
X Research Sentiment Briefing
Summarizes public X/Twitter sentiment on a topic into a cited Markdown report, using only sources actually available.
- Repository
- nexu-io/open-design
- Stars
- 105,448
- Licence
- Apache-2.0
- Files
- 1 file
What it does
When asked what people are saying on X/Twitter about a stock, company, product, or market event, the agent follows a fixed workflow: it defines the topic and time window (default 7 days), runs a few targeted searches, groups the posts into bullish, bearish, neutral, and disagreement themes, and saves a cited Markdown report to the Design Files folder. It is instructed to say clearly when X is unavailable and fall back to web search or user-provided links, and to avoid claiming coverage it did not check.
Great for
- Analysts wanting a quick, cited snapshot of public reaction to a company or market event
- Product or marketing teams gauging community response to a launch
- Students or researchers who want a structured sentiment summary with source citations
Skip it if
- Rigorous statistical sentiment measurement: the skill itself says results carry sample bias and the report is a qualitative briefing, not a quantified survey
- Investment decisions without independent verification, since social media posts can be misleading, manipulated, or outdated
Try asking
- “What is Twitter saying about NVIDIA's earnings this week?”
- “Run X research on public sentiment toward our new app launch.”
- “Summarize CT sentiment on the Solana ecosystem over the last 7 days.”
- “Check what experts on X are saying about the recent Fed rate decision.”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
x-research.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip x-research.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip x-research.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide an X export, screenshots, or specific links if you lack live X access, so the report reflects real posts.
- Specify a time window and target entity (e.g., a ticker or product name) to get more focused queries.
- Treat the overall sentiment label as a rough summary and check the cited posts yourself before acting on it.
What's inside
- SKILL.md
Redistributed unmodified from nexu-io/open-design under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.