數據與 AI

Use when launching a new product end-to-end from market research through post-launch monitoring.Orchestrates 15+ specialist agents across 5 phases in a 10-week coordinated workflow includingresearch, development, marketing, sales preparation, launch execution, and ongoing optimization.Employs hierarchical coordination with parallel execution for efficiency and comprehensive coverage.

Generate images using Google Gemini's image generation APIs via Python CLI. Use for "generate image", "create image", "gemini image", "AI image", or when needing AI image generation in Claude Code.

Statistical analysis for selecting trading symbols compatible with mean-reversion/momentum strategies, GARCH risk models, and Markov regime detection

Context-driven development methodology for organized, spec-first coding. Use when:- Project has a `conductor/` directory- User mentions specs, plans, tracks, or context-driven development- Files like `conductor/tracks.md`, `conductor/product.md`, `conductor/workflow.md` exist- User asks about project status, implementation progress, or track management- User wants to organize development work with TDD practices- User invokes `/conductor-*` commands (setup, newtrack, implement, status, revert, validate, block, skip, revise, archive, export, refresh)- User mentions documentation is outdated or wants to sync context with codebase changesInteroperable with Gemini CLI extension and Claude Code commands.Integrates with Beads for persistent task memory across sessions.

Review and improve English in daily journal entries. Use when the user wants to review their daily English practice with Japanese originals in `::ja` and `::en` sections.

PROACTIVE skill - STOP and invoke BEFORE writing dbt SQL. Validates models against coding conventions for staging, integration, and warehouse layers. Covers naming, SQL structure, field conventions, testing, and documentation. CRITICAL - When about to write .sql files in models/, invoke this skill first, write second. Supports project-specific convention overrides and sqlfluff integration.

Fast ideation and problem exploration. Triggers on Ukrainian/English phrases like "подумай", "поміркуй", "брейнштормінг", "brainstorm", "think through", "накидай ідеї", "generate ideas". Rapid divergent thinking to uncover insights, problems, and solutions through interactive dialogue.

This skill should be used when creating, modifying, or debugging Claude Code hooks. Triggers on phrases like "create a hook", "add a hook", "make a PreToolUse hook", "automate before tool runs", "block tool execution", "validate tool input", "log tool output", "hook for Write/Edit/Bash", "PostToolUse handler", "session start hook", or when working with files in .claude/hooks/ directory.

AI-powered PR Author Agent that transforms Observability Diff Plans into Pull Requests. Use when: (1) Generating instrumentation code from Scout Agent output, (2) Creating OTel configuration, correlation headers, lineage specs, (3) Scaffolding telemetry validation tests, (4) Creating GitHub/GitLab PRs with observability artifacts. Triggers: "generate PR from diff plan", "create instrumentation PR", "scaffold observability code", "generate OTel config", "create telemetry PR".

Generate actionable, dependency-ordered task lists from implementation plans usingSpecification-Driven Development (SDD) methodology. Use when creating executablework breakdown, task lists, or executing the /tasks command.This skill analyzes design artifacts (plan, contracts, data models, test scenarios)and generates a sequenced task list with parallel execution markers. Tasks followTDD (test-first) and contract-first principles, with clear dependencies and file paths.Triggered by: /tasks command, user request for "task list", "work breakdown","implementation steps", or "what tasks do I need to complete?".

Retrieves facility geometries from EPA's Facility Registry Service (FRS) for Illinois, Maine, and Ohio as GeoDataFrames

Exploit AWS, Azure, and GCP cloud misconfigurations including S3 buckets, IAM roles, metadata services, serverless functions, and cloud-specific privilege escalation. Use when pentesting cloud environments or assessing cloud security.

Generate comprehensive implementation plans using Specification-Driven Development (SDD)methodology. Use when creating technical design, implementation roadmap, or executingthe /plan command.This skill orchestrates the plan-template.md execution flow, generating research, datamodels, API contracts, and test scenarios. It validates constitutional compliance(Library-First, Test-First, Contract-First) and prepares for task generation.Triggered by: /plan command, user request for "implementation plan", "technical design","how to implement", or "design this feature".

Run verification commands and confirm output before claiming success

Implement the repository pattern for database abstraction with sqlx, transactions, and retry logic. Use when building data access layers.

Detect when user is working in an un-indexed project and proactively suggest enabling semantic memory. Activates on first code question in new projects to guide users through initial setup.

Run D&D campaigns from published adventures using CandleKeep rulebooks. Acts as Dungeon Master, references adventure books, manages game state, and tracks session progress.

Autonomous software development for agents with no persistent memory. Use when building, testing, or maintaining code projects. Ensures all work is independently verifiable without context from previous sessions.

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale. | Sử dụng khi: xử lý PDF, trích xuất, ghép file, chia nhỏ, điền form PDF.

Agent Skills のスキルレビューを行い、公式仕様への準拠とベストプラクティスの観点で指摘と改善案を提示する。スキルのレビュー依頼、SKILL.mdの品質確認、スキル構成の妥当性チェック、Agent Skills仕様への適合性評価の文脈で使用する。