Search and analyze X (Twitter) using xAI Grok 4 via OpenRouter with Live Search. Trigger on prompts that explicitly or implicitly ask to "search Twitter/X", "what's trending", "tweets from @handle", "hashtag #…", "what are people saying", or that require tweet-level activity/engagement from X.
Scanned 2/12/2026
Install via CLI
openskills install majiayu000/claude-skill-registry---
name: grok-skill
description: >
Search and analyze X (Twitter) using xAI Grok 4 via OpenRouter with Live Search.
Trigger on prompts that explicitly or implicitly ask to "search Twitter/X", "what's
trending", "tweets from @handle", "hashtag #…", "what are people saying", or
that require tweet-level activity/engagement from X.
---
# Grok 4 — X/Twitter Live Search Skill
## Prerequisites
- **OpenRouter API key** required (set as `OPENROUTER_API_KEY` environment variable)
- Get your key at [openrouter.ai](https://openrouter.ai)
- Bun runtime installed
## When to use
Use this Skill whenever the user asks for trends, activity, examples, or evidence **from X/Twitter**:
- "search twitter|x for <query>"
- "what's trending on X"
- "top tweets/threads/hashtags about <topic>"
- "what are people saying about <project>"
- "tweets from @handle", "compare @a vs @b"
## How to run (Claude should execute these)
- Minimal:
```bash
bun scripts/grok.ts --q "<query>"
```
- One-off with inline API key:
```bash
OPENROUTER_API_KEY="sk-or-..." bun scripts/grok.ts --q "<query>"
```
- With handles and date window (YYYY-MM-DD):
```bash
bun scripts/grok.ts \
--q "<topic or question>" \
--mode on \
--include "@OpenAI" "@AnthropicAI" \
--from "2025-11-01" --to "2025-11-07" \
--min-faves 50 --min-views 0 \
--max 12
```
- Output is concise JSON: `summary`, `citations` (tweet URLs), and `usage`. Paste a short synthesis with linked tweets.
## Defaults & notes
- Live Search `mode` defaults to `auto`; use `on` for explicit "search X now".
- If user gives handles, pass them via `--include` (or `--exclude`).
- Use `--from/--to` for time-bounded asks; if unspecified, do not assume dates.
- Keep `--max` modest (8–20) for cost/latency; raise only if sparse.
- `--include` and `--exclude` are **mutually exclusive**.
- Do **not** claim access to private/protected content. Prefer links over long quotes.
## Troubleshooting
- Sparse results → increase `--max` or relax filters; consider removing handles.
- Missing links → they're in `citations` of the JSON output; share the URLs.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.