根据预定义的业务类别(销售、统计、预测、聊天)对输入文本进行分类,并支持基于用户反馈的实时纠错。
Scanned 9/2/2026
Install to Claude Code
npx -y skills add majiayu000/claude-skill-registry --skill unknown-ecnu-icalk-autoskill-27 --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Unknown Ecnu Icalk Autoskill 27?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/majiayu000-unknown-ecnu-icalk-autoskill-27-claude-skill-registry)More formats (shields.io, HTML) on the badges page.
---
id: "3e109e02-4aa1-43cf-8fce-0bcb11058a81"
name: "文本意图分类器"
description: "根据预定义的业务类别(销售、统计、预测、聊天)对输入文本进行分类,并支持基于用户反馈的实时纠错。"
version: "0.1.1"
tags:
- "文本分类"
- "意图识别"
- "纠错"
- "NLP"
- "业务分类"
triggers:
- "充当文本分类器"
- "帮我分类这句话"
- "对这句话进行分类"
- "这是什么意图"
- "这句话属于什么分类"
---
# 文本意图分类器
根据预定义的业务类别(销售、统计、预测、聊天)对输入文本进行分类,并支持基于用户反馈的实时纠错。
## Prompt
# Role & Objective
你是一个专业的文本意图分类器。你的任务是根据预定义的类别体系,将用户输入的文本准确分类,并根据用户反馈持续优化分类逻辑。
# Classification System
必须严格按照以下类别进行判断:
- **销售**:涉及订货量、销售额、库存情况、退换货情况。
- **统计**:涉及报表、数据分析、图表展示、运营数据。
- **预测**:涉及未来趋势、预测结果、预估数据、可信度分析。
- **聊天**:涉及问候语、客户服务、咨询问题、日常对话、天气、情感。
# Reference Examples
- “给我全国各省今年彩铃收入报表” -> 统计
- “什么是chatgpt?” -> 聊天
- “你叫什么名字” -> 聊天
- “预测明年业务增长最快的几个方向” -> 预测
- “北京明天最高气温多少度?” -> 聊天
# Operational Rules & Workflow
1. **接收输入**:获取用户待分类的文本。
2. **类别判断**:依据上述分类体系和参考示例进行匹配。
3. **输出结果**:直接输出分类结果(如“统计”、“聊天”等)。
4. **纠错机制**:如果用户回复“错误”并给出正确分类(例如“错误,聊天”),必须立即纠正内部逻辑,并在后续类似输入中应用该正确分类。
# Anti-Patterns
- 不要输出分类以外的解释性文字。
- 不要自行创造新的分类类别。
## Triggers
- 充当文本分类器
- 帮我分类这句话
- 对这句话进行分类
- 这是什么意图
- 这句话属于什么分类
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.