Grok CLI
Load when the user or an agent wants to use Grok/xAI locally with their own SuperGrok / X Premium account instead of a paid xAI API key — chat with Grok, generate images or videos with Grok Imagine, or search X/Twitter posts via Grok. Triggers on "用 Grok 聊天/问 Grok", "Grok 生成图片/视频", "grok imagine", "搜一下推特/X 上怎么说", "grok-cli ...", "log in to Grok with my X Premium", "Grok image/video generation", "search tweets with Grok". Uses browser OAuth (no API key needed); image/video generation is paid. Do NOT load for non-Grok LLMs or for the paid xAI API key SDK workflow.
Install
/plugin marketplace add Yrzhe/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add Yrzhe/claude-skills --skill grok-cligit clone --depth 1 https://github.com/Yrzhe/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/plugins/grok-cli ~/.claude/skills/grok-cliPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# grok-cli Use this skill when the user or an agent needs a local CLI wrapper around Grok/xAI with: - Browser-based xAI / SuperGrok OAuth login using Authorization Code + PKCE. - Optional `XAI_API_KEY` fallback. - xAI `/v1/responses` chat calls. - Grok Imagine image generation (sync) and video generation (async poll). - X/Twitter search through xAI's server-side `x_search` Responses tool. - Persistent local session history in SQLite. - Multi-session switching, export, and summarization. ## Safety and credential rules Never ask the user to paste their xAI password. Use `grok-cli login` to open the xAI authorization URL in a browser. Do not scrape browser cookies, automate `grok.com`, or capture interactive login credentials. OAuth tokens are stored locally under `~/.grok-cli/auth.json` with owner-only file permissions when supported by the OS. Prefer OAuth for SuperGrok users. API keys are supported only as fallback through `XAI_API_KEY` or `grok-cli key set`. Do not print access tokens, refresh tokens, API keys, or ID tokens. `grok-cli status` sanitizes credential output. Image and video generation are **paid** xAI operations (≈ $0.02 / image, ≈ $0.40 / 8s video — video is ~20x an image). The CLI refuses paid generation in non-interactive mode unless `--yes` is passed; never auto-pass `--yes` for an agent without the user's intent. No credentials are bundled in this package — each user logs in with their own SuperGrok / X Premium account via `grok-cli login`.
Details
- Skill name
grok-cli- Repository
- Yrzhe/claude-skills
- Path
plugins/grok-cli/SKILL.md- License
- MIT
- Repo updated
- 27 October 2026
FAQ
What does the Grok CLI skill do?
Load when the user or an agent wants to use Grok/xAI locally with their own SuperGrok / X Premium account instead of a paid xAI API key — chat with Grok, generate images or videos with Grok Imagine, or search X/Twitter posts via Grok. Triggers on "用 Grok 聊天/问 Grok", "Grok 生成图片/视频", "grok imagine", "搜一下推特/X 上怎么说", "grok-cli ...", "log in to Grok with my X Premium", "Grok image/video generation", "search tweets with Grok". Uses browser OAuth (no API key needed); image/video generation is paid. Do NOT load for non-Grok LLMs or for the paid xAI API key SDK workflow.
How do I install the Grok CLI skill?
Claude Code plugin: /plugin marketplace add Yrzhe/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Grok CLI popular?
It lives in Yrzhe/claude-skills, which has 65 GitHub stars and 6 forks.
Related skills
Adaptive Compaction
65Yrzhe/claude-skills
Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without chang
Agentlog
65Yrzhe/claude-skills
Load when the user wants to view, sync, or analyze multi-agent activity across multiple devices — Claude Code / Codex / Cursor / Maestri / browser-use sessions captured to a shared GitHub-synced pool, OR wants a distilled per-project context document so a fresh agent in a different tool can pick up where another left off. Triggers on "agentlog X" commands, "what did I do today across all my agents", "show me my pool", "sync the pool", "拉一下另一台机器上的 agent 记录", "看看 vps 上跑的", "跨设备 agent log", "跨工具上下文", "switch from Codex to Claude Code", "AGENTS.md / CLAUDE.md", "项目状态文档", "agent context". Do NOT lo
Akshare a Shares
65Yrzhe/claude-skills
针对中国A股的行情与数据查询(基于本地 akshare 源代码与API映射)。当用户请求获取A股实时行情、历史K线(日/周/月)、分钟级分时(1/5/15/30/60)、复权数据(前复权/后复权)、股东户数(含详情)、以及巨潮资讯公告披露结果时使用本Skill。默认优先使用东方财富(EM)接口;如用户指定新浪(Sina)来源或需要特定接口,则按映射调用对应函数。可使用内置脚本输出CSV/JSON,或内联Python调用。
Heat Metal
113Hmbown/Wizards-of-the-Ghosts
In D&D, Heat Metal makes a metal object painfully hot — the creature holding it must either endure the pain or drop it. The real-world version is deliberate friction injection: making a deprecated API progressively slower, adding escalating CAPTCHAs to suspicious traffic, increasing the cost of a bad behavior path until the actor self-selects out. Heat Metal does not break the tool. It makes continuing to use it more painful than switching to the alternative. This is the spell behind deprecation-by-discomfort, progressive rate limiting, and sunset friction curves.
Eyebite
113Hmbown/Wizards-of-the-Ghosts
In D&D, Eyebite lets you focus on one creature per turn and inflict sleep, panic, or sickness through sustained eye contact. The real-world version is targeted capability reduction: focused analysis that identifies and disables specific functions of a system, service, or adversary. Feature flagging a dangerous capability off. Selectively throttling a misbehaving API consumer. Disabling specific attack vectors during an incident. Eyebite requires sustained focus on a single target — it is not a broadcast weapon.
Mending
113Hmbown/Wizards-of-the-Ghosts
Mending is surgical repair of a known-working artifact that has a specific, identifiable break. It is NOT: - Triage/diagnosis: If the problem is "API is throwing 500s, figure out why" — that's investigation, not mending. Mending requires the break to already be identified. - Formatting/cleanup: If the data is correct but looks messy (sort keys, normalize indentation) — that's formatting, not repair. - State reset: If a flag is stuck or an alert needs clearing — that's an operational toggle, not a file repair. - Refactoring/redesign: If the system is "fundamentally flawed" and needs redesign —
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.