Loading...
Loading...
Found 260 Skills
Set up and optimize repositories for AI coding agents. Creates minimal AGENTS.md, CLAUDE.md symlink, docs/REQUIREMENTS.md, docs/BUSINESS-RULES.md, feedback loops, and deterministic enforcement (Claude Code hooks, OpenCode plugins). Use when user wants to make a repo AI-friendly, set up AGENTS.md/CLAUDE.md, document requirements/business rules for AI, add pre-commit hooks for AI workflows, or optimize codebase structure for coding agents.
Universal Cross-session Memory Protocol (Universal Memory Protocol). Enable all AI programming tools to share the same memory system. Applicable to Claude Code / Cursor / Aider / Cline / Codex / Trae / OpenCode. Capabilities: Intelligent Classification / FSRS Decay / Monthly Compression / Multi-layer Retrieval. Triggers: User says "remember"; asks "previous"; sensitive information detected; session ends.
Enables agents to register, manage, and execute scheduled tasks using OS native scheduler (crontab for Linux/WSL, launchd for macOS). No git, no dangerous flags, no session dependency. Tasks run headless, output to log files, user reads when ready. Use this skill when: - User wants to schedule recurring tasks with natural language - User mentions "every day at", "cada hora", "schedule", "programar", "automatizar" - User needs tasks to run without open session (headless) - User wants OS-level scheduling (crontab/launchd) - User mentions "cada minuto durante la próxima hora" or temporal intervals ACTIVATE when user mentions: "schedule", "programar", "cron", "cada día", "every hour", "automate", "tarea programada", "ejecutar automáticamente", "recordatorio", "cada minuto durante", "durante la próxima", "intervalo", "task scheduler", "opencode headless", "kiro scheduled", "background task", "tarea en segundo plano" DO NOT USE for: git operations, dangerous permissions, MCP sampling dependency.
Delegate tasks to the cost-effective opencode/glm-5 model. Use when you need inexpensive task execution, simple research, or delegating work that doesn't require the most powerful models.
Sync provider changes from cloned repositories in the providers/ folder. Use when syncing upstream changes from external provider repositories (claude-code, gemini, codex) while preserving local customizations. Includes multi-step workflow: checking for new commits via GitHub CLI, generating diffs, deep analysis, Pal MCP refactor planning, and applying changes incrementally. Never use for opencode provider (created locally, not cloned).
Use the beans CLI to track issues/tasks alongside your code. Flat-file issue tracker that stores beans as markdown files in .beans/ directory. Integrates with Codex, OpenCode, and Claude Code via beans-prime.
Initialize repo-scoped code review policy files under .opencode/review. Use when setting up project-specific review rules for /code-review.
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, Gemini, and OpenCode backends with agent presets, skill injection, file references (@syntax), worktree isolation, parallel execution, and structured output.
AI Debugging Collaboration Solution. Convert console.log into HTTP requests to collect logs. After the user completes operations, AI can automatically view and analyze the logs without the need for screenshots or copying console content. Supports Claude Code, OpenCode, Cursor.
Core patterns for AI coding agents based on analysis of Claude Code, Codex, Cline, Aider, OpenCode. Triggers when: Building an AI coding agent or assistant, implementing tool-calling loops, managing context windows for LLMs, setting up agent memory or skill systems, or designing multi-provider LLM abstraction. Capabilities: Core agent loop with while(true) and tool execution, context management with pruning and compression and repo maps, tool safety with sandboxing and approval flows and doom loop detection, multi-provider abstraction with unified API for different LLMs, memory systems with project rules and auto-memory and skill loading, session persistence with SQLite vs JSONL patterns.
Audit token waste across agent systems (Claude Code, OpenClaw, Hermes, OpenCode). Detect idle burns, model misrouting, and config bloat with dollar savings.
Answer ZenMux questions by reading the latest official docs. Use for product features, APIs, integration, pricing, models/providers, routing, fallback, streaming, multimodal, structured output, tool calling, reasoning, prompt caching, image/video generation, web search, long context, observability, logs, cost tracking, subscriptions, PAYG, invoices, FAQ, privacy, terms, compliance, and tool guides for Claude Code, Cursor, Cline, Codex, Gemini CLI, opencode, Cherry Studio, Obsidian, Sider, Open-WebUI, Dify, and GitHub Copilot. Trigger on "ZenMux docs", "ZenMux API", "how to use ZenMux", "models", "pricing", "ZenMux 怎么用", "文档", "快速开始", "API 参考", "模型路由", "供应商路由", "订阅", "按量计费", "接入", "配置". Also use when ZenMux is the project context and the user asks about LLM API aggregation, model routing, or provider fallback.