kumewata
36 verified skills
terraform-style-guide
Generate Terraform HCL code following HashiCorp's official style conventions and best practices. Use when writing, reviewing, or generating Terraform configurations.
development
dbt
dbt Expert Engineer Skill - Comprehensive guide for dbt development best practices, command execution, and environment configuration Use when: - Running dbt commands (debug, compile, run, test, show) - Setting up Issue-specific targets in profiles.yml - Working with Databricks SQL dialect in dbt
development
steering-lakeview-handoff
Lakeview ダッシュボード開発で Genie Code に渡す lakeview-handoff.md を生成・更新するスキル。 Claude Code / Codex 側で SQL とデータセット設計を確定した後、ウィジェット実装を Genie Code に委譲するためのハンドオフ契約書を作る。 Genie Code 側の同名スキル (steering-lakeview-handoff) と対称関係。 Use when: - Databricks Lakeview ダッシュボードの SQL/データセット設計が完了し、Genie Code にウィジェット実装を渡したいとき - lakeview-handoff.md を生成・更新したいとき - Genie Code が追記した Implementation Log を pull 後に読み込み、feedback memory に反映したいとき
development
lakeview-pitfalls
Lakeview ダッシュボードのウィジェット JSON 編集時に踏みやすい pitfall の回避策と共通ルールを提供する参照スキル。 ウィジェット編集前に必ず読むこと。 Use when: - Lakeview ウィジェットの JSON を編集するとき - bar / line / table / pivot / counter / pie のいずれかを扱うとき - 30KB を超える JSON のデプロイが必要なとき - encoding type / NULL 表示 / 数値整形 / filter の設計判断をするとき
tools
bigquery
BigQuery Expert Engineer Skill - Comprehensive guide for GoogleSQL queries, data management, performance optimization, and cost management Use when: - Running bq commands (query, load, extract) - Writing GoogleSQL queries (functions, JOINs, CTEs) - Designing partitioned/clustered tables - Using BigQuery ML or external data sources
development
databricks
Databricks Expert Engineer Skill - Comprehensive guide for data engineering, machine learning infrastructure, and permission design Use when: - Running databricks CLI commands (auth, api) - Executing SQL queries via Databricks SQL Warehouse - Working with Unity Catalog permissions - Managing Lakeflow Jobs or Delta Lake
tools
snowflake
Snowflake Expert Engineer Skill - Comprehensive guide for Snowflake SQL queries, data investigation, performance analysis, and Snowflake CLI (snow) usage Use when: - Running snow CLI commands (sql, object, connection) - Writing Snowflake SQL queries (functions, JOINs, CTEs, window functions) - Investigating data in Snowflake warehouses - Analyzing query performance (Query Profile, QUERY_HISTORY) - Using Snowflake MCP for agentic data operations
tools
steering-lakeview-handoff
lakeview-handoff.md を読み、Lakeview ダッシュボードのウィジェット JSON を編集する実装側スキル。 Claude Code / Codex 側が生成した handoff ファイルの指示に従い、ウィジェットを実装し、 完了後に Implementation Log を追記する。Claude Code 側の同名スキルと対称関係。 Use when: - Lakeview ダッシュボード作業を依頼され、対応する steering task dir に lakeview-handoff.md が存在するとき - ウィジェット JSON の追加・変更・修正をするとき - 作業完了後に Implementation Log を残すとき
development
codex-delegate
Use when the user wants a second opinion or review from Codex on code, docs, diffs, or design notes without modifying files. This includes implementation review, bug risk review, security review, and document clarity review through `codex exec`. Do NOT use for tasks that require file edits or direct implementation; keep this skill review-only. Trigger especially when the user says review with Codex, second opinion, delegate review, use codex, or check this diff or document.
development
orchestrate
Use when the user wants a complex implementation, bug fix, refactor, or security-sensitive change to be handled in multiple explicit phases with planning, review, and handoff artifacts instead of one straight-line execution. Do NOT use for simple fixes, single-file edits, or tasks that do not need staged review. Trigger especially when the user asks for orchestration, phased execution, planner plus reviewer flow, multi-agent workflow, or asks to use orchestrate.
