Loading...
Loading...
Found 137 Skills
Find, install, and configure MCP servers. Use proactively for MCP discovery, OAuth setup, env vars, stdio vs SSE transport, or troubleshooting MCP connections. Examples: - user: "Add the filesystem MCP server" → read server file, add to mcpServers in opencode.json, verify transport type - user: "How do I use MCP with GitHub?" → check catalog, install @modelcontextprotocol/server-github, configure OAuth token - user: "MCP not connecting" → check transport type (stdio/SSE), verify args/command, check env vars are passed - user: "What MCPs are available?" → run list_mcps.py, show catalog with auth types and install commands
Audit and optimise context window usage for AI coding tools (Claude Code, OpenCode, etc.). Estimates token breakdown, identifies waste (duplicate skills, overlapping rules, bloated instruction files, dirty git status, MCP server overhead), and provides actionable recommendations with projected savings. Use when the user says "context checkup", "reduce context", "check context", "context audit", "how big is my context", or when sessions feel sluggish.
Write and refactor TypeScript code in repos that use Effect-TS services, Zod schemas, event-sourced persistence, and namespace-driven architecture. Use this skill when implementing features, fixing bugs, writing tests, or refactoring in opencode or any TypeScript codebase built on the same stack (Effect DI, Drizzle ORM, Hono routes, Bun runtime). Triggers on tasks involving Effect services, namespace modules, Zod schema definitions, SyncEvent patterns, tool implementations, test writing, or code review in Effect-based TypeScript projects.
Rigorously evaluate an Agent Skill end-to-end across ANY coding-agent CLI — verify its scripts emit the documented numbers (deterministic checks), test whether its description triggers on the right prompts, and measure whether an agent following the SKILL.md beats a no-skill baseline (with/without pass-rate delta, mean ± stddev, benchmarked). Use whenever you need to test, benchmark, validate, grade, or quantify a skill's quality, check if a skill "actually works," compare two skill versions, optimize a skill's triggering, or set up an eval suite — even if the user just says "is this skill any good," "does my skill work," or "benchmark this skill." Drives Claude Code, OpenAI Codex, Antigravity (agy), Cursor, GitHub Copilot, Amp, opencode, or Grok in headless mode.
Spawn a single autonomous AI agent with a specific task, personality, and CLI backend (Claude, Gemini, OpenCode, Copilot). Agent accepts task from docs/todo/pending/, selects personality based on task type, and works autonomously with CLI tools. Integrates with docs-first workflow via task signals and progress tracking.
Explore and analyze TUI applications to document their features for cloning. Use when asked to reverse-engineer, analyze, document, or understand a terminal UI like Claude Code, OpenCode, Codex, lazygit, or any ratatui/ncurses-based application. Launches the target TUI in tmux, systematically explores all views and keybindings, captures ASCII diagrams of each screen, and writes findings incrementally to a markdown file (survives context compaction).
SwiftUI 前端设计 skill — anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review. Works with Claude Code, Cursor, Codex, and OpenCode.
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.
Decide which CLI worker (Claude, OpenCode, or Gemini) should implement a given task. Routes by task type — large-context to Gemini, mechanical to OpenCode, judgment to Claude. Returns the chosen worker and a short rationale; the caller invokes the worker via scripts/invoke-worker.sh.
Audit and improve repositories for reliable agentic work across Codex and Codex App, Claude Code, and OpenCode. Use when reviewing AGENTS.md or CLAUDE.md quality and discovery, instruction routing in monorepos or meta-repos, agent settings, MCP configuration, skills, subagents, context budgets, or repository organization for coding agents.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Cross-tool AI consultation. Use when user asks to 'consult gemini', 'ask codex', 'get second opinion', 'cross-check with claude', 'consult another AI', 'ask opencode', 'copilot opinion', or wants a second opinion from a different AI tool.