CI/CD

Use when navigating code, understanding unfamiliar functions, finding definitions or references, tracing call hierarchies, preparing for refactoring, or analyzing code impact. Enforces LSP-first semantic code intelligence with mandatory pre-edit checks, impact analysis before refactoring, and post-edit diagnostics. Provides IDE-like precision for code operations in large codebases. Covers navigation (goToDefinition, findReferences), understanding (hover, documentSymbol), and call analysis (incomingCalls, outgoingCalls).

Implement authentication, authorization, data protection, vulnerability checks, and security best practices. Use when adding authentication, protecting API endpoints, handling user data, or implementing security features.

Conduct subgroup analyses to examine effect moderation. Use when: (1) Testing pre-specified moderators, (2) Exploring heterogeneity, (3) Identifying differential effects, (4) Meta-analysis synthesis.

NDP-specific GitHub workflow using Trunk-Based Development (TBD). Commit directly to main with conventional commits. Use this skill for ALL git operations in the Neural Data Platform project.

Generate a specification file from user input/requirements. Use when user says "generate spec", "create spec", "write spec", "spec from requirements", or provides feature requirements and asks to create a spec. (user)

Implement caching strategies using @delon/cache. Use this skill when adding memory cache, LocalStorage cache, SessionStorage cache, or cache interceptors for HTTP requests. Supports TTL-based expiration, cache invalidation, cache grouping, and persistent storage. Optimizes performance by reducing redundant API calls and database queries.

Playdate game development in Lua with the Playdate SDK, including game loop, sprites, graphics, input (crank, buttons, accelerometer), UI, performance, metadata (pdxinfo), and simulator/device workflow. Use when asked to make a Playdate game, implement Playdate-specific mechanics, or apply Playdate design and accessibility guidelines.

Analyze, update, and manage Python dependencies in pyproject.toml, checking for version compatibility, security vulnerabilities, and suggesting upgrades.

Comprehensive code review skill for Wasp applications. Use when reviewing code, PRs, or architectural changes. Covers Wasp-specific patterns, import rules, auth checks, TDD compliance, multi-tenant permissions, and performance. Integrates all CLAUDE.md critical rules.

Generate testable scientific hypotheses from observations, data, or research questions. Develop competing explanations, design experiments, and formulate predictions. Use during the PLANNING phase or when developing research aims.

Dynamic agent orchestration system that autonomously creates and dispatches specialized sub-agents with pre-selected skill subsets for complex multi-step tasks

Enhanced Just-In-Time document loading system that intelligently discovers, loads, and caches relevant documentation based on user intent and project context. Use when users need specific documentation, when working with new technologies, when answering domain-specific questions, or when context indicates documentation gaps.

Use when integrating OpenAI GPT models for conversational AI. Covers chat completions, streaming responses, function calling, system prompts, token management, cost optimization, error handling, and building specialized agent personas for Physical AI tutoring.

Transforms technical specifications into task files with 15 enrichments (10 universal + 5 spec-specific including UX flow and success metrics). Use when user says 'format specification', 'convert spec to tasks', 'process requirements', 'extract tasks from spec', or when detect-input-type returns 'spec'. Handles PRDs, feature specs, and technical requirements in .md files. (plugin:task-streams)

Universal security checklist based on OWASP Top 10 for ANY project type or language. Use before deploying to production, handling sensitive data, or processing user input.

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Best practices for common command-line tools. Use when working with specific CLI commands like rm, tree, and other Unix utilities.

Architecture Decision Records (ADRs)をdocs/adr/ディレクトリで管理します。新しいADRの作成、既存ADRの編集、ADR索引の確認を行います。ユーザーがアーキテクチャ決定の記録、ADRの作成・更新・検索を依頼したときに使用してください。番号の自動採番、プロジェクト固有のフォーマット（日本語、メタデータ構造）を遵守します。

Systematic technical debt reduction and code optimization agent. Use when refactoring code, reducing complexity, eliminating code smells, improving performance, cleaning up unused code, or modernizing legacy patterns. Handles dependency updates, architecture improvements, and codebase health metrics.

Only use when explicitly specified by the user.