Data & AI skills

API reference: Combine. Query for publishers, subscribers, operators, async data streams.

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

統計検定の選択・仮定チェック・検出力分析・APA形式レポートを支援するスキル。 「統計分析をして」「t検定を実行」「適切な検定を選んで」等のリクエストで発動。

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

主要データウェアハウス方言で正確かつ高性能なSQLを記述するスキル。 「SQLを書いて」「クエリを最適化して」「BigQueryで集計」等のリクエストで発動。

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

Python (matplotlib, seaborn, plotly) でデータ可視化を行うスキル。 「グラフを作って」「チャート作成」「データを可視化して」等のリクエストで発動。 チャート選定、デザイン原則、アクセシビリティ対応も含む。

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

BigQuery/Snowflake接続、EDA、可視化、Marimoノートブック作成を行うサブエージェント。 データ分析関連の4つのルール（data_analysis, visualization, notebook, marimo_variable_naming）を統合。 「データ分析して」「BigQueryに接続」「EDAを実行」「Marimoで分析」等のリクエストで発動。

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

200以上のファイル形式に対応した探索的データ分析（EDA）スキル。 「データを分析して」「EDAして」「ファイルの中身を調べて」等のリクエストで発動。 ファイル自動検出、品質評価、統計サマリー、可視化推奨を含むレポート生成。

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

アナリティクスのトラッキング設定・改善・監査を支援するスキル。 「トラッキングを設定」「GA4を導入」「コンバージョン計測」「イベントトラッキング」「UTMパラメータ」「GTMの設定」等のリクエストで発動。 A/Bテスト計測は ab-test-setup を参照。

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

How to query a Well workspace correctly — discover the schema first, then query the right root. Use whenever the user asks about their invoices, companies, contacts, bank transactions, accounts, or accounting ledger in Well, or before writing any well_query_records call.

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

Generate diverse solution candidates with category-spanning ideation methods and rotation. Use when stuck on a design or fighting repetitive LLM output.

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

Merges ephemeral report and analysis artifacts into permanent documentation. Use when LLM-generated markdown files have accumulated and need consolidation.

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

Verifies math-heavy code for algorithmic correctness and numerical stability. Use when reviewing scientific algorithms, ML models, or numerical code.

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

Provisions the oracle ML inference daemon with onnxruntime via uv. Use when setting up local ONNX model inference for skill quality evaluation.

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

Shapes agent behavior via instruction framing and style transfer. Use when composing dispatch prompts or writing skill instructions for parallel review agents.

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

Analyzes changesets with risk scoring, categorization by type and impact, and release note preparation. Use when extracting insights from raw change data.

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

Delegates tasks to a locally served Muse Glimmer via ollama. Use when delegation-core selects glimmer or the prompt must not leave the machine.

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

Generates a Mermaid sequence diagram showing how data moves between components. Use when tracing request flows or documenting data transformation pipelines.

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

Applies data-grid architecture for high-traffic stateful workloads. Use when a single database cannot scale and in-memory partitioning is needed.

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

Stack Honey onto Superpowers-style subagent workflows: dispatched subagents skip the session hook, so inject the levers into each dispatch prompt.

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

Inject Honey levers into dispatched subagent prompts.

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

Stack Honey onto Superpowers-style workflows (subagent-driven-development, dispatching-parallel-agents, executing-plans) and any orchestration that dispatches fresh subagents. Dispatched subagents run in isolated context and do NOT inherit the session's Honey hook, so they emit full-fat code and verbose reports. Use when you are about to dispatch implementer/reviewer/fixer/parallel subagents: it gives the exact Honey directive to paste into each dispatch prompt, with a worker variant and a reviewer variant, so the levers apply inside the subagents too — where the multiplied cost actually is.

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

Honey for plain Claude — the terse-prose core with no agent-harness features. Paste into a claude.ai Project's custom instructions, a Style, or an API system prompt. Strips filler, hedging, and pleasantries from every response while keeping facts, names, numbers, steps, and code exact. No tools required.

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

Rewrite a memory or context file (CLAUDE.md, AGENTS.md, a todo or notes file) into Honey-terse form so it costs fewer input tokens every session, without losing meaning. Backs up the original first. Use when asked to shrink or compress context files, trim CLAUDE.md, or cut per-session input cost. Prose only — never code, config, or data.

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

Use davidsandberg/facenet for TensorFlow 1.x face recognition workflows: MTCNN alignment, embeddings, classification, LFW evaluation, training, and model export.

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

Use geemap for Google Earth Engine interactive mapping, geospatial conversion, visualization, timelapse, and ML helper workflows.

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