開發

Define custom Claude Code slash commands for agents in the Traycer enforcement framework. This skill should be used when creating or updating agents and needing to specify reusable prompts that agents can execute as slash commands. Commands are Markdown files stored in .claude/commands/ and referenced in agent config.yaml files. This is for Claude Code slash commands (/command-name), not bash/CLI commands.

Convert documents (PPTX, PDF, DOCX, XLSX, images) to Markdown/JSON/HTML using IBM Docling. This skill should be used when user asks to convert, parse, or extract content from documents. Triggers on "convert pptx", "parse pdf", "extract from document", "конвертуй презентацію", "витягни з pdf".

Generate JWTs for GitHub App authentication. Direct JWT generation for app-level operations, installation discovery, and bootstrapping workflows.

Waterfall ledger semantics and clawback behavior for the Phoenix VC fund model. Use when working on tier or ledger waterfall code, clawback behavior, or waterfall truth cases.

Build GTK4 desktop applications with GTKX React framework. Use when creating GTKX components, working with GTK widgets, handling signals, or building Linux desktop UIs with React.

Comprehensive Framer Motion animation library for React. Covers motion components, variants, gestures, page transitions, and scroll animations. Use when adding animations to React/Next.js applications.

Apply performance optimization patterns for game loop, rendering, and state updates. Use when discussing frame rate, optimization, profiling, or when editing core game loop code. Auto-apply when user mentions "slow", "fps", "lag", or "performance".

Detect hardcoded secrets, API keys, passwords, and credentials in source code. Security audit for leaked secrets. Works across all languages. Use when user asks about security issues or secret detection.

Эксперт по планам развития. Используй для создания IDP, competency mapping, skill assessments и learning pathways.

Master frontend, backend, and specialized frameworks. Covers React, Vue, Angular, Node.js, Django, Spring Boot, and ecosystem tools. Use when learning frameworks, choosing between options, or need best practices.

Build complete agent prompts deterministically via Python script. Use BEFORE spawning any BAZINGA agent (Developer, QA, Tech Lead, PM, etc.).

End-to-end frontend testing with Playwright Java and Chromium. Use for UI validation, form testing, API interaction verification, and screenshot capture on failures.

Generate persistent test cases from project analysis, or add individual test cases interactively. Supports full project analysis or adding single test cases via prompt description with browser exploration.

Guide for testing EDS blocks using test.html files and the development server. Covers test file structure, EDS core integration, testing patterns, and debugging workflows for Adobe Edge Delivery Services blocks.

Generates src/App.vue root component with unit test. Creates both App.vue and App.spec.ts files.

Creates distinctive, production-grade frontend interfaces that avoid generic AI aesthetics. Analyzes existing designs and adapts to project aesthetics.TRIGGERS - Keywords: UI, UX, CSS, SCSS, Sass, Less, styling, styles, stylesheet, Tailwind, styled-components, emotion, CSS-in-JS, Chakra, MUI, Material UI, Radix, shadcn, headless UI, layout, flexbox, grid, responsive, mobile-first, breakpoints, media queries, animation, transition, motion, keyframes, hover, focus, active states, visual design, typography, fonts, typeface, font-family, text styling, headings, color, colors, palette, color scheme, theme, theming, dark mode, light mode, branding, spacing, padding, margin, gap, whitespace, shadows, box-shadow, borders, border-radius, rounded corners, gradients, buttons, cards, forms, inputs, modals, dialogs, navigation, navbar, sidebar, header, footer, hero section, landing page, dashboard, component styling, design system, design tokens.TRIGGERS - Phrases: "make it look better", "improve the look", "looks ugly"

Provides token-efficient navigation of PROJECT_INDEX.json for codebase analysis. Use when blast radius analysis, dead code detection, caller dependency analysis, or call stack tracing is needed. Mention 'blast radius', 'find callers', 'dead code', or provide file:line references to trigger. Primary consumer is AI agents requiring deterministic, minimal-token codebase navigation.

Go error handling patterns including wrapping, custom error types, errors.Is/As, and error conventions. Use when handling, creating, or checking errors in Go.

Use for Phase 5 of Course OS - designing complete curriculum structure including modules, lessons, sequencing, learning paths, and outcome mapping. Triggers on "/course-architecture", "design curriculum", "structure modules", "lesson sequencing", or after completing Phase 4.

Assess current project state and suggest the most valuable next action. The primary entry point for users who aren't sure what to do. Analyzes context, checks for issues, and recommends specific skills or actions.