development
claude-config-optimizer
Use when editing or reviewing Claude Code configuration artifacts such as CLAUDE.md, rules, skills, agents, commands, or settings, or when the user asks for Claude Code configuration best practices, changelog review, new features, or breaking changes. Do NOT use for Codex-only configuration changes unless the task also affects shared agent assets in this repository. Trigger especially when the user mentions CLAUDE.md, Claude Code settings, rules, hooks, agents, commands, changelog, updates, or config optimization.
development
waza-eval
Use when creating a new skill or making a substantial change to an existing skill and you also need to design, update, or review Waza-based executable evaluations. This includes deciding whether Waza is warranted, mapping `evals.json` cases into Waza tasks, choosing fixtures and graders, selecting a valid model with `waza models --json`, and running a local-first `waza run` workflow. Do NOT use for installing the Waza CLI itself or for general skill-authoring advice that does not involve Waza; use `skill-creator` for skill design and this skill for the Waza execution layer. Trigger especially when the user mentions Waza, `waza run`, `waza models`, executable evals, compare, graders, fixtures, or wants to validate a skill change with model-backed evaluation.
tools
cc-delegate
Use when the user wants Codex to ask Claude Code for a second opinion or review on code, docs, diffs, PR changes, or design notes without modifying files. This delegates bounded review-only analysis through the Claude Code CLI (`claude -p`). Do NOT use for implementation or file edits; keep this skill review-only. Trigger especially when the user says ask Claude, ask Claude Code, cc-delegate, Claude review, second opinion from Claude, compare Codex and Claude, or review this diff/document with Claude Code.
tools
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
content-media
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
testing
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
development
difit
Git diff viewer with browser-based UI. Use when: - Reviewing code changes before commit or PR - Comparing branches or commits visually - User mentions "difit", "diff viewer", or asks to review changes in browser
development
draw-io
draw.io diagram creation, editing, and review. Use for .drawio XML editing, PNG conversion, layout adjustment, and AWS icon usage.
devops
frontmatter
任意のドキュメントに YAML Front Matter を追加し、ドキュメント検索を効率化するためのスキル。技術ドキュメント、設計書、メモ、タスク管理の4種類のテンプレートを提供。
data-ai
nix
Nix commands and package management guide. Use when: - Running nix build, nix run - Adding custom packages - Using nurl for hash acquisition
development
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
content-media
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
testing
review-assist
Use when the user wants help understanding and reviewing a PR in an unfamiliar domain, needs background explanation of PR changes and surrounding code conventions, wants AI-assisted research for human-only review judgments such as architecture, business logic, security/privacy/authorization, data model, operational impact, or needs to determine whether to escalate the review to a domain expert. Trigger especially when the user says "help me understand this PR", "explain this PR", "who should review this", "review support for unfamiliar code", "PRのレビューを手伝って", "このPRの背景を教えて", "人間が見るべき観点を整理して", or asks for review guidance with context about being unfamiliar with the domain. Do NOT use for automated code review (use codex-delegate instead), posting review comments directly to GitHub (use github skill), or local git-only operations without a PR context.
development
terraform-refactor-module
Transform monolithic Terraform configurations into reusable, maintainable modules following HashiCorp's module design principles and community best practices.
development
terraform-test
Comprehensive guide for writing and running Terraform tests. Use when creating test files (.tftest.hcl), writing test scenarios with run blocks, validating infrastructure behavior with assertions, mocking providers and data sources, testing module outputs and resource configurations, or troubleshooting Terraform test syntax and execution.
testing
terraform
Terraform Expert Engineer Skill - Comprehensive guide for Infrastructure as Code, resource management, module design, and state management Use when: - Running terraform init, plan, apply, destroy - Managing Terraform state (import, move, rm) - Designing modules or configuring backends - Working with HCP Terraform / Terraform Cloud
development
xlsx
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
development
gws
Google Workspace CLI (`gws`) を使って Google スプレッドシート・ドキュメント・スライドを参照・編集するためのスキル。 Use when: - ユーザーが Google Sheets / Docs / Slides の URL（`docs.google.com/spreadsheets/d/...` / `docs.google.com/document/d/...` / `docs.google.com/presentation/d/...`）を貼り付けた、または ID を渡したとき - 「このスプレッドシートを要約して」「A 列の値を見せて」「タブ X の中身は？」「このセルを更新して」「行を追記して」等、Sheets の読み書きを依頼されたとき - 「この Doc をレビューして」「この Google ドキュメントの本文を Markdown で」等、Docs の本文が欲しいとき - 「このスライドのタイトル一覧」「5 枚目の内容」等、Google Slides の内容参照を依頼されたとき - URL は無いが特定の Google Workspace ファイル（Sheets/Docs/Slides）を名前で探す必要があるとき - `gws` コマンドを実行する、または出力を解釈するとき Do NOT use when: - Google API を Python / Node SDK から直接呼ぶ場合（本スキルは CLI 実行が前提） - ユーザーがブラウザ操作を希望している場合 - 汎用の Google Drive 管理（権限、共有、フォルダ構成）が主目的で Workspace ファイル内容は触らないとき
tools
tone
Use when the user asks for help drafting a GitHub PR description, a PR review comment, or a Slack post in their own tone (i.e., their personal writing voice). The skill detects the context (formal for PR / review, casual for Slack) and target_type (pr_description, pr_review, slack), drafts the body with an explicit reflection step that avoids verbose, mechanical phrasing, and stages the draft to `~/.local/state/tone/drafts/` via `tone-stage-draft.sh`. The user later runs `/tone-capture <url>` after posting, which pairs the staged draft with the final body to build a corpus for future tone tuning. Trigger especially when the user mentions PR description, PR review comment, Slack post, または「文を書いて」「文面を作って」「自分らしく」「トーン」「tone」.
development
airflow
Airflow DAG development skill for writing, reviewing, testing, and debugging Apache Airflow workflows. Use whenever the user mentions Airflow, DAGs, tasks, operators, sensors, schedules, retries, catchup, DAG import errors, DAG parse performance, or workflow orchestration in Python. Also use for Amazon MWAA / Managed Workflows for Apache Airflow work, including MWAA DAG deployment, requirements.txt, plugins.zip, aws-mwaa-docker-images, S3 DAG folders, CloudWatch logs, and MWAA-specific dependency or IAM issues.
tools
github
Use when the task is primarily about GitHub operations through gh CLI, such as working with issues, pull requests, review comments, inline comments, sub-issues, or fetching PR diffs with line numbers. Do NOT use for local Git-only workflow questions that do not touch GitHub; use the git skill for those. Trigger especially when the user mentions GitHub, gh, issue, pull request, PR review, inline comment, review reply, or diff with line numbers.
tools
git
Use when the task is primarily about Git operations or Git workflow, such as writing commit messages, creating or switching branches, understanding rebase or cherry-pick flow, inspecting history, or deciding how to structure commits. Do NOT use for GitHub-specific actions like PR comments or issue updates; use the github skill for those. Trigger especially when the user mentions commit, branch, rebase, cherry-pick, stash, merge, or Conventional Commits.
testing
steering
Use when the user asks for a plan, implementation checklist, task breakdown, progress tracking, or a durable task artifact for a non-trivial task. Also use when creating or updating steering documents such as requirements, design, or tasklist files under ~/.local/state/steering. Do NOT use for simple Q&A, lightweight investigation with no artifact, or single-file obvious edits that do not need planning. Trigger especially on requests like "改善プラン", "実装計画", "タスクリスト", "進捗管理", or "steeringを使って".
testing
index-generator
指定ディレクトリの YAML Front Matter を持つ Markdown ファイルをスキャンして INDEX.md を自動生成するスキル。プロジェクト一覧、タグインデックス、キーワードインデックスを構築し、doc-search エージェントの Level 1 検索を有効化する。
documentation
codex-insights
Generate a private monthly Codex usage and workflow insights report from local ~/.codex/sessions JSONL without exposing raw transcripts. Use when the user explicitly asks for $codex-insights, Codex insights, monthly AI-agent usage review, or a Codex replacement for Claude Code /insights.
development
databricks-steering-sync
Databricks Workspace とローカルの steering ドキュメントを同期する。 push（ローカル → Databricks）と pull（Databricks → ローカル）の両方向に対応。 pull 時は diff を解釈してローカルファイルにマージする。 Use when: - steering ドキュメントを Databricks Genie Code に同期したいとき - Databricks 上の変更をローカルに取り込みたいとき - ユーザーが「databricks に同期」「Genie に push」「pull して」と言ったとき
development