Menu
Analyze the sentiment of financial news and aggregate coverage into key themes. Use when you need to assess market sentiment, gauge media coverage, or decide whether news about a stock is bullish, bearish, or neutral.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Benchmark a stock against sector averages and assess its market position, share, and competitive advantages. Use when you need to understand a company's competitive landscape, peer ranking, or sector standing.
Calculate fundamental financial metrics (P/E, ROE, profit margin, market cap) and assess valuation as overvalued, fairly valued, or undervalued. Use when you need deep financial analysis of a company's fundamentals.
Assemble a complete interactive HTML dashboard (Chart.js) from a JSON config. Use AFTER research is complete to render summary cards, sections, and charts into a single shareable report file.
Compare performance of multiple stocks side-by-side. Use when the user asks to "compare", "contrast", "which is better", or analyze "multiple stocks" together. Calculates returns, volatility, and correlations.
Analyze investment risk metrics for stocks including volatility, beta, VaR, and downside risk. Use when the user asks about "risk", "volatility", "how safe", "beta", or wants to understand risk profile.
Fetch and analyze historical stock data for any ticker symbol. Use when the user asks to "look up", "fetch", "get data for", or "analyze" a specific stock ticker. Retrieves price history, volume, and basic statistics.
| name | news-sentiment |
| description | Analyze the sentiment of financial news and aggregate coverage into key themes. Use when you need to assess market sentiment, gauge media coverage, or decide whether news about a stock is bullish, bearish, or neutral. |
This skill scores the sentiment of financial news text and groups coverage into common themes (earnings, products, market performance, management, regulation). It helps turn a batch of raw headlines or articles into a quick read on market mood.
Use this skill when the user (or a coordinating agent):
Collect the news you want to analyze. If you used the Tavily Search MCP, save the
returned headlines/snippets to a file (one item per line) in tmp/.
The helper script analyze_sentiment.py does the scoring and theme aggregation:
uv run python .claude/skills/news-sentiment/analyze_sentiment.py \
--input tmp/news.txt \
--output tmp/sentiment.json
You can also pass text directly instead of a file:
uv run python .claude/skills/news-sentiment/analyze_sentiment.py \
--text "Company beats earnings; analysts upgrade to buy"
Arguments:
--input (optional): Path to a text file of news, one item per line--text (optional): News text passed directly (use instead of --input)--output (optional): Path to write JSON results (e.g., tmp/sentiment.json)Provide either --input or --text.
Use the theme counts to highlight what the news is actually about (e.g., mostly earnings vs. mostly regulatory concerns).
When --output is supplied, the script writes JSON like:
{
"sentiment": {
"classification": "Positive",
"score": 4,
"positive_signals": 5,
"negative_signals": 1
},
"total_items": 8,
"themes": {
"Earnings & Financial Results": 4,
"Product & Innovation": 2
}
}
tmp/ for input/output filesuv run python to execute (not plain python)