x-researchlisted

# X Research Skill Agentic research over X/Twitter using the `x_search` tool. Decompose the research question into targeted searches, iterate to refine signal, and synthesize into a sourced sentiment briefing. ## Research Loop ### 1. Decompose into Queries Turn the research question into 3–5 targeted queries using X operators: - **Core query**: Direct keywords or `$TICKER` cashtag - **Expert voices**: `from:username` for known analysts or accounts - **Bearish signal**: keywords like `(overvalued OR bubble OR risk OR concern)` - **Bullish signal**: keywords like `(bullish OR upside OR catalyst OR beat)` - **News/links**: add `has:links` to surface tweets with sources - **Noise reduction**: `-is:reply` to focus on original posts; `-airdrop -giveaway` for crypto topics ### 2. Execute Searches Use the `x_search` tool with `command: "search"`. For each query: - Start with `sort: "likes"` and `limit: 15` to surface highest-signal tweets - Add `min_likes: 5` or higher to filter noise for broad topics - Use `since: "1d"` or `"7d"` depending on how time-sensitive the topic is - If a query returns too much noise, narrow with more operators or raise `min_likes` - If too few results, broaden with `OR` terms or remove restrictive operators ### 3. Check Key Accounts (Optional) For well-known analysts, fund managers, or company executives, use `command: "profile"` to see their recent posts directly. ### 4. Follow Threads (Optional) When a high-engagement tweet appears to be a th