Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
技術ドキュメント向けMarkdown高度構文スキル。Mermaid図、複雑テーブル、コードブロック、数式表現を活用。 Anchors: • GitHub Flavored Markdown Spec / 適用: 拡張構文 / 目的: プラットフォーム互換ドキュメント • CommonMark Spec / 適用: 基本構文 / 目的: クロスプラットフォーム互換性 • Mermaid Official Docs / 適用: ダイアグラム / 目的: ビジュアル技術文書 Trigger: Use when creating technical documentation with Mermaid diagrams, complex tables, syntax-highlighted code blocks, mathematical expressions, or YAML front-matter.
Documentation patterns for creating clear, executable, and maintainable usage examples across APIs, CLIs, libraries, and frameworks. Anchors: • Docs for Developers (Jared Bhatti et al.) / 適用: 実践的な例示パターン / 目的: 開発者に即座に理解・実行可能な例を提供 • The Documentation System (Diataxis) / 適用: チュートリアル・ハウツー・リファレンス分類 / 目的: 目的に応じた例の種類と粒度を選択 • Clean Code (Robert C. Martin) / 適用: 明確な命名・単一責務 / 目的: 自己説明的なサンプルコード Trigger: Use when creating code examples, writing tutorials, documenting API usage, building sample projects, establishing example conventions, or standardizing example patterns across a codebase. example creation, tutorial writing, API documentation, sample code, documentation patterns
Create custom recipes based on available ingredients, dietary restrictions, and preferences
Audit logs in project against fractary-logs best practices and generate actionable remediation specification
Audit documentation against fractary-docs standards and generate actionable remediation specification
Manage IAM permissions - grant missing permissions when deployments fail, maintain IAM audit trail, enforce profile separation, scope permissions to environment. Uses discover-deploy profile to grant permissions, never grants to production without explicit approval.
Test infrastructure configurations and deployments - security scanning with Checkov/tfsec, cost estimation analysis, pre-deployment validation, post- deployment verification, integration testing, generates comprehensive test reports with pass/fail status, identifies vulnerabilities and compliance issues, tracks test history for trend analysis.
Validates generated artifacts against Fractary plugin standards using automated validators. Checks XML markup, frontmatter, naming conventions, and structure.
Generate Terraform infrastructure as code - read design documents and implement them as Terraform configurations including resources, variables, outputs, and provider configurations. Creates modular, maintainable Terraform code following best practices with proper resource naming, tagging, and organization.
Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"
Defensive epistemology protocol for coding agents. Rationalist principles applied to code: explicit predictions, notice confusion, verify before proceeding.
Browse and search the complete SOP library extracted from Lenny's Podcast. Use when: looking for specific frameworks, browsing available SOPs, or needing to find the right framework for a situation. Contains 225 SOPs across 15 domains from 80+ expert sources.
Validates synthetic lethality claims from CRISPR knockout screens using BioGRID ORCS 5-phase workflow. This skill should be used when the user asks to "validate synthetic lethality", "query CRISPR essentiality data", "find gene dependencies", "compare cell line screens", or mentions BioGRID ORCS, gene knockout data, essentiality scores (CERES, MAGeCK, BAGEL), or asks to validate claims from published CRISPR papers.
Verify OrcaFlex model results against industry standards (DNV, API, ISO). Perform capacity checks, safety factor verification, and compliance reporting for offshore structures.
Compare 3D CAD models using boolean operations (IoU, Dice, precision/recall). Use when evaluating generated models against gold references, diffing CAD revisions, or computing similarity metrics for ML training. Triggers on: model diff, compare models, IoU, intersection over union, model similarity, CAD comparison, STEP diff, 3D evaluation, gold reference, generated model, precision recall 3D.
Specialized AI agent for finite element mesh generation and manipulation using GMSH. Use for 1D/2D/3D mesh generation, geometry processing, quality assessment, optimization, and integration with OrcaFlex, ANSYS, and OpenFOAM.
Use when "scientific computing", "astronomy", "astropy", "bioinformatics", "biopython", "symbolic math", "sympy", "statistics", "statsmodels", "scientific Python"
コードスメルとアーキテクチャ・アンチパターンを整理し、レビューと改善対象の特定を支援するスキル。 クラス/メソッドのスメル検出、改善優先度の整理、レポート化を扱う。 Anchors: • Clean Code (Robert C. Martin) / 適用: コード品質レビュー / 目的: 意図の明確化 • Refactoring (Martin Fowler) / 適用: スメル検出と改善 / 目的: 安全な修正 • Working Effectively with Legacy Code (Michael Feathers) / 適用: 改善対象の特定 / 目的: リスク最小化 Trigger: Use when detecting code smells, identifying refactoring targets, analyzing technical debt, or documenting anti-patterns. code smells, anti-patterns, refactoring targets, technical debt, architecture review
