Tools

Initializes session with environment check and task status overview. Use when user mentions セッション開始, 作業開始, 状況確認, what should I work on, start session. Do NOT load for: 実装作業, レビュー, セッション途中の作業.

Sets up new projects and generates workflow files like CLAUDE.md, AGENTS.md, Plans.md. Use when user mentions セットアップ, setup, 初期化, initialize, 新規プロジェクト, ワークフローファイル生成. Do NOT load for: 実装作業, レビュー, ビルド検証, デプロイ.

Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.

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.

Analyze the current session and consolidate learnings. Use at the end of a session or task.

Context-aware development assistant for AgenticFleet with auto-learning and dual memory (NeonDB + ChromaDB). Handles development workflows with intelligent context management.

Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.

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.

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.

Overthrow mod architecture patterns, naming conventions, and project structure

EnforceScript component patterns, networking, persistence, and memory management for Enfusion engine

Renders and validates Crossplane compositions with security and policy checks. Automatically activates when testing compositions, rendering examples, or validating resources with Polaris, kube-linter, and Datree. Works standalone or as part of complete KCL validation workflow.

Arma Reforger Workbench workflow, testing guidelines, and debugging patterns

Bump project versions across configs, docs, and changelog usinggit-workspace-review context.Triggers: version bump, semver, release version, changelog update, versionupdate, package version, release preparationUse when: bumping project versions, updating changelogs, preparing releases,coordinating version changes across filesDO NOT use when: just documentation updates - use doc-updates.DO NOT use when: full PR preparation - use pr-prep.Use this skill for version management and release preparation.

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.

Generate conventional commit messages from staged changes with correct type/scope.Triggers: commit message, conventional commit, git commitUse when: generating commit messages in conventional commits formatDO NOT use when: full PR preparation - use pr-prep instead.

Design, manage, and evolve digital gardens as living knowledge bases withinmemory palaces.Triggers: digital garden, knowledge base, linking, note curation, content lifecycle,garden maintenance, bidirectional links, knowledge evolutionUse when: managing note collections, creating link structures, maintainingknowledge bases, tending garden health and growthDO NOT use when: creating memory palace structures - use memory-palace-architect.DO NOT use when: evaluating new knowledge - use knowledge-intake.Consult this skill when cultivating and maintaining digital gardens.

Guide to formatting review deliverables for consistency, ensuring findingsare comparable across different types of analysis.Triggers: report formatting, deliverable structure, consistent output, reviewoutput, findings format, report template, output consistencyUse when: formatting final review outputs, ensuring consistent deliverablestructure, making findings comparable across reviewsDO NOT use when: capturing evidence during analysis - use evidence-logging.DO NOT use when: reviewing changes - use diff-analysis or review-core first.Consult this skill when formatting final review deliverables.