自然語言處理

Restores full context when user says "hi-ai" or starts a new conversation. Searches project files, loads memory indexes, reads session state, and creates visual dashboard showing current project, recent decisions, active blockers, and quick actions. Use when user says "hi-ai", "continue", "restore context", or starts a fresh conversation.

Require comprehensive WHY/WHEN/HOW documentation for all functions. Apply when writing functions, classes, or complex logic to explain purpose, usage context, and implementation approach.

Edits that never fail. Find functions by name, not text matching.

This skill should be used when creating or extending ActorSheet/ItemSheet classes, implementing getData or _prepareContext, binding events with activateListeners, handling drag/drop, or migrating from ApplicationV1 to ApplicationV2. Covers both legacy V1 and modern V2 patterns.

Verify developers are working in the right repository type (brain vs code)

Track complex, multi-session work with dependency graphs using beads issue tracker. Use when work spans multiple sessions, has complex dependencies, or requires persistent context across compaction cycles. For simple single-session linear tasks, TodoWrite remains appropriate.

Validate inputs and preconditions before work begins using symmetric validation across layers, allowlist thinking, and contextual business rules with auditability. Use this skill when writing input validation, form handling, API request validation, or domain logic checks. Applies to all boundary validation requiring structured error responses, edge-case coverage, sanitization, escaping, and contract tests ensuring consistent validation across clients, APIs, background jobs, and CLIs.

Update and maintain Memory Bank files (activeContext, progress, decisionLog).LOAD THIS SKILL WHEN: Task completed | session ending | User says "記錄進度", "更新 memory" | before git commit | context needs saving.FILES: activeContext.md (current focus), progress.md (done/doing/next), decisionLog.md (decisions).

AI-powered image generation and editing using Gemini. Use when Claude needs to: (1) Generate images from text descriptions, (2) Edit existing images with instructions, (3) Create infographics or charts, (4) Generate visual assets for reports/presentations, (5) Work with .png, .jpg, .jpeg, .webp files for editing.

Access plain text versions of GitHub content (diffs, patches, raw files) using GitHub's URL transformations. Use when users share GitHub URLs for PRs, commits, files, or gists and you need to analyze the actual content. Works for pull requests, commits, file blobs, comparisons, and gists.

Enhanced docs unified with AI-powered features. Enhanced with Context7 MCP for up-to-date documentation.

Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.

⚡ PRIMARY TOOL for: 'comprehensive audit', 'deep analysis', 'full codebase review', 'multi-perspective investigation', 'complex questions'. Combines ALL detective perspectives (architect+developer+tester+debugger). Uses Opus model. REPLACES grep/glob entirely. Uses claudemem v0.3.0 AST with ALL commands (map, symbol, callers, callees, context). GREP/FIND/GLOB ARE FORBIDDEN.

Implement rich text editors using Plate.js. Supports creating both simple (comment/chat) and detailed (document/blog) editors.

Use Gemini CLI for analyzing large codebases or multiple files that exceed context limits. Leverage Google Gemini's massive context window with `gemini -p` and `@` syntax for file/directory inclusion to verify implementations, check patterns, and understand project-wide architecture.

GPTers 플랫폼의 데이터 소스 레퍼런스를 조회합니다. Portal DB(PostgreSQL)와 Airtable 테이블 구조, 필드 정보, 동기화 방향, ID 매핑 관계를 확인할 때 사용하세요. 데이터베이스 스키마, 테이블 관계, Sync 테이블, Hightouch 동기화에 대한 질문에 활용됩니다.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Enterprise Shell scripting with Bash 5.2, ShellCheck, bats-core testing, POSIX compliance, and Context7 MCP integration for defensive scripting patterns.

Elite multi-agent research orchestration utilizing ref MCP, exa MCP, brave-search MCP, and context7 with parallel execution of deep-research-agent, search-specialist, trend-researcher, and ux-researcher. Use for comprehensive research requiring maximum depth, breadth, and quality. Automatically invoked during /sc:research commands for world-class research capabilities surpassing any traditional deep research approach.

Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.