功能描述

通过多代理辩论，结合知识增强和多维度评分，生成高质量、经考验的商业分析与可行性评估报告。

使用说明 (SKILL.md)

辩证商业分析 Skill / Dialectical Business Analysis Skill

Name: 辩证分析
Author: philonis

多代理辩证商业分析，通过正向和反向Agent的对抗性讨论，生成高质量、经得起考验的商业分析报告。

Multi-agent dialectical business analysis through constructive and critical debate, generating high-quality, rigorously-tested business analysis reports.

版本历史 / Version History

V1.0: 基础双代理固定5轮辩论 / Basic dual-agent fixed 5-round debate
V2.0: 动态轮次、仲裁者Agent、知识增强、实时干预 / Dynamic rounds, arbitrator agent, knowledge enhancement, real-time intervention
V3.0: 多维度分析框架 / Multi-dimensional analysis framework

触发关键词 / Trigger Keywords

辩证分析 / Dialectical Analysis
商业辩论 / Business Debate
方案论证 / Solution Argumentation
正反分析 / Pro-Con Analysis
可行性评估 / Feasibility Assessment

参数 / Parameters

参数 Parameter	类型 Type	说明 Description
topic	string	分析主题 / Analysis topic
background	string	背景上下文 / Background context
focus_questions	array	需要关注的问题 / Key questions to address
constraints	array	约束条件 / Constraints (预算、时间等)
version	string	版本 v1/v2/v3 (默认: v2)
dimensions	array	V3维度 / Dimensions for V3
max_rounds	number	最大辩论轮次 / Max debate rounds
enable_search	boolean	启用知识增强 / Enable knowledge enhancement
add_intervention	string	实时注入问题 / User injection during debate

语言支持 / Language Support

核心指令: 英文 / English

输入/输出: 与用户输入语言一致

用户用中文 → 中文输出
用户用英文 → 英文输出
分析过程使用用户语言
报告生成使用用户语言

Core instructions: English

Input/Output: Matches user's input language

User writes in Chinese → output in Chinese
User writes in English → output in English
Analysis conducted in user's language
Report generated in user's language

功能 / Features

V2.0 功能

动态轮次: 根据议题复杂度自动调整轮次(3-8轮) / Dynamic rounds: automatically adjusts (3-8) based on topic complexity
仲裁者Agent: 提供第三方客观总结 / Arbitrator agent: third-party objective summary
知识增强: 自动搜索行业数据( tavily/brave/ddg ) / Knowledge enhancement: auto-search industry data
实时干预: 用户可中途注入问题 / Real-time intervention: inject questions mid-debate

V3.0 功能

多维度分析: 技术-市场-财务-法律框架 / Multi-dimensional: Tech-Market-Finance-Legal framework
维度评分: 每维度1-10分 / Dimension scoring: 1-10 per dimension
加权评分: 自定义各维度权重 / Weighted scoring: custom weights per dimension

使用示例 / Usage Examples

中文示例

使用 Skill: dialectical-business-analysis
参数: topic=是否进入智能家居摄像头市场, background=公司专注软件研发..., focus_questions=["市场时机","竞争壁垒"], constraints=["预算2000万"]

English Example

Use Skill: dialectical-business-analysis
Params: topic=Should we enter the smart home camera market?, background=Company focuses on software R&D..., version=v2

命令行 / CLI

python3 dialectic_runner.py --topic "分析主题" --version v2
python3 dialectic_runner.py --topic "Should we enter X market?" --version v3 --dimensions "tech,market,finance,legal"

配置 / Configuration

环境变量 / Environment Variables

变量 Variable	说明 Description
TAVILY_API_KEY	Tavily搜索API密钥 (推荐) / Tavily search API key (recommended)
BRAVE_API_KEY	Brave Search API密钥 (备选) / Brave Search API key (fallback)

如未配置任一，skill将尝试ddg CLI备选。/ If neither is configured, skill will attempt ddg CLI fallback.

架构 / Architecture

┌─────────────────────────────────────┐
│         主协调器 Main Orchestrator  │
│  - 辩论协调 / Debate coordination    │
│  - 收敛检测 / Convergence detection │
│  - 报告生成 / Report generation     │
└─────────────────────────────────────┘
         ↑                    ↑
    ┌────┴────┐          ┌────┴────┐
    │   正向   │◄────────►│   反向   │
    │  Pro    │  辩论    │   Con   │
    └─────────┘          └─────────┘
    
    可选 / Optional:
    ┌─────────────┐
    │  仲裁者     │ (V2+)
    │  Arbitrator │
    └─────────────┘
    
    知识增强 / Knowledge:
    ┌─────────────┐
    │   Tavily   │ (V2+)
    │   Search   │
    └─────────────┘

需求 / Requirements

Python 3.8+
OpenClaw框架 / OpenClaw framework
可选: Tavily API密钥用于知识增强 / Optional: Tavily API key for knowledge enhancement

备注 / Notes

知识增强需要配置API密钥 / Knowledge enhancement requires API key configuration
默认轮次: 5轮(V1), 3-8动态(V2+) / Default rounds: 5 (V1), 3-8 dynamic (V2+)
满足收敛条件时辩论自动结束 / Debate automatically ends when convergence conditions met
最终报告包含共识、分歧和建议 / Final report includes consensus, disagreements, and recommendations

运行时依赖 / Runtime Dependencies

必需 / Required

Python 3.8+

可选搜索功能 / Optional (Search Feature)

