← 返回 Skills 市场
nidhov01

06 AI总结

作者 nidhov01 · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
238
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install 06-ai
功能描述
AI智能内容总结和项目复盘工具,支持多个大模型API
使用说明 (SKILL.md)

AI总结复盘技能 v2.0 - 增强版

智能内容总结和项目复盘工具,支持多个大模型API,提供AI增强的总结能力。

技能描述

在基础总结功能之上,支持多个大模型API(智谱AI、OpenAI、Claude、DeepSeek、通义千问、Moonshot),提供更强大的AI总结和复盘能力。当无API时自动降级到基础总结。

使用场景

  • 用户:"用AI总结今天的工作" → AI智能提取关键要点
  • 用户:"用GPT-4复盘这个项目" → 深度分析项目经验
  • 用户:"用Claude总结这篇文章" → 高质量文章总结
  • 用户:"对比不同模型的总结效果" → 多模型对比

工具和依赖

工具列表

  • scripts/summary_review_llm.py:AI增强总结复盘模块

API密钥

可选(有API时AI增强,无API时降级到基础总结):

# 智谱AI(推荐,性价比高)
export ZHIPU_API_KEY="your-key"

# OpenAI
export OPENAI_API_KEY="your-key"

# Anthropic Claude
export ANTHROPIC_API_KEY="your-key"

# DeepSeek
export DEEPSEEK_API_KEY="your-key"

# 通义千问
export DASHSCOPE_API_KEY="your-key"

# Moonshot
export MOONSHOT_API_KEY="your-key"

外部依赖

  • Python 3.7+
  • openai(使用OpenAI时)
  • anthropic(使用Claude时)

配置说明

API密钥获取

智谱AI(推荐):

  1. 访问:https://open.bigmodel.cn/usercenter/apikeys
  2. 创建新的API密钥
  3. 新用户有免费额度

OpenAI

  1. 访问:https://platform.openai.com/api-keys
  2. 创建API密钥

Anthropic Claude

  1. 访问:https://console.anthropic.com/
  2. 获取API密钥

配置文件

创建 ~/.ai_llm_config.json

{
  "zhipu": {
    "api_key": "your-zhipu-key"
  },
  "openai": {
    "api_key": "your-openai-key"
  }
}

使用示例

基本用法

from summary_review_llm import AISummaryReview

# 使用智谱AI
system = AISummaryReview(provider="zhipu")

# 内容总结
summary = system.summarize_content(
    "今天完成了用户模块开发...",
    content_type="daily",
    title="工作日报"
)

# 项目复盘
review = system.review_project({
    'name': 'AI助手项目',
    'goals': ['实现对话', '添加知识库'],
    'results': ['对话已实现', '知识库完成80%']
})

场景1:使用智谱AI总结

用户:"用智谱AI总结我的日报"

AI:

system = AISummaryReview(provider="zhipu")
summary = system.summarize_content(daily_content, 'daily', '工作日报')
# 使用GLM-4模型进行智能总结

场景2:切换模型

用户:"用Claude总结这篇文章"

AI:

system_claude = AISummaryReview(provider="anthropic")
summary = system_claude.summarize_content(article, 'article', '文章标题')
# 使用Claude模型进行总结

场景3:无API时自动降级

用户:"总结这段内容"(未配置API)

AI:

system = AISummaryReview(provider="zhipu")
result = system.summarize_content(content, 'daily')
# 检测到无API密钥,自动降级到基础总结
# result['method'] = 'basic'

场景4:对比不同模型

用户:"对比智谱和Claude的总结效果"

AI:

providers = ['zhipu', 'anthropic']
for p in providers:
    system = AISummaryReview(provider=p)
    result = system.summarize_content(content)
    print(f"{p}: {result['summary'][:100]}...")

支持的总结类型

类型 说明 AI提示优化
daily 日报 ✓ 提取任务/问题/计划
meeting 会议记录 ✓ 提取议题/决策/行动
project 项目总结 ✓ 目标/经验/问题
article 文章总结 ✓ 观点/论据/结论
general 通用内容 ✓ 关键要点提取

故障排除

问题1:API调用失败

现象:提示API错误

解决

  1. 检查API密钥是否正确
  2. 确认API配额充足
  3. 检查网络连接
  4. 或使用其他提供商

问题2:无API时能否使用

现象:没有配置API密钥

解决

  • 可以!系统会自动降级到基础总结功能
  • 虽然总结质量略低,但仍可用

问题3:如何获取智谱API密钥

现象:不知道如何获取密钥

解决

  1. 访问:https://open.bigmodel.cn/usercenter/apikeys
  2. 注册账号
  3. 创建API密钥
  4. 新用户有免费额度

v1.0 vs v2.0 对比

功能 v1.0 (基础版) v2.0 (增强版)
总结方式 规则提取 AI智能总结
支持模型 智谱/OpenAI/Claude等
复盘质量 基础统计 AI深度分析
API依赖 可选(有API时AI增强)
降级方案 - ✓ 无API时自动降级

