Results for “spa”

Audit one datafusion-spark function against Apache Spark 4.2.0. Compare source code, accepted types, and edge cases, verify expected results with PySpark, then fix differences and record remaining gaps as issues and disabled tests.

• Auditing a function for Spark compatibility
• Checking NULL, overflow, and ANSI mode behavior
• Finding missing SQL test coverage

**未導入プロジェクト向け**の sparkle-design 初期導入・セットアップを支援するスキル。 npm インストール、sparkle-design-cli による初回 CSS 生成、sparkle.config.json の 新規作成、AI ガード（Sparkle Design Guard）の導入、コンポーネント選択ガイドまでをカバー。 **導入済みプロジェクトでテーマ（primary / font / radius）を変えたい場合は `change-sparkle-config` スキルを使うこと** — この setup スキルは初期導入専用。 「Sparkle Design を導入」「sparkle-design をインストール」「デザインシステムをセットアップ」 「コンポーネントライブラリを追加」「どのコンポーネントを使えばいい」で発動。 English: "install sparkle-design", "add sparkle design", "set up sparkle design", "which component should I use"

The English summary is being prepared. Showing the original description.

Build Apache Spark pipelines for large datasets, including transformations, aggregations, and streaming analysis. Get PySpark or Scala code, partitioning strategies for dividing data across workers, and configuration advice to investigate slow jobs and resource usage.

• Build a pipeline to transform and aggregate large datasets
• Investigate slow Spark jobs and uneven data distribution
• Tune memory settings and data partitions

Sparkle Design の UI コンポーネントを shadcn registry 経由でプロジェクトに追加するスキル。 パッケージマネージャの自動検出、設定バリデーション、コンポーネントインストール、 Storybook 統合、CSS セットアップ、トラブルシューティングをカバーする。 「Sparkle コンポーネントを追加」「sparkle-design のコンポーネントをインストール」 「@sparkle-design のセットアップ」「コンポーネントをどう追加する」 「registry の設定」「components.json の設定」への言及で発動する。 English: "add a sparkle button", "install sparkle-design card", "add @sparkle-design/input", "set up components from sparkle registry", "how do I install components", "registry setup"

The English summary is being prepared. Showing the original description.

sparkle-design（公開 npm パッケージ）の新バージョンをリリースするための手順スキル。 package.json の version bump、CHANGELOG.md の更新、リリース PR 作成、PR マージ後の npm への stage、メンテナーによる 2FA 承認（npm stage approve）、承認後の git tag・ GitHub Release 作成までを一連の手順で実行する。 CHANGELOG 更新漏れと GitHub Release 作成漏れを防ぐためのチェックリストを含む。 「sparkle-design をリリース」「sparkle-design の新バージョンを切る」「vX.Y.Z をリリース」 「sparkle-design の CHANGELOG を更新」で発動。 English: "release sparkle-design", "cut a new sparkle-design version", "publish sparkle-design", "bump sparkle-design version".

The English summary is being prepared. Showing the original description.

Write and review Gradio demos for Hugging Face ZeroGPU. Configure GPU time limits and dependencies, and troubleshoot errors caused by separate worker processes, shared state, concurrent requests, or CUDA package installation.

• Review GPU handlers in a Gradio demo
• Tune GPU duration and quota usage
• Fix PicklingError and stale state across worker processes

Audit GitHub Codespaces startup time and spending, then identify up to three evidence-based improvements to development containers, machine sizes, prebuilds, or idle timeouts, with validation results and expected impact.

• Investigating slow Codespaces startup
• Reviewing Codespaces spending
• Trimming unused development container components

Check ten recurring problems before or during machine learning runs on NVIDIA DGX Spark. Diagnose startup failures, out-of-memory errors, and falling throughput, with guidance on compatible environments, resource use, numeric formats, and training across two devices.

• Checking a DGX Spark before a long training run
• Diagnosing memory errors despite apparent free capacity
• Investigating throughput drops during training

Improve slow Apache Spark jobs by reviewing data partitions, caching, memory settings, and shuffles, which move data between workers. Use the guidance to investigate bottlenecks and tune pipelines for larger datasets.

• Investigating slow Spark jobs
• Tuning memory and executor settings
• Reducing data skew and shuffle traffic

Guides LLM compression through pruning, which removes selected model weights. Covers Wanda and SparseGPT methods without retraining, accuracy comparisons, and structured weight patterns that can accelerate inference on compatible hardware.

• Trying model compression without retraining
• Comparing accuracy before and after pruning
• Choosing between Wanda and SparseGPT

Build and maintain machine learning apps on Hugging Face Spaces. Choose a suitable app framework and computing hardware, load models, deploy files, and check logs and outputs to diagnose build or runtime problems.

