Loading...
Loading...
Found 2,448 Skills
Fetch and apply Cursor-style workspace rules supporting all rule formats (.cursor/rules/*.md, *.mdc, AGENTS.md, and legacy .cursorrules).
CRITICAL: Use for MolyKit AI chat toolkit. Triggers on: BotClient, OpenAI, SSE streaming, AI chat, molykit, PlatformSend, spawn(), ThreadToken, cross-platform async, Chat widget, Messages, PromptInput, Avatar, LLM
Guía para generar mensajes de commit en español siguiendo Conventional Commits estrictos con Emojis. Usa esta skill siempre que el usuario pida hacer un commit, generar un mensaje de commit, commitear cambios, o cuando se complete un cambio de código y sea momento de registrarlo en git. También se activa con 'commit', 'commitear', 'guardar cambios', 'registrar cambios' o cualquier intención de crear un punto en el historial de git.
Blue Ocean Strategy framework based on W. Chan Kim & Renée Mauborgne's book. Use when you need to: (1) create uncontested market space instead of competing head-to-head, (2) analyze competitive landscape (red vs. blue oceans), (3) design value innovation propositions, (4) use Strategy Canvas and Four Actions Framework (ERRC), (5) identify non-customers and convert them, (6) break the value-cost trade-off, (7) shift from competition to value innovation.
Expert blueprint for shader programming (visual effects, post-processing, material customization) using Godot's GLSL-like shader language. Covers canvas_item (2D), spatial (3D), uniforms, built-in variables, and performance. Use when implementing custom effects OR stylized rendering. Keywords shader, GLSL, fragment, vertex, canvas_item, spatial, uniform, UV, COLOR, ALBEDO, post-processing.
Use when multiple reviews or paper notes need integration, cross-cutting themes must be identified, or project-specific implications must be drawn from disparate sources
CLAUDE.md file generation and optimization for Claude Code projects. Capabilities: initialize project instructions, analyze codebase context, optimize existing CLAUDE.md, apply Anthropic best practices, reduce token usage, improve effectiveness. Actions: init, create, optimize, enhance CLAUDE.md files. Keywords: CLAUDE.md, project instructions, Claude Code setup, project context, codebase analysis, Anthropic best practices, token optimization, project configuration, AI instructions, coding guidelines, project rules, workspace setup. Use when: initializing CLAUDE.md for new projects, optimizing existing project instructions, setting up Claude Code for a codebase, improving AI coding guidelines.
Research-driven code review and validation at multiple levels of abstraction. Two modes: (1) Session review — after making changes, review and verify work using parallel reviewers that research-validate every assumption; (2) Full codebase audit — deep end-to-end evaluation using parallel teams of subagent-spawning reviewers. Use when reviewing changes, verifying work quality, auditing a codebase, validating correctness, checking assumptions, finding defects, reducing complexity. NOT for writing new code, explaining code, or benchmarking.
Universal web design implementation methodology — BEM, responsive, accessibility, CSS architecture, spacing systems, dark mode. The HOW of building production-grade HTML/CSS.
Summarize lessons learned from ccbox session logs (projects/sessions/history/skills) so the agent can do better next time. Produce copy-ready instruction updates (project + global) backed by evidence, with optional skill-span context to attribute failures to specific skills. Use when asked to run /ccbox:insights, generate a "lessons learned" memo, or propose standing instructions from session history.
Validate that the problem you want to solve is real, painful, and worth solving before building anything. Master Cindy Alvarez's structured approach to problem discovery interviews. Use when: **Before solution interviews** to confirm the problem exists; **Early customer discovery** to understand the problem space; **Pivoting** to find new problems worth solving; **Market expansion** to understand problems in new segments; **Feature prioritization** to validate which problems matter most
Build production-grade frontend interfaces with modern React, Tailwind CSS, and shadcn/ui. Five modes: scaffold projects, create components, configure themes and design tokens, refactor styles, and audit codebases. Encodes best practices for React 19 Server Components (framework-dependent), TailwindCSS v4 CSS-first config, shadcn/ui with Radix primitives, modern CSS (container queries, :has(), view transitions, scroll-driven animations), Monaspace typography, and Vite 6. Supersedes the frontend-design skill. Use when building, styling, theming, or improving any frontend project. NOT for backend APIs, database design, DevOps, testing frameworks, state management libraries, routing, or full SSR framework setup.