開發

Comprehensive reference for understanding any repo fast. All patterns for docs, code, configs, git, and conversation history. The complete playbook.

Use when formulating mixed integer programming (MIP) models, handling discontinuous variables, modeling logical constraints (either-or, conditional), or linearizing nonlinear terms

This skill should be used when the user asks to "refactor", "extract function", "rename", "improve code quality", "reduce duplication", or "remove code smell". Supports Lean 4 and general refactoring patterns.

Tavily AI search API integration via curl. Use this skill to perform live web search and RAG-style retrieval.

Triggers and monitors Jellyfin library scans, shows scan progress, displays newly added content, and verifies library statistics. Use this after adding new media, when content doesn't appear in Jellyfin, or when investigating indexing issues.

Comprehensive security specialist that performs vulnerability assessments, secure code reviews, dependency audits, and provides remediation guidance following OWASP, CWE, and industry security standards

Эксперт по заявкам на изменения. Используй для форм CR, impact analysis, approval workflows и change control.

SmartACE (Agentic Context Engineering) workflow engine with MCP-B (Master Client Bridge) and AMUM-QCI-ETHIC module. Dual database architecture using DuckDB (analytics) + SurrealDB (graph). Uses Blender 5.0 (bpy) and UE5 Remote Control. Use when (1) MCP-B agent-to-agent communication (INQC protocol), (2) AMUM 3→6→9 progressive alignment, (3) QCI quantum coherence states, (4) ETHIC principles enforcement (Marcel/Anthropic/EU AI Act), (5) SurrealDB graph relationships, (6) DuckDB SQL workflows, (7) ML inference with infera/vss, (8) Blender 5.0 headless processing, (9) UE5 scene control, (10) DuckLake time travel.

This skill should be used when working with the Ghostmind development system, which uses meta.json as a central configuration for Docker, Compose, Terraform, and Tmux. Use this skill when creating or modifying configurations for any of these components, setting up new applications, or understanding how the system components interconnect.

Plan backend observability using RED + USE + 4 Golden Signals + JTBD

Detects hardcoded values, magic numbers, and duplicate constants using Ruff, Semgrep, and jscpd. Use when auditing for hardcodes, magic numbers, PLR2004, constant detection, or before release.

Generate properly configured tsconfig.json files for TypeScript projects with appropriate compiler options for various project types. Triggers on "create tsconfig", "generate tsconfig.json", "typescript config for", "configure TypeScript".

Python開発パターン集。Pythonコード作成、データ処理、ファイル操作時に使用。

This skill should be used when the user asks to "add unit tests", "write tests", "set up Vitest", "create a utility function", "add test coverage", or mentions TDD, test-driven development, or testing utilities. Provides guidance for unit testing with Vitest in TypeScript/Next.js projects using TDD approach.

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".

Security-focused code review guidelines for identifying vulnerabilities

Use this skill when exploring codebase architecture or planning new features requiring models/enums.AUTO-ACTIVATE when user mentions (FR/EN): - modèle, model, models, enum, enums, schema, Prisma schema - architecture, domain, domaine, existe, exists, available, disponible - créer, create, ajouter, add, nouveau, new, nouvelle feature - quel modèle, what model, which model,quel enum - 121 modèles, 87 enums, Planning, Leave, Business RulesThis skill provides INSTANT lookup (500 tokens vs 15k for full ERD) for 121 models and 87 enums.

Follow these patterns when designing guardrails validation contracts in OptAIC. Use for signal bounds, dataset schemas, portfolio constraints, PIT validation, and other domain-specific validation rules. Covers the "Law vs Police" architecture where Definitions contain contracts and the Engine enforces them.

Guide for creating Claude Code hooks - shell commands that execute at specific lifecycle events (SessionStart, SessionEnd, PreToolUse, PostToolUse, etc.). Use when users want to automate actions, add validation, logging, or integrate external tools into Claude Code workflows.

仕様駆動開発（SDD）ワークフローを自動発動で強制。Subtask開始時にAC確認、TDD実行、完了時にACチェックを実施。スコープ外実装を禁止。Use when implementing features, creating new functionality, or when "実装して", "作成して", "開発して" keywords appear.