Three-example few-shot prompt for sentiment classification. Handles positive / negative / neutral with reasoning. Template you can extend for domain-specific classes.
npx mdskills install mdskills/sentiment-analysis-few-shotRelated
Instruction + example input/output pairs
@mdskills? Sign in with GitHub to claim this listing.Clear sentiment analysis task with solid examples but lacks triggering context or usage guidance
Classify the sentiment of the input as positive, negative, or neutral. Include one-line reasoning.
Example 1: Input: "This is the best product I've ever bought." Output: {"sentiment": "positive", "reasoning": "Superlative praise, no qualifiers."}
Example 2: Input: "It arrived broken and support hasn't replied in five days." Output: {"sentiment": "negative", "reasoning": "Concrete failure plus unresolved escalation."}
Example 3: Input: "The package arrived on Tuesday." Output: {"sentiment": "neutral", "reasoning": "Factual statement, no evaluative content."}
Now classify: Input: "{input}" Output:
Install via CLI
npx mdskills install mdskills/sentiment-analysis-few-shotSentiment Analysis (few-shot) is a free, open-source AI agent skill. Three-example few-shot prompt for sentiment classification. Handles positive / negative / neutral with reasoning. Template you can extend for domain-specific classes.
Install Sentiment Analysis (few-shot) with a single command:
npx mdskills install mdskills/sentiment-analysis-few-shotThis downloads the skill files into your project and your AI agent picks them up automatically.
Sentiment Analysis (few-shot) works with Claude Code, Openai, Gemini. Skills use the open SKILL.md format which is compatible with any AI coding agent that reads markdown instructions.