• Publishing a machine learning demo
• Adapting an existing Gradio app for ZeroGPU
• Diagnosing Space build or runtime failures

Manage Workspace users, groups, and organizational units through gog. The skill guides account selection and command checking, with confirmation of the target and intended change before writes or deletions, plus preview checks for supported writes.

• Managing Workspace users
• Managing Workspace groups
• Managing Workspace organizational units

Work in a local or remote computer environment whose screen you can watch. Run commands, transfer files, launch coding agents, move signed-in app sessions, and share the host computer’s network when needed.

• Run tasks in an isolated environment you can watch
• Transfer files into and out of a Space
• Launch and monitor coding agents

Create and manage isolated GSD workspaces with repository copies and separate planning folders. Use one command to create an environment, review active workspace status, or remove a workspace and clean up its worktrees.

• Create a workspace with its own planning folder
• List active workspaces and review their status
• Remove an unused workspace and clean up worktrees

Reduce LLM weight usage through pruning, which removes selected model parameters. Explore Wanda and SparseGPT for compression without retraining, choose hardware-friendly patterns for faster inference, and compare the compressed model's accuracy with the original.

• Compressing an LLM without retraining
• Comparing pruning methods
• Exploring faster inference on supported hardware

Search LangBot Space for plugins, MCP servers, and skills through MCP, a protocol for connecting agents to tools. Inspect item details, check plugin usage compatibility, and review model availability to support setup decisions.

• Find LangBot plugins for agent workflows
• Browse MCP servers and skills
• Check model availability during setup

**導入済みの sparkle-design プロジェクト**で、ユーザーが目指したい「雰囲気」を 自然言語で伝えたら、`sparkle.config.json` の primary / font-pro / font-mono / radius を 書き換えて `sparkle-design-cli generate` まで実行するスキル。選択肢は Theme Settings Figma プラグインが扱える範囲（primary 7 色 / radius 8 段階 / fonts 11 種）に揃えて おり、Figma と CLI の見た目がずれません。**未導入プロジェクトの初期セットアップは `setup-sparkle-design`（internal 環境では `install-sparkle-design`）を使うこと。** 「雰囲気を変えたい」「もっとポップに」「ビジネスライクに」「高級感を出したい」 「primary を変えたい」「角丸をもっと丸く」「フォントを変えたい」「テーマを提案して」 「テナントごとに配色を変えたい」「役割ごとに色を出し分けたい」（後者2つは複数 バリアント要望として範囲外に誘導するために発動） で発動。English: "change the vibe", "make it more playful", "make it more business-like", "adjust the theme", "change primary color".

The English summary is being prepared. Showing the original description.

Manage Contentful spaces, the containers used to organize content, from Claude Code through Composio. List accessible spaces, inspect creation dates and current versions, rename spaces, and review the organization's space inventory.

• List all accessible Contentful spaces
• Check a space's metadata and current version
• Rename a Contentful space

Find and load Copilot Spaces, shared collections of project documents, code, and instructions, to answer team-specific questions or follow reporting workflows. Also create and update spaces, attached resources, and collaborator settings through the GitHub CLI.

• Find spaces available to a team
• Answer questions using project documentation
• Draft weekly updates from a space's workflow

Automate Google Workspace tasks with the gws command-line tool, including email, file management, spreadsheets, and scheduling. Get guidance on installation, authentication, reusable workflow templates, and security audits of sharing and account settings.

• Automating Gmail sending and inbox organization
• Managing Drive files and sharing permissions
• Reading and updating Sheets data

Manage Contentful spaces, the containers used to organize content, from Claude Code through Composio. List accessible spaces, inspect creation dates and current versions, rename spaces, and review the organization's space inventory.

• List all accessible Contentful spaces
• Check a space's metadata and current version
• Rename a Contentful space

Configure a repository for Superset so new isolated Git workspaces have dependencies, environment files, and service access ready. Create lifecycle scripts in .superset/config.json and verify the setup by starting a real test workspace.

• Prepare a repository for use with Superset
• Install dependencies automatically in new workspaces
• Provide environment files when creating workspaces

/dispatcher-handover で書き出した handover ファイルを読み込み、 ディスパッチャーを新しい session で復帰させる。/clear 直後の最初のターンで使う。 state.db の dispatcher_pane_id / dispatcher_peer_id を atomic に更新し、 worker monitoring の /loop 3m を再開する。 secretary が /clear の後にディスパッチャーペインへ /dispatcher-resume を打鍵したときに使う。 context-handover watcher が `/dispatcher-resume auto op=<OP>` を打鍵したときも使う。 /org-start ではない（ワーカー・窓口は生きている前提。キュレーターは常駐しない）。

The English summary is being prepared. Showing the original description.

Automate D2lbrightspace operations through Rube MCP, a connection for agent tools. The skill guides agents through discovering supported operations, checking the service connection, and executing tasks with current input formats and shared workflow sessions.

• Find supported tools for a D2lbrightspace task
• Verify the connection before running operations
• Run related operations within one workflow session