注意事项

  1. API选择:智谱AI性价比高,新用户有免费额度
  2. 自动降级:无API时仍可使用基础总结功能
  3. 成本控制:注意API使用量,避免超额费用
  4. 版本兼容:与v1.0数据库兼容
  5. 模型切换:切换模型无需重新安装,只需修改provider参数
安全使用建议
This skill appears to implement summarization and project review as advertised, but it depends on external components that are not included in the package: specifically llm_client (UniversalLLMClient) and references to ../llm_config.py. Before installing or running it, inspect or obtain the implementation of llm_client and llm_config.py to verify where requests go and how API keys are handled. Treat any API keys you provide as sensitive: prefer creating limited-scope/test keys, run the skill in an isolated environment, and monitor network activity. If you cannot review the external client, consider this incoherent dependency a risk and avoid providing real credentials or running it with sensitive data.
功能分析
Type: OpenClaw Skill Name: 06-ai Version: 1.0.0 The skill bundle is a legitimate tool for AI-driven content summarization and project review, supporting multiple LLM providers like Zhipu, OpenAI, and Claude. The code in `summary_review_llm.py` implements standard features including local SQLite storage for history, Markdown export, and a non-AI fallback mechanism. No evidence of data exfiltration, malicious execution, or prompt injection was found; the installation script `install.sh` and the main logic follow expected patterns for a modular AI agent skill.
能力评估
Purpose & Capability
Name/description match functionality: summarization and project review. The code and SKILL.md legitimately request optional LLM API keys (zhipu/openai/anthropic/etc.) for enhanced behavior. However, the packaged code imports UniversalLLMClient from a non-included module (llm_client) and the install/usage text references ../llm_config.py — indicating the skill expects external components not bundled with the skill. That dependency mismatch is unexpected and reduces coherence.
Instruction Scope
SKILL.md and code instruct creating ~/.ai_llm_config.json and possibly running ../llm_config.py; summary_review_llm.py writes a sqlite DB to the user's home (~/.ai_summary.db). The code does not reference unrelated system files, but the import of an external UniversalLLMClient means runtime behavior (network endpoints, telemetry, how API keys are used) is delegated to that external component. Because that client implementation is not included, the skill's runtime scope is underspecified and could permit unreviewed network transmissions of data or credentials.
Install Mechanism
No remote downloads or obscure installers. install.sh uses pip to install public packages (openai, optionally anthropic) and creates a run.sh wrapper. requirements.txt lists public packages. This is a low-risk install approach, but it does install network-capable SDKs which will use any API keys provided.
Credentials
The skill declares no required env vars and lists several optional API keys (ZHIPU/OpenAI/ANTHROPIC/DEEPSEEK/DASHSCOPE/MOONSHOT) which are consistent with multi-LLM support. Requesting multiple model API keys is reasonable here, but those are sensitive secrets; the package will attempt to use whatever provider keys are present, and because the UniversalLLMClient implementation is not included, it's unclear exactly how keys are stored/used/transmitted.
Persistence & Privilege
The skill is not always-enabled, is user-invocable, and doesn't request elevated privileges. It does create and use a local sqlite DB at ~/.ai_summary.db and a config file at ~/.ai_llm_config.json — expected for a summarization tool but worth noting as persistent data written to the user's home directory.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install 06-ai
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /06-ai 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
**v2.0.0 is a major upgrade: Adds multi-LLM support and AI-enhanced summarization with fallback.** - Supports multiple AI model providers (Zhipu, OpenAI, Claude, DeepSeek, Dashscope, Moonshot) for smarter content summarization and project reviews. - Introduces automatic fallback to basic summarization when API keys are unavailable. - Adds API key configuration and usage instructions; options for cost-effective providers and how to use free quotas. - Provides code samples for switching models, doing comparative results, and typical use cases. - Remains backward compatible with data from v1.0; no installation changes required to switch models. - Enhanced documentation on troubleshooting, supported summary types, and configuration steps.
元数据
Slug 06-ai
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

06 AI总结 是什么?

AI智能内容总结和项目复盘工具,支持多个大模型API. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 238 次。

如何安装 06 AI总结?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install 06-ai」即可一键安装,无需额外配置。

06 AI总结 是免费的吗?

是的,06 AI总结 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

06 AI总结 支持哪些平台?

06 AI总结 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 06 AI总结?

由 nidhov01(@nidhov01)开发并维护,当前版本 v1.0.0。

💬 留言讨论