開發

Brief description of what this skill does and when to use it. Be specific with trigger keywords so Claude knows when to apply this skill.

Route-aware gap analysis. For Brownfield - uses /speckit.analyze to compare specs against implementation. For Greenfield - validates spec completeness and asks about target tech stack for new implementation. This is Step 4 of 6 in the reverse engineering process.

Automatically update repository documentation whenever code changes (add/edit/refactor) occur. Use when modifying source code, public APIs/contracts, rendering/interaction/data/compute logic, diagnostics, or build/release/CI flows so docs stay consistent without asking.

Complete HUMMBL Base120 mental models framework with all 120 models across 6 transformations (Perspective, Inversion, Composition, Decomposition, Recursion, Meta-Systems). Includes model selection guidance, evidence standards, quality criteria, and application methodology. Essential reference for HUMMBL-based development, analysis, and problem-solving.

This skill should be used when the user asks to "implement with TDD", "write tests first", "do test-driven development", or as Phase 3 of the /dev workflow. Enforces RED-GREEN-REFACTOR cycle with mandatory test-first approach.

Add OpenAI Realtime API voice agent to a Next.js presentation. Use when adding voice interactivity, realtime audio, AI presenter, or voice navigation to slides. Triggers on "voice agent", "realtime API", "audio presentation", "AI presenter", "voice navigation".

Go backend development assistant for building production-ready services with modern 2025 best practices. Supports project initialization, framework selection (Gin/Chi/Echo/Fiber), database layer (pgx/sqlc/GORM), and API development. Activated when users mention "Go", "Golang", "고랭", "백엔드", or need Go service development help.

Integrate and embed OpenAI ChatKit UI into TypeScript/JavaScript frontends (Next.js, React, or vanilla) using either hosted workflows or a custom backend (e.g. Python with the Agents SDK). Use this Skill whenever the user wants to add a ChatKit chat UI to a website or app, configure api.url, auth, domain keys, uploadStrategy, or debug blank/buggy ChatKit widgets.

Review text message conversations with a specified contact and send appropriate replies with cheerful tone and humor using Arlen's authentic writing style. This skill should be used when the user says "reply to [name]'s text", "respond to [name]", "text [name] back", or wants to send contextual replies to contacts. Automatically handles contact lookup and conversation review via subagent delegation. Integrates email skill writing style guide for authentic voice. Considers ALL messages received from contact since last reply (not just latest). TRIGGER PHRASES - "reply to", "respond to", "text back", "answer [name]'s message".

Use when converting an existing Python project into an MCP server via the web editor: create an mcp_{server} folder, build a facade service.py with @mcp_service, auto-pick key functions to expose, seed tool_definition_templates.py with defaults, and wire editor_config.json so the tool editor can generate tool_definitions.py/server.py.

Use percentage-based capital limits, not hard-coded dollar amounts. Trigger when: (1) trades blocked on small accounts, (2) min_cash_buffer is absolute dollars, (3) capital allocation doesn't scale with account size, (4) fixed dollar thresholds in risk code.

Go concurrency patterns including goroutines, channels, context propagation, and sync primitives. Use when working with goroutines, channels, context.Context, or any concurrent Go code.

Recursive Self-Improvement Development. Continually improve the codebase.

Use when performing any web search (WebSearch, WebFetch).Trigger phrases: "검색해봐", "알아봐", "찾아봐", "분석해봐", "search", "look up", "find"Ensures Claude uses the current year instead of defaulting to outdated years (e.g., 2024).

Provides Git version control operations for managing code repositories. Allows agents to check repository status, view commit history, and perform basic Git operations.

Comprehensive Bun runtime expertise covering all major features.Use when working with Bun projects, migrating from Node.js, or leveraging Bun-specific APIs.Activates for: Bun.serve, Bun.file, bun:test, bun:sqlite, bun install, bun build,bunfig.toml, TypeScript in Bun, package manager operations, bundler configuration,and Node.js compatibility questions.

Visual testing skill for React Native apps across iPhone models. Use when testing app appearance on iPhone 11 through 17 (all variants including Pro, Pro Max, Plus, Mini, Air, and SE). Covers screenshot capture, simulator configuration, screen dimension validation, safe area handling, Dynamic Island/notch compatibility, and pixel-perfect verification across all iPhone screen sizes and resolutions.

TestFlight and App Store distribution guide. Use when preparing app for TestFlight, creating production builds, or submitting to App Store Connect.

Generates production-ready BAML applications from natural language requirements. Creates complete type definitions, functions, clients, tests, and framework integrations for data extraction, classification, RAG, and agent workflows. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), 6 programming languages (Python, TypeScript, Ruby, Java, Go, C#), 10+ frameworks, 50-70% token optimization, and 95%+ compilation success.

Rapid task execution without hesitation or deterrence. Expert in overcoming blockers, making quick decisions, and maintaining forward momentum. Use for urgent tasks, breaking through impediments, decisive action. Activates on 'swift', 'execute quickly', 'undeterred', 'overcome blocker', 'just do it'. NOT for strategic planning, careful analysis, or research tasks.