Tools

⚡ PRIMARY TOOL for: 'why is X broken', 'find bug source', 'root cause analysis', 'trace error', 'debug issue', 'find where X fails'. Uses claudemem v0.3.0 AST with context command for call chain analysis. GREP/FIND/GLOB ARE FORBIDDEN.

Row Level Security policy templates for Supabase - multi-tenant patterns, user isolation, role-based access, and secure-by-default configurations. Use when securing Supabase tables, implementing RLS policies, building multi-tenant AI apps, protecting user data, creating chat/RAG systems, or when user mentions row level security, RLS, Supabase security, tenant isolation, or data access policies.

根据用户给出的文字或者用户指定的txt/md文件内容，从类型列表中选择合适的文本类型，按照指定的格式给出podcast直播口述稿和音频文件

Create, modify, and manage Claude Code subagents. Use when users request to create new specialized agents, update existing agents, or need templates for common agent patterns. Also use when agents or other skills need to automatically generate subagents for specific domains.

Smart Git assistance for commits, branches, PRs, and repository management. Helps write good commit messages, resolve merge conflicts, understand git history, and manage branches. Use when user asks about git, commits, branches, merging, or version control.

Invoke Claude Code CLI from Python orchestrators and shell scripts. Use when asked to "spawn claude as subprocess", "automate claude cli", "run claude headless", "configure --allowedTools", "set up claude hooks", or "parallel claude invocation". Covers permissions, directory access (--add-dir), hooks, sandbox mode, and async patterns.

Implements atomic CSS with UnoCSS using on-demand generation, custom rules, and presets. Use when wanting instant atomic CSS, custom utility frameworks, or Tailwind alternatives with more flexibility.

Create and edit blog posts for Ghost CMS. Use when creating blog post projections from ideas, editing existing posts, or working with Ghost frontmatter and SEO. Includes blog-specific voice, structure, and templates.

Implement comprehensive input validation on both client and server sides, using allowlists over blocklists, sanitizing user input, and providing specific error messages to prevent security vulnerabilities. Use this skill when writing validation logic for forms, API endpoints, function parameters, or any user input. Use this skill when implementing server-side validation to ensure data integrity and security, adding client-side validation for immediate user feedback, or sanitizing input to prevent injection attacks. Use this skill when working with form components, API route handlers, data processing functions, or validation schemas. Use this skill when defining validation rules for data types, formats, ranges, required fields, or business logic constraints across all application entry points.

Use when instruction drift is likely: multi-step tasks, mid-task detours (tooling upgrades), or when agents must consult MCP memory / Skills / sessions and re-anchor repeatedly. Triggers: 'stay on track', 'follow instructions', 'resume main task', 'detour', 'intermediate task done'.

Global drug development pipeline tracking by disease, target, mechanism, or company. Use for competitive intelligence, opportunity identification, and trend analysis. Keywords: pipeline, drug development, clinical trials, R&D tracking, competitive landscape

Multiple individual Edit calls instead of batch MultiEdit

质量门禁/发布前检查流程生成器。统一输出可复用的质量门禁清单与命令集：跑测试、覆盖率阈值、格式化、lint、依赖漏洞扫描、构建产物检查、变更摘要。用于让 git-manager/test-builder/debug-helper 形成稳定闭环。

Test game mechanics via SQL. Use game_* tools for gameplay flow.

Task에 작업량(Estimate Point) 설정. Use when (1) 백로그 그루밍 시 작업량 추정,(2) Sprint 계획 전 작업량 설정, (3) 기존 Task 작업량 수정, (4) /SAX:sprint estimate 커맨드.

Docker build and test workflow with mandatory pre-push validation checklist to prevent CI/CD failures

UI/UX design for digital board games. Use when building game interfaces, implementing drag-and-drop, rendering game boards, showing player information, handling animations, or designing responsive layouts. Covers Canvas, SVG, and DOM-based approaches.

Use this when working with DWG file generation features (Tiles, Playground, Symbol Generator). Provides AutoLISP script patterns, DWGUNITS command, entity creation (entmake), APS Design Automation requirements, and critical rules for headless AutoCAD operation.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Clear, concise writing standards for documentation, comments, commit messages, and technical communication. Use when writing README files, documentation, PR descriptions, code comments, or any technical writing. Focuses on clarity, brevity, and active voice.