如需启用知识增强功能，需要以下任一配置：

依赖	说明	获取方式
TAVILY_API_KEY	Tavily搜索API（推荐）	https://tavily.com
BRAVE_API_KEY	Brave Search API	https://brave.com/search/api
ddg CLI	DuckDuckGo命令行工具	`brew install ddg`

注意：如未配置任何API，搜索功能将尝试使用免费的DuckDuckGo HTML接口（无需配置）。

安全说明

所有搜索逻辑已内置，不依赖外部Skill
搜索仅在用户明确启用时运行
不执行任何外部脚本

安全使用建议

This skill appears coherent with its purpose. Before installing or invoking it, consider: (1) Knowledge enhancement will send your topic, background, and constraints to external search services (Tavily, Brave, or DuckDuckGo HTML) if you enable it — do not enable search for sensitive or confidential topics unless you trust the external service and its privacy policy. (2) If you prefer not to send data externally, run with enable_search=false (the skill still functions without search). (3) Ensure your environment has the Python 'requests' package if you plan to use Tavily/Brave APIs. (4) The skill stores session files under its own workspace directory (inside the skill folder); review those files if you want to remove traces. (5) If you supply API keys, treat them as sensitive credentials and confirm the target API endpoints (e.g., tavily.com) before providing keys. Overall the skill is internally consistent; these notes are privacy and dependency cautions rather than indicators of malicious behavior.

功能分析

Type: OpenClaw Skill Name: dialectical-analysis Version: 3.0.1 The skill bundle implements a multi-agent dialectical business analysis framework. The core logic in `dialectic_runner.py` manages a structured debate between 'Pro' and 'Con' agents, including a complexity analyzer and a knowledge enhancement module that utilizes legitimate search APIs (Tavily, Brave) or DuckDuckGo scraping. The system prompts and templates are strictly aligned with the stated purpose of business analysis and contain no evidence of prompt injection, data exfiltration, or unauthorized execution. File operations are confined to a local workspace directory, and the code lacks any malicious indicators such as obfuscation or persistence mechanisms.

能力评估

✓ Purpose & Capability

Name/description (dialectical business analysis) match the included code and prompts: orchestrator, pro/con/arbitrator agents, multi‑dimensional framework, and optional knowledge enhancement. Requested/used resources (Tavily/Brave/DDG search) align with the 'knowledge enhancement' feature.

ℹ Instruction Scope

SKILL.md and the runner are focused on debate orchestration and report generation. Important note: when enable_search is true, the skill sends user-provided topic/background/constraints as search queries to external search APIs (Tavily, Brave, or DuckDuckGo HTML). SKILL.md states search runs only when explicitly enabled, which matches the code.

✓ Install Mechanism

No install spec — instruction-only skill with an included Python runner. No downloads or archive extraction. This is low risk from an install perspective. The package relies on standard Python usage; no installer behavior observed.

ℹ Credentials

The skill optionally reads TAVILY_API_KEY and BRAVE_API_KEY from environment variables — proportionate to its optional search feature. Two implementation notes: (1) the code uses the 'requests' library when calling those APIs but 'requests' is not declared as a required dependency in SKILL.md; (2) enabling search will transmit the user's input to third‑party endpoints, so sensitive data may be exposed to those services.

✓ Persistence & Privilege

always is false and the skill writes session state and artifacts only to a workspace directory under the skill folder. It does not request system‑wide config changes or other skills' credentials. No elevated persistence or privileges detected.

版本历史

v3.0.1

## Changelog for dialectical-analysis v3.0.1 - Removed two files: input.json and state.json, likely related to temporary or intermediate process data. - No changes to core logic, interfaces, or features. - The skill’s documented usage, configuration, and capabilities remain unchanged.

v3.0.0

Changelog - dialectical-analysis v3.0.0. v3.0.0 (2026-03-13) - 安全修复版 / Security Fix Release 🔒 安全改进 / Security Improvements ✅ 移除外部脚本依赖: 不再调用 ~/.openclaw/workspace/skills/tavily-search/scripts/search.mjs Removed external script dependency: No longer executes scripts from external skill directories ✅ 内置搜索逻辑: 所有搜索功能完全内置，不依赖任何外部Skill Built-in search: All search logic is now self-contained ✅ 移除CLI依赖: 移除对 ddg CLI 的调用 Removed CLI dependency: No longer requires external CLI tools ✅ 明确运行时声明: SKILL.md 中完整声明所有可选依赖 Clear runtime documentation: All optional dependencies documented in SKILL.md ✅ 增加免费Fallback: 无需任何API Key也可使用DuckDuckGo HTML搜索 Free fallback: DuckDuckGo HTML search available without any API keys

v2.0.0

Initial release of dialectical-analysis skill. - Enables dual-agent dialectical business analysis with a fixed 5-round debate format. - Produces rigorous business analysis reports through constructive and critical agent discussion. - Supports both English and Chinese language input and output. - Allows specification of analysis topic, background, focus questions, and constraints.

元数据

Slug dialectical-analysis

版本 3.0.1

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 3

常见问题

辩证分析是什么？

通过多代理辩论，结合知识增强和多维度评分，生成高质量、经考验的商业分析与可行性评估报告。它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 269 次。

如何安装辩证分析？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install dialectical-analysis」即可一键安装，无需额外配置。

辩证分析是免费的吗？

是的，辩证分析完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

辩证分析支持哪些平台？

辩证分析跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了辩证分析？

由 philonis（@philonis）开发并维护，当前版本 v3.0.1。

辩证分析