Aggregate news from popular cryptocurrency RSS feeds, analyze sentiment of articles, and calculate an overall market sentiment score with detailed explanation. Use when assessing crypto market sentiment for trading decisions, research, or monitoring trends from RSS sources.
Install
npx skills add https://github.com/kukapay/crypto-skills --skill market-sentimentSKILL.md
Crypto Market Sentiment
Overview
This skill enables aggregation of news from popular cryptocurrency RSS feeds, performs sentiment analysis on the articles, and computes a market sentiment score ranging from -1 (highly negative) to +1 (highly positive), along with evidence-based explanations.
Workflow
Follow these steps to analyze crypto market sentiment:
- Select RSS Feeds: Choose popular crypto RSS feeds (see references/rss_feeds.md for a curated list).
- Fetch News: Retrieve recent articles from the selected feeds.
- Analyze Sentiment: Classify each article's sentiment as positive (+1), negative (-1), or neutral (0) based on content keywords and context.
- Calculate Score: Compute the average sentiment score across all articles.
- Generate Explanation: Provide evidence from the news items supporting the score.
Sentiment Classification Guidelines
- Positive (+1): News about adoption, launches, partnerships, ETF approvals, price rallies, regulatory wins, or technological breakthroughs.
- Negative (-1): News about hacks, crashes, regulatory crackdowns, liquidations, delays, or criticisms.
- Neutral (0): Factual updates, mixed outcomes, or speculative content without clear bias.
Output Format
The skill outputs:
- Sentiment Score: Numerical value between -1 and 1.
- Explanation: Breakdown by feed/source, key positive/negative drivers, and overall market implications.
Resources
scripts/
sentiment_analyzer.py: Python script to fetch RSS feeds, parse articles, and compute sentiment score. Run withpython sentiment_analyzer.pyto get automated results.
references/
rss_feeds.md: List of popular crypto RSS feeds with URLs and descriptions.sentiment_examples.md: Examples of sentiment classification for common news types.
Related skills
researchmattpocock575KInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.paper-context-resolverlllllllama451KRigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing Renv-and-assets-bootstraplllllllama450KRigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target.ai-research-explorelllllllama311KRigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family, dataset, benchmark, evaluation method, provided SOTA references, and wants candidate-only exploration on top of `current_research` with auditable repo understanding, idea gating, fair comparison, and governed experiments written to `explore_outputs/`. Do not use for README-first trusted reproduction, open-ended direction finding, narrow c