grok
Skill41 starsChanged 5 months agoNo licenceView on GitHub
Grok X 实时抓取：让 Claude 调用本地 grok-build 获取真实 X (Twitter) 帖子。 X 模式必须优先驱动 Grok 原生 X 工具族：x_keyword_search、x_semantic_search、 x_user_search、x_thread_fetch；必要时再用 web_search/open_page 交叉验证。 返回带 @用户名、点赞/浏览数、链接、时间的真实帖子。复用用户已登录的 grok.com 订阅， 调用零额外成本（不像 MCP 方案要 xAI API key 按 token 付费）。 三种模式：x（X 实时抓取，主力）、ask（把 Grok 当独立第二意见）、continue（续接追问）。 当用户需要真实 X/Twitter 实时数据时使用，例如： 问问 grok X 上在聊什么、让 grok 搜 X 上对某事的实时讨论、grok 看看 @某账号最近发了什么、 X 上现在怎么说、X 实时热点、X 实时趋势、ask grok what X is saying about、 grok 第二意见、consult grok。 排除（不要触发本 skill）：写 X 推文 → 用 x-twitter-writer；大规模历史语料采集 → 用 x-sousuo；泛网络调研 → 用 smart-research。本 skill 的差异点是 Grok 对公共 X 搜索 工具有原生路径，适合可复核的 X 话语采样；不是 firehose，也不是事实裁判。 没有"公共 X 搜索 / X 实时反馈 / thread 上下文"诉求时不要用它。
- Deletes or force-pushes
11 other projects use a version of this.
Adopted by
Most recently taken up by
- DaeSeokSong/oh-my-ouroborostheir own version, first seen Nov 1, 2026
- base58ed/claude_code_filestheir own version, first seen Oct 20, 2026
- thedigitalorganizer/soloshiptheir own version, first seen Oct 15, 2026
- bolasblack/claude-skillstheir own version, first seen Oct 6, 2026
- shaal/skillstheir own version, first seen Sep 26, 2026
- oil-oil/groktheir own version, first seen Sep 10, 2026
Other versions11 projects use a version of this.
Word for word · 1
- yangliu2060/smith--skills★ 40100% same
Edited · 0
None found.
Wrote their own version · 10
- oil-oil/grok★ 7same name
- bolasblack/claude-skills★ 4same name
- Wangnov/grok-skills★ 4same name
- DaeSeokSong/oh-my-ouroboros★ 3same name
- shaal/skills★ 3same name
- base58ed/claude_code_files★ 1same name
- OhSeungWan/skills★ 1same name
- runapi-ai/grok★ 1same name
- sh0wrun/skills★ 0same name
- thedigitalorganizer/soloship★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository18 other files it gives its agents.
- ai-readability-auditSkill
- claude-reviewSkill
- cold-email-personalizerSkill
- competitor-price-monitorSkill
- competitor-researchSkill
- ecommerce-supportSkill
- email-assistantSkill
- geo-content-optimizerSkill
- influencer-evaluatorSkill
- linkedin-post-creatorSkill
- loopforgeSkill
- seo-analyzerSkill
- social-trend-monitorSkill
- storm-research-agentSkill
- video-creatorSkill
- viral-post-creatorSkill
- youtube-video-analyzerSkill
- z-imageSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.