Z.AI CLI providing: - Vision: image/video analysis, OCR, UI-to-code, error diagnosis (GLM-4.6V) - Search: real-time web search with domain/recency filtering - Reader: web page to markdown extraction - Repo: GitHub code search and reading via ZRead - Tools: MCP tool discovery and raw calls - Code: TypeScript tool chaining Use for visual content analysis, web search, page reading, or GitHub exploration. Requires Z_AI_API_KEY.
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Access Z.AI capabilities via npx zai-cli. The CLI is self-documenting - use --help at any level.
export Z_AI_API_KEY="your-api-key"
Get a key at: https://z.ai/manage-apikey/apikey-list
| Command | Purpose | Help |
|---|---|---|
| vision | Analyze images, screenshots, videos | --help for 8 subcommands |
| search | Real-time web search | --help for filtering options |
| read | Fetch web pages as markdown | --help for format options |
| repo | GitHub code search and reading | --help for tree/search/read |
| tools | List available MCP tools | |
| tool | Show tool schema | |
| call | Raw MCP tool invocation | |
| code | TypeScript tool chaining | |
| doctor | Check setup and connectivity |
# Analyze an image
npx zai-cli vision analyze ./screenshot.png "What errors do you see?"
# Search the web
npx zai-cli search "React 19 new features" --count 5
# Read a web page
npx zai-cli read https://docs.example.com/api
npx zai-cli read https://docs.example.com/api --with-images-summary --no-gfm
# Explore a GitHub repo
npx zai-cli repo search facebook/react "server components"
npx zai-cli repo search openai/codex "config" --language en
npx zai-cli repo tree openai/codex --path codex-rs --depth 2
# Check setup
npx zai-cli doctor
Default: data-only (raw output for token efficiency).
Use --output-format json for { success, data, timestamp } wrapping.
For raw MCP tool calls (tools, tool, call), Code Mode, and performance tuning (cache/retries),
see references/advanced.md.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Browser automation with persistent named pages via the dev-browser CLI. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, log into sites, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", "open the browser", or any browser interaction request.
中文简介正在准备中。当前显示原文说明。
Multi-agent orchestrator for Claude Code. Use when user mentions gastown, gas town, gt commands, bd commands, convoys, polecats, crew, rigs, slinging work, multi-agent coordination, beads, hooks, molecules, workflows, the witness, the mayor, the refinery, the deacon, dogs, escalation, or wants to run multiple AI agents on projects simultaneously. Handles installation, workspace setup, work tracking, agent lifecycle, crash recovery, and all gt/bd CLI operations.
中文简介正在准备中。当前显示原文说明。
End-to-end GitHub repository maintenance for open-source projects. Use when asked to triage issues, review PRs, analyze contributor activity, generate maintenance reports, or maintain a repository. Triggers include "triage", "maintain", "review PRs", "analyze issues", "repo maintenance", "what needs attention", "open source maintenance", or any request to understand and act on GitHub issues/PRs. Supports human-in-the-loop workflows with persistent memory across sessions.
中文简介正在准备中。当前显示原文说明。
Multi-agent orchestration for complex tasks. Use when tasks require parallel work, multiple agents, or sophisticated coordination. Triggers include requests for features, reviews, refactoring, testing, documentation, or any work that benefits from decomposition into parallel subtasks. This skill defines how to orchestrate work using cc-mirror tasks for persistent dependency tracking and TodoWrite for real-time session visibility.
中文简介正在准备中。当前显示原文说明。