{"id":"338db701-42a6-455f-9abb-14c8503c8985","shortId":"TydC9a","kind":"skill","title":"alphaear-sentiment","tagline":"Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets.","description":"# AlphaEar Sentiment Skill\n\n## Overview\n\nThis skill provides sentiment analysis capabilities tailored for financial texts, supporting both FinBERT (local model) and LLM-based analysis modes.\n\n## Capabilities\n\n## Capabilities\n\n### 1. Analyze Sentiment (FinBERT / Local)\n\nUse `scripts/sentiment_tools.py` for high-speed, local sentiment analysis using FinBERT.\n\n**Key Methods:**\n\n-   `analyze_sentiment(text)`: Get sentiment score and label using localized FinBERT model.\n    -   **Returns**: `{'score': float, 'label': str, 'reason': str}`.\n    -   **Score Range**: -1.0 (Negative) to 1.0 (Positive).\n-   `batch_update_news_sentiment(source, limit)`: Batch process unanalyzed news in the database (FinBERT only).\n\n### 2. Analyze Sentiment (LLM / Agentic)\n\nFor higher accuracy or reasoning capabilities, **YOU (the Agent)** should perform the analysis using the Prompt below, calling the LLM directly, and then update the database if necessary.\n\n#### Sentiment Analysis Prompt\n\nUse this prompt to analyze financial texts if the local tool is insufficient or if reasoning is required.\n\n```markdown\n请分析以下金融/新闻文本的情绪极性。\n返回严格的 JSON 格式:\n{\"score\": <float: -1.0到1.0>, \"label\": \"<positive/negative/neutral>\", \"reason\": \"<简短理由>\"}\n\n文本: {text}\n```\n\n**Scoring Guide:**\n- **Positive (0.1 to 1.0)**: Optimistic news, profit growth, policy support, etc.\n- **Negative (-1.0 to -0.1)**: Losses, sanctions, price drops, pessimism.\n- **Neutral (-0.1 to 0.1)**: Factual reporting, sideways movement, ambiguous impact.\n\n#### Helper Methods\n- `update_single_news_sentiment(id, score, reason)`: Use this to save your manual analysis to the database.\n\n## Dependencies\n\n-   `torch` (for FinBERT)\n-   `transformers` (for FinBERT)\n-   `sqlite3` (built-in)\n\nEnsure `DatabaseManager` is initialized correctly.","tags":["alphaear","sentiment","awesome","finance","skills","rkiding","agent","agent-skills","finances","fintech"],"capabilities":["skill","source-rkiding","skill-alphaear-sentiment","topic-agent","topic-agent-skills","topic-finances","topic-fintech"],"categories":["Awesome-finance-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/RKiding/Awesome-finance-skills/alphaear-sentiment","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add RKiding/Awesome-finance-skills","source_repo":"https://github.com/RKiding/Awesome-finance-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 2025 github stars · SKILL.md body (1,777 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-03T00:52:44.176Z","embedding":null,"createdAt":"2026-04-18T21:54:11.019Z","updatedAt":"2026-05-03T00:52:44.176Z","lastSeenAt":"2026-05-03T00:52:44.176Z","tsv":"'-0.1':200,207 '-1.0':94,176,198 '0.1':187,209 '1':55 '1.0':97,189 '2':114 'accuraci':121 'agent':118,127 'alphaear':2,28 'alphaear-senti':1 'ambigu':214 'analysi':36,51,68,131,148,231 'analyz':4,56,73,115,154 'base':50 'batch':99,105 'built':244 'built-in':243 'call':136 'capabl':37,53,54,124 'correct':250 'databas':111,144,234 'databasemanag':247 'depend':235 'determin':18 'direct':139 'drop':204 'ensur':246 'etc':196 'factual':210 'financ':5 'financi':25,40,155 'finbert':9,44,58,70,83,112,238,241 'float':87,175 'get':76 'growth':193 'guid':185 'helper':216 'high':64 'high-spe':63 'higher':120 'id':222 'impact':215 'initi':249 'insuffici':162 'json':172 'key':71 'label':80,88,178 'limit':104 'llm':11,49,117,138 'llm-base':48 'local':45,59,66,82,159 'loss':201 'manual':230 'markdown':168 'market':27 'method':72,217 'mode':52 'model':46,84 'movement':213 'necessari':146 'need':16 'negat':95,197 'neutral':206 'news':101,108,191,220 'optimist':190 'overview':31 'perform':129 'pessim':205 'polici':194 'posit':98,186 'positive/negative/neutral':21,179 'price':203 'process':106 'profit':192 'prompt':134,149,152 'provid':34 'rang':93 'reason':90,123,165,180,224 'report':211 'requir':167 'return':85 'sanction':202 'save':228 'score':23,78,86,92,174,184,223 'scripts/sentiment_tools.py':61 'sentiment':3,7,20,29,35,57,67,74,77,102,116,147,221 'sideway':212 'singl':219 'skill':30,33 'skill-alphaear-sentiment' 'sourc':103 'source-rkiding' 'speed':65 'sqlite3':242 'str':89,91 'support':42,195 'tailor':38 'text':6,26,41,75,156,183 'tool':160 'topic-agent' 'topic-agent-skills' 'topic-finances' 'topic-fintech' 'torch':236 'transform':239 'unanalyz':107 'updat':100,142,218 'use':8,12,60,69,81,132,150,225 'user':15 '到1.0':177 '文本':182 '新闻文本的情绪极性':170 '格式':173 '简短理由':181 '请分析以下金融':169 '返回严格的':171","prices":[{"id":"0d0eb096-a4bb-4755-b406-b6a365ad946e","listingId":"338db701-42a6-455f-9abb-14c8503c8985","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"RKiding","category":"Awesome-finance-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:54:11.019Z"}],"sources":[{"listingId":"338db701-42a6-455f-9abb-14c8503c8985","source":"github","sourceId":"RKiding/Awesome-finance-skills/alphaear-sentiment","sourceUrl":"https://github.com/RKiding/Awesome-finance-skills/tree/main/skills/alphaear-sentiment","isPrimary":false,"firstSeenAt":"2026-04-18T21:54:11.019Z","lastSeenAt":"2026-05-03T00:52:44.176Z"}],"details":{"listingId":"338db701-42a6-455f-9abb-14c8503c8985","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"RKiding","slug":"alphaear-sentiment","github":{"repo":"RKiding/Awesome-finance-skills","stars":2025,"topics":["agent","agent-skills","finances","fintech"],"license":"apache-2.0","html_url":"https://github.com/RKiding/Awesome-finance-skills","pushed_at":"2026-03-29T05:03:47Z","description":"A collection of Awesome Finance Agent Skills for free and easy to start | 一系列开源免费的金融分析Agent Skills","skill_md_sha":"2d5fc7f356a93e406e44ddd8a182e7c58660988a","skill_md_path":"skills/alphaear-sentiment/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/RKiding/Awesome-finance-skills/tree/main/skills/alphaear-sentiment"},"layout":"multi","source":"github","category":"Awesome-finance-skills","frontmatter":{"name":"alphaear-sentiment","description":"Analyze finance text sentiment using FinBERT or LLM. Use when the user needs to determine the sentiment (positive/negative/neutral) and score of financial text markets."},"skills_sh_url":"https://skills.sh/RKiding/Awesome-finance-skills/alphaear-sentiment"},"updatedAt":"2026-05-03T00:52:44.176Z"}}