Development

Implements features and writes code based on Plans.md tasks. Use when user mentions 実装, implement, 機能追加, コードを書いて, 機能を作って, feature, coding, 新機能, implementing functions, classes, or features, 新しい関数. Do not use for review or build verification.

Build UI components using the compound component pattern. Use when creating new React components, building UI elements, refactoring components, or when the user mentions compound components, composable components, component patterns, or UI building blocks.

Work with internationalization using next-intl and PO files. Use when handling translations, i18n, PO files, getExtracted, useExtracted, translating content, or when the user needs to add or modify translations.

End-to-end guide for creating React components in AgenticFleet's frontend, from design tokens through Tailwind styling, shadcn/ui integration, state management, to testing.

Create, review, and refactor project documentation (README, AGENTS.md, architecture docs, runbooks, API docs) with deep codebase analysis, clear markdown structure, and diagrams/user flows. Use when asked to write or improve docs, audit existing documentation for accuracy or quality, generate diagrams/flows, or assess agent-first docs like AGENTS.md/PLANS.md for freshness and completeness.

Expert Python backend code reviewer that identifies over-complexity, duplicates, bad optimizations, and violations of best practices. Use when asked to review Python code quality, check for duplicate code, analyze module complexity, optimize backend code, identify anti-patterns, or ensure adherence to best practices. Ideal for preventing AI-generated code from creating unnecessary files instead of imports, finding repeated validation logic, and catching over-engineered solutions.

Comprehensive guide for initializing or reorganizing agent memory and project context. Use when setting up a new project, when the user asks you to learn about the codebase, or when you need to create effective memory blocks for project conventions, preferences, and workflows.

Delegates coding tasks to Codex CLI for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.

Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.

Creates unique, production-grade frontend interfaces with exceptional design quality. Use when user asks to build web components, pages, materials, posters, or applications (e.g., websites, landing pages, dashboards, React components, HTML/CSS layouts, or styling/beautifying any web UI). Generates creative, polished code and UI designs that avoid mediocre AI aesthetics.

Aggregates and summarizes the latest AI news from multiple sources including AI news websites and web search. Provides concise news briefs with direct links to original articles. Activates when user asks for 'today's AI news', 'AI updates', 'latest AI developments', or mentions wanting a 'daily AI briefing'.

Guides systematic code refactoring following the DRY (Don't Repeat Yourself) principle. Use when user asks to eliminate code duplication, refactor repetitive code, apply DRY principle, or mentions code smells like copy-paste, magic numbers, or repeated logic. Implements a 4-step workflow from identifying repetition to verified refactoring.

This skill should be used when the user asks to "analyze my product", "research competitors", "find feature gaps", "create feature request", "prioritize backlog", "generate PRD", "plan roadmap", "what should we build next", "competitive analysis", "gap analysis", "sync issues", or mentions product management workflows. Provides AI-native PM capabilities for startups with signal-based feature tracking, the WINNING prioritization filter, and GitHub Issues integration with deduplication.

Generate architecture diagrams as .excalidraw files from codebase analysis. Use when the user asks to create architecture diagrams, system diagrams, visualize codebase structure, or generate excalidraw files.

Systematic validation methodology for ResearchPacks and Implementation Plans. Provides scoring rubrics and quality gates to ensure outputs meet standards before proceeding to next phase. Prevents garbage-in-garbage-out scenarios.

Systematic approach for creating minimal-change, reversible implementation plans. Claude invokes this skill when transforming requirements/research into executable blueprints. Emphasizes simplicity, safety, and clear verification steps.

Active context curation to fight context rot. Curates what goes into limited context window from constantly evolving information universe. 39% improvement, 84% token reduction.

Systematic approach for gathering authoritative, version-accurate documentation. Claude invokes this skill when research is needed before implementation. Ensures truth over speed while achieving both.

Create distributable Python packages with proper structure and publishing.Triggers: Python packaging, pyproject.toml, uv, pip, PyPI, distribution, CLI tools,entry points, package structure, publishingUse when: creating Python packages, configuring pyproject.toml, setting upentry points, publishing to PyPI, CI/CD for packagesDO NOT use when: testing packages - use python-testing instead.DO NOT use when: optimizing package performance - use python-performance.Consult this skill for Python package creation and distribution.

Profile and optimize Python code using cProfile, memory profilers, andperformance best practices.Triggers: profiling, optimization, cProfile, memory profiler, bottleneck,slow code, performance, benchmarking, py-spy, tracemallocUse when: debugging slow code, identifying bottlenecks, optimizing memory,benchmarking performance, production profilingDO NOT use when: async concurrency - use python-async instead.DO NOT use when: CPU/GPU system monitoring - use conservation:cpu-gpu-performance.Consult this skill for Python performance profiling and optimization.