Générer automatiquement résumé commits projet Git

Maison

Liste de prompts IA

Génération automatique résumé commits GitHub

${:__('collect %s',Génération automatique résumé commits GitHub)}$

Génère un résumé clair et concis des modifications à partir de l'historique des commits GitHub d'un projet logiciel, trie les changements clés des versions pour aider l'équipe de développement à aligner la progression du projet.

Contenu du prompt

Copier

Sort through all commit records from the past two weeks of a specified GitHub repository, organize all changes into three categories: new features, bug fixes and architecture adjustments, and write an easy-to-understand natural language summary for the project team's weekly meeting, avoid jargon and keep the language straightforward.

Copier

Parcourez tous les commits des deux dernières semaines d'un dépôt GitHub spécifié, classez les changements dans trois catégories : nouvelles fonctionnalités, correction de bugs et ajustements d'architecture, puis rédigez un résumé en langage naturel facile à comprendre pour la réunion hebdomadaire de l'équipe projet, évitez le jargon technique et gardez un langage simple.

Copier

Partager Cliquez pour copier le lien

commentaires (0)

0/300

Soumettre

Recommandation

Classificateur de Tickets E-com

Analyze the following customer service message from an e-commerce platform and determine its business category. The possible categories are: Logistics Inquiry, Return/Exchange Request, Product Quality Issue, Price Dispute, or Other Inquiry. Output only the category name without any explanation or additional text. If the message cannot be clearly classified, output 'Other Inquiry'.

Classement Billets EC

Act as a data analysis assistant for an e-commerce customer service system. Read the current list of pending customer inquiry tickets, automatically categorize them into four major categories based on the nature of the issue: logistics inquiry, product quality, return/exchange application, or complaint/suggestion. Extract key entities such as order numbers, product SKUs, and user sentiment tendencies, and finally output structured classification results for subsequent manual review or automatic routing.

Classificateur de tickets EC

Act as an intelligent customer service assistant for an e-commerce platform. Receive the raw text of a user's inquiry, analyze its core intent and urgency, and categorize it into one of four types: pre-sales consultation, after-sales rights protection, logistics inquiry, or complaint/suggestion. Extract key entities such as order numbers, product names, and problem descriptions. Finally, output a structured classification result and handling suggestions, ensuring the response is accurate and complies with corporate customer service standards.

Classificateur de Tickets E-commerce

Please analyze the following e-commerce customer service ticket content and classify it into one of four categories: 'Logistics Inquiry', 'Return/Exchange Request', 'Product Quality Complaint', or 'Other Inquiry' based on predefined business rules. If the ticket involves multiple issues, prioritize the most urgent or core issue category. Ensure the classification result is accurate and aligns with actual business scenarios to enable the customer service team to respond quickly.

Classification des tickets e-commerce

Please analyze the following e-commerce customer inquiry ticket content, automatically classify it into one of four categories: 'Logistics Inquiry', 'Return/Exchange Request', 'Product Quality Complaint', or 'Other Inquiry' based on business semantics, and briefly explain the classification basis to enable the customer service team to respond and handle it quickly.

Catégorisation des tickets de support

Analyze the provided customer inquiry text and categorize it into one of four predefined classes: pre-sales consultation, after-sales service, logistics inquiry, or complaint/suggestion based on business semantics. If an order number is mentioned, extract it; if emotional expression is present, label the sentiment as positive, neutral, or negative. The output must include the classification result, key entity extraction, and sentiment label, ensuring the logic aligns with standard e-commerce customer service protocols without additional explanatory reasoning.