) or for fully POSIX-compliant shared file systems (Filestore, Managed Lustre).
更多Data & Analytics技能

Content Strategy
anthropics
把 PayPal、QuickBooks 或 Square 的銷售資料轉成排序過的 30 天內容簡報。

Cash Flow Snapshot
anthropics
依據帳簿、支付平台或 CSV 資料產出 30/60/90 天現金流預測,含信心區間與具名風險提示。

Pipeline Review
anthropics
依階段檢視 CRM 銷售管道健康狀況,標記老化、停滯與高風險商機並檢查覆蓋率。

Metrics Review
anthropics
檢視產品指標,分析趨勢並與目標對比,產出附建議行動的指標計分卡。

Performance Report
anthropics
產出營銷成效報告,包含關鍵指標、趨勢分析、成功與不足之處,以及依優先順序排列的優化建議。

People Report
anthropics
根據人力資料產出員額編制、流失率、多元性與組織健康度等人才分析報告。