5.7K skills · sorted by relevance
Helps add Apache 2.0 license headers to new Apache Beam files using the correct comment format and placement. Covers source files, configuration, documentation, and local checks for missing license notices.
Check article and file availability through the NCBI PMC Open Access service using supported article identifiers. Receive a concise metadata summary, with the option to save the original XML response when you need the full service output.
Create and refine YAML prompts for AI assistants using structured roles, requirements, and output instructions. Organize reusable templates with variable placeholders, and check indentation, braces, headings, and formatting for consistency.
Write and review GitHub Actions workflows for syntax and structural correctness. Check quoting around expressions and special characters, then validate with actionlint, a workflow checker, to catch errors that ordinary YAML parsing can miss.
Create an interactive HTML implementation plan that connects proposed behavior to mockups, code, and data structures. Readers can explore details, choose options, edit schemas, and return comments before development starts.
Build a reproducible Stata analysis from data cleaning through modeling, diagnostic checks, and robustness tests. Generate runnable .do files, regression tables, and figures for empirical papers, with additional workflows for epidemiology and machine learning approaches to causal inference.
Create slides for management meetings and proposals using design rules and 62 layout patterns. Build HTML and PDF decks, check content and layout, and produce editable PPTX files when requested, including pages matching an existing presentation.
Integrate Core ML models in iOS apps for on-device machine learning inference. Covers model loading (.mlmodel, .mlpackage, .mlmodelc), predictions with auto-generated classes and MLFeatureProvider, compute unit configuration (CPU, GPU, Neural Engine), MLTensor, VNCoreMLRequest, MLComputePlan, multi-model pipelines, and deployment strategies. Use when loading Core ML models, making predictions, configuring compute units, or profiling model performance.
The English summary is being prepared. Showing the original description.
Generates standalone Markdown reference documentation for QML components and applications. Use this skill whenever you want to document QML files, create API reference docs for a QML component or module, document a Qt Quick application, or produce developer-facing documentation from .qml source code. Triggers on: "document this QML", "write docs for my QML", "create reference docs", "document QML component", "QML API docs", "document my Qt Quick component", "document my Qt app", or any time one or more .qml files are provided and documentation is needed. Works with single files, pasted code, or entire project folders. DO NOT use if the user asks for QDoc format output.
The English summary is being prepared. Showing the original description.
因果推論・効果検証（A/B テスト / ABテスト / オンライン実験 / リフト / SRM / CUPED、観察データの処置効果 / ATE / ATT / CATE / 傾向スコア / propensity score / IPW / 二重頑健 / DML / causal forest、準実験 / 差の差 / DiD / イベントスタディ / 操作変数 / IV / 2SLS / 回帰不連続 / RDD / 合成コントロール）を実行したら必ずセットで出す図と値のルーター。 proportions_ztest, chisquare, statsmodels.stats.power, dowhy, econml, causalml, doubleml, propensity, LinearDML, IV2SLS, rdrobust, rddensity, pysyncon, treat*post がコードに現れたとき、またはユーザーが「ABテストの結果を 見て」「施策の効果を推定して」「差の差で」「傾向スコアで揃えて」「閾値前後で比較して」と言ったときに使う。SRM・ バランス・並行トレンド・first-stage に言及がなくても適用する。SKILL.md のルーティング表で設計を特定し、対応する references/<設計>.md を読んでから実行する。実験でない群間比較の検定は statistical-inference-diagnostics、 予測モデルの解釈（SHAP 等）は predictive-modeling-diagnostics を使う。
The English summary is being prepared. Showing the original description.
Handles TOML configuration file operations in Python using tomlkit for comment-preserving read-modify-write cycles. Use when reading or writing pyproject.toml or any .toml config file, selecting between tomlkit and tomllib, modifying TOML while preserving comments and whitespace, implementing atomic config file updates, integrating TOML with Python dataclasses, handling TOML parse errors, or applying XDG base directory patterns for config file locations.
The English summary is being prepared. Showing the original description.
sgcop の RuboCop 設定を、導入先プロジェクトの .rubocop.yml にセットアップ・更新する。標準（rubocop.yml）か厳格版（rubocop_strict.yml）かの導入方針をまず確認して inherit_gem を整え、既存 .rubocop.yml から sgcop と重複する不要設定を削除する。gem 依存のカスタム Cop（enumerize 系など）は必要時のみ確認。そのうえで rubocop --auto-gen-config で .rubocop_todo.yml を生成し、違反（ノイズ）が多い Cop は無効化・Exclude・段階対応を提案、無効化したら todo を作り直す。
The English summary is being prepared. Showing the original description.
修正完了後に agent-review-kit でレビューHTMLを生成し、ユーザーがブラウザで書いた差分コメントを Codex または Claude Code の同一セッションで受け取り、回答・修正・resolve を未解決0件まで繰り返すレビューループ。AIレビューの指摘を add-comment でブラウザ上のコメントとして表示し、ユーザーが返信した指摘だけ修正する「AIレビューモード」も含む。実装プラン・設計書などの任意HTMLを publish-html でレンダリング済みのまま表示し、要素クリック・テキスト範囲でコメントを受け取る「HTMLレビューモード」も含む。他のレビュースキルの結果の出力先として agent-review-kit が指定された場合も、このスキルを読んで AI レビューモードの手順に従うこと。Use when the user wants to review changes in a browser (GitHub-like diff review), review a rendered HTML doc (plan/design doc) in a browser, iterate on fixes with inline comments, or display AI review findings as browser comments (output target: agent-review-kit).
The English summary is being prepared. Showing the original description.
Present local Markdown plans and HTML artifacts in a browser for review. People can annotate specific elements, chat, and approve or request changes, while the agent receives structured feedback and file edits appear automatically.
Turn a system description into a dark-themed architecture diagram in a single HTML file. It uses SVG, a scalable graphics format, to show components, connections, cloud boundaries, and security flows in a browser.
Produces detailed HTML or Markdown reports on pull requests, branches, or large code contributions. It explains how the system works, ranks concrete findings, compares designs when needed, and recommends whether and how to merge the changes.
Turn notes or documents into a talk outline, page-by-page media choices, and a production brief for a separate slide-making skill. After rendering, check each slide against its planned purpose and generate revision instructions for up to three rounds.
Create a retail training deck about consultative selling, covering the sales conversation, role plays, and daily practice. The HTML slides use a warm peach palette and consistent, approachable layouts for store associates and floor managers.
Create an HTML slide deck about neighborhood shops using portraits, local voices, and a handmade print style. Organize community stories in a coordinated beige-and-green layout that feels like a small independent magazine.
Create an HTML pitch deck for Series A fundraising, explaining growth, expansion, and the case for venture-scale returns. Large headlines and a red accent help organize the story around a few clear statements per slide.
Turn a Kyoto cherry-blossom trip into an HTML photo essay, from arrival to peak bloom and a memorable moment. A vintage Japanese cassette-package design gives the slides a consistent visual style for sharing with friends and travel readers.
Build an HTML finance deck explaining per-unit profitability and BYOK costs, where users supply their own API keys. Present assumptions and how results change under different conditions, using a consistent cream and rust-red visual style for CFOs and investors.
Create an anniversary photo essay as an HTML slide deck, combining a couple’s memories and turning points. Use a coordinated black, pink, and cream design to tell a decade-long story for the couple, family, and friends.
Create HTML slide decks for humanities lectures and research presentations, organizing sources, arguments, and evidence. A coordinated navy and warm-yellow template gives the slides a calm, scholarly